1
|
Fokin AA, Wycech Knight J, Gallagher PK, Xie JF, Brinton KC, Tharp ME, Puente I. Characteristics and outcomes of trauma patients with unplanned intensive care unit admissions: Bounce backs and upgrades comparison. World J Crit Care Med 2025; 14:101957. [DOI: 10.5492/wjccm.v14.i2.101957] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/03/2024] [Revised: 11/21/2024] [Accepted: 12/09/2024] [Indexed: 02/27/2025] Open
Abstract
BACKGROUND The need for an emergency upgrade of a hospitalized trauma patient from the floor to the trauma intensive care unit (ICU) is an unanticipated event with possible life-threatening consequences. Unplanned ICU admissions are associated with increased morbidity and mortality and are an indicator of trauma service quality. Two different types of unplanned ICU admissions include upgrades (patients admitted to the floor then moved to the ICU) and bounce backs (patients admitted to the ICU, discharged to the floor, and then readmitted to the ICU). Previous studies have shown that geriatric trauma patients are at higher risk for unfavorable outcomes.
AIM To analyze the characteristics, management and outcomes of trauma patients who had an unplanned ICU admission during their hospitalization.
METHODS This institutional review board approved, retrospective cohort study examined 203 adult trauma patients with unplanned ICU admission at an urban level 1 trauma center over a six-year period (2017-2023). This included 134 upgrades and 69 bounce backs. Analyzed variables included: (1) Age; (2) Sex; (3) Comorbidities; (4) Mechanism of injury (MOI); (5) Injury severity score (ISS); (6) Glasgow Coma Scale (GCS); (7) Type of injury; (8) Transfusions; (9) Consultations; (10) Timing and reason for unplanned admission; (11) Intubations; (12) Surgical interventions; (13) ICU and hospital lengths of stay; and (14) Mortality.
RESULTS Unplanned ICU admissions comprised 4.2% of total ICU admissions. Main MOI was falls. Mean age was 70.7 years, ISS was 12.8 and GCS was 13.9. Main injuries were traumatic brain injury (37.4%) and thoracic injury (21.7%), and main reason for unplanned ICU admission was respiratory complication (39.4%). The 47.3% underwent a surgical procedure and 46.8% were intubated. Average timing for unplanned ICU admission was 2.9 days. Bounce backs occurred half as often as upgrades, however had higher rates of transfusions (63.8% vs 40.3%, P = 0.002), consultations (4.8 vs 3.0, P < 0.001), intubations (63.8% vs 38.1%%, P = 0.001), longer ICU lengths of stay (13.2 days vs 6.4 days, P < 0.001) and hospital lengths of stay (26.7 days vs 13.0 days, P < 0.001). Mortality was 25.6% among unplanned ICU admissions, 31.9% among geriatric unplanned ICU admissions and 11.9% among all trauma ICU patients.
CONCLUSION Unplanned ICU admissions constituted 4.2% of total ICU admissions. Respiratory complications were the main cause of unplanned ICU admissions. Bounce backs occurred half as often as upgrades, but were associated with worse outcomes.
Collapse
Affiliation(s)
- Alexander A Fokin
- Department of Trauma and Critical Care Services, Delray Medical Center, Delray Beach, FL 33484, United States
- Department of Surgery, Florida Atlantic University Charles E Schmidt College of Medicine, Boca Raton, FL 33431, United States
| | - Joanna Wycech Knight
- Department of Trauma and Critical Care Services, Delray Medical Center, Delray Beach, FL 33484, United States
- Department of Trauma and Critical Care Services, Broward Health Medical Center, Fort Lauderdale, FL 33316, United States
| | - Phoebe K Gallagher
- Department of Trauma and Critical Care Services, Delray Medical Center, Delray Beach, FL 33484, United States
- Department of Surgery, Florida Atlantic University Charles E Schmidt College of Medicine, Boca Raton, FL 33431, United States
| | - Justin Fengyuan Xie
- Department of Trauma and Critical Care Services, Delray Medical Center, Delray Beach, FL 33484, United States
- Department of Surgery, Florida Atlantic University Charles E Schmidt College of Medicine, Boca Raton, FL 33431, United States
| | - Kyler C Brinton
- Department of Trauma and Critical Care Services, Delray Medical Center, Delray Beach, FL 33484, United States
- Department of Surgery, Florida Atlantic University Charles E Schmidt College of Medicine, Boca Raton, FL 33431, United States
| | - Madison E Tharp
- Department of Trauma and Critical Care Services, Delray Medical Center, Delray Beach, FL 33484, United States
- Department of Surgery, Florida Atlantic University Charles E Schmidt College of Medicine, Boca Raton, FL 33431, United States
| | - Ivan Puente
- Department of Trauma and Critical Care Services, Delray Medical Center, Delray Beach, FL 33484, United States
- Department of Surgery, Florida Atlantic University Charles E Schmidt College of Medicine, Boca Raton, FL 33431, United States
- Department of Trauma and Critical Care Services, Broward Health Medical Center, Fort Lauderdale, FL 33316, United States
- Department of Surgery, Florida International University Herbert Wertheim College of Medicine, Miami, FL 33199, United States
| |
Collapse
|
2
|
Moin EE, Seewald NJ, Halpern SD. Use of Life Support and Outcomes Among Patients Admitted to Intensive Care Units. JAMA 2025; 333:1793-1803. [PMID: 40227733 PMCID: PMC11997855 DOI: 10.1001/jama.2025.2163] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/21/2024] [Accepted: 02/11/2025] [Indexed: 04/15/2025]
Abstract
Importance Nationwide data are unavailable regarding changes in intensive care unit (ICU) outcomes and use of life support over the past 10 years, limiting understanding of practice changes. Objective To portray the epidemiology of US critical care before, during, and after the COVID-19 pandemic. Design, Setting, and Participants Retrospective cohort study of adult patients admitted to an ICU for any reason, using data from the 54 US health systems continuously contributing to the Epic Cosmos database from 2014-2023. Exposures Patient demographics, COVID-19 status, and pandemic era. Main Outcomes and Measures In-hospital mortality unadjusted and adjusted for patient demographics, comorbidities, and illness severity; ICU length of stay; and receipt of life-support interventions, including mechanical ventilation and vasopressor medications. Results Of 3 453 687 admissions including ICU care, median age was 65 (IQR, 53-75) years. Patients were 55.3% male; 17.3% Black and 6.1% Hispanic or Latino; and overall in-hospital mortality was 10.9%. The adjusted in-hospital mortality was elevated during the pandemic in COVID-negative (adjusted odds ratio [aOR], 1.3 [95% CI, 1.2-1.3]) and COVID-positive (aOR, 4.3 [95% CI, 3.8-4.8]) patients and returned to baseline by mid-2022. The median ICU length of stay was 2.1 (IQR, 1.1-4.2) days, with increases during the pandemic among COVID-positive patients (difference for COVID-positive vs COVID-negative patients, 2.0 days [95% CI, 2.0-2.1]). Rates of invasive mechanical ventilation were 23.2% (95% CI, 23.1%-23.2%) before the pandemic, increased to 25.8% (95% CI, 25.8%-25.9%) during the pandemic, and declined below prepandemic baseline thereafter (22.0% [95% CI, 21.9%-22.2%]). The use of vasopressors increased from 7.2% to 21.6% of ICU stays. Conclusions and Relevance Pandemic-era increases in length of stay and adjusted in-hospital mortality among US ICU patients returned to recent historical baselines. Fewer patients are now receiving mechanical ventilation than prior to the pandemic, while more patients are administered vasopressor medications.
Collapse
Affiliation(s)
- Emily E. Moin
- Division of Pulmonary, Allergy, and Critical Care, University of Pennsylvania, Philadelphia
- Palliative and Advanced Illness Research (PAIR) Center, University of Pennsylvania, Philadelphia
| | - Nicholas J. Seewald
- Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania, Philadelphia
| | - Scott D. Halpern
- Division of Pulmonary, Allergy, and Critical Care, University of Pennsylvania, Philadelphia
- Palliative and Advanced Illness Research (PAIR) Center, University of Pennsylvania, Philadelphia
- Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania, Philadelphia
| |
Collapse
|
3
|
Terrington I, Brown M, Pennell A, Smith A, Cox O, Beecham R, Dushianthan A. Evaluation of the physiological variables and scoring systems at intensive care discharge as predictors of clinical deterioration and readmission: a single-centre retrospective study. BMJ Open 2025; 15:e099352. [PMID: 40341150 PMCID: PMC12060887 DOI: 10.1136/bmjopen-2025-099352] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/15/2025] [Accepted: 04/25/2025] [Indexed: 05/10/2025] Open
Abstract
OBJECTIVES We aim to determine, using routinely collected data and common scoring systems, whether parameters seen at intensive care unit (ICU) discharge can be predictive of subsequent clinical deterioration. DESIGN/SETTING A single-centre retrospective study located in a tertiary hospital in the south of England. PARTICIPANTS 1868 patients who were admitted and discharged from ICU between 1 April 2023 and 31 March 2024 were screened for eligibility. A total of 1393 patients were included in the final analysis, including 122 patients who were classified in the 'deteriorated' subgroup. INTERVENTIONS Assessment of vital signs, blood markers of infection and inflammation and three scoring systems (National Early Warning Score 2 (NEWS2), Acute Physiology and Chronic Health Evaluation II Score and Sequential Organ Failure Assessment (SOFA) score) taken within 24 hours prior to ICU discharge. PRIMARY OUTCOMES Assessment of predictors of deterioration after ICU discharge. SECONDARY OUTCOMES Reasons for readmission to ICU, hospital mortality, ICU length of stay and time before readmission to ICU. RESULTS Heart rate, conscious level (alert, voice, pain, unresponsive scale) and SOFA score were independent predictors of deterioration after ICU discharge (under the curve 0.85, CI 0.79 to 0.90, specificity 82.3%, sensitivity 79.7%) in multivariable models. Of these, a reduced level of consciousness was the most significant predictor of clinical deterioration (OR 19.6, CI 11.4 to 35.0). NEWS2 was an independent predictor for deterioration on univariable analysis. Mortality was significantly increased in patients who experienced deterioration after ICU discharge, as was ICU length of stay. CONCLUSIONS Predictive models may be useful in assisting clinicians with ICU discharge decisions. Further research is required to develop patient-tailored scoring systems that incorporate other factors that are needed for decisions around ICU discharge.
Collapse
Affiliation(s)
- Isis Terrington
- General Intensive Care Unit, University Hospital Southampton NHS Foundation Trust, Southampton, UK
| | - Mark Brown
- Perioperative and Critical Care Research Theme, Southampton National Institute of Health Research Biomedical Research Centre (NIHR), University Hospital Southampton NHS Foundation Trust, Southampton, UK
| | - Amelia Pennell
- School of Electronics and Computer Science, University of Southampton, Southampton, UK
| | - Alexander Smith
- Department of Emergency Medicine, University Hospital Southampton NHS Foundation Trust, Southampton, UK
| | - Olivia Cox
- General Intensive Care Unit, University Hospital Southampton NHS Foundation Trust, Southampton, UK
| | - Ryan Beecham
- General Intensive Care Unit, University Hospital Southampton NHS Foundation Trust, Southampton, UK
| | - Ahilanandan Dushianthan
- General Intensive Care Unit, University Hospital Southampton NHS Foundation Trust, Southampton, UK
- Perioperative and Critical Care Research Theme, Southampton National Institute of Health Research Biomedical Research Centre (NIHR), University Hospital Southampton NHS Foundation Trust, Southampton, UK
- Integrative Physiology and Critical Illness Group, Clinical and Experimental Sciences, Faculty of Medicine, University of Southampton Faculty of Medicine, Southampton, England, UK
| |
Collapse
|
4
|
Lim L, Kim M, Cho K, Yoo D, Sim D, Ryu HG, Lee HC. Multicenter validation of a machine learning model to predict intensive care unit readmission within 48 hours after discharge. EClinicalMedicine 2025; 81:103112. [PMID: 40034564 PMCID: PMC11872568 DOI: 10.1016/j.eclinm.2025.103112] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/16/2024] [Revised: 01/16/2025] [Accepted: 01/29/2025] [Indexed: 03/05/2025] Open
Abstract
Background Intensive care unit (ICU) readmission is a crucial indicator of patient safety. However, discharge decisions often rely on subjective assessment due to a lack of standardized guidelines. We aimed to develop a machine-learning model to predict ICU readmission within 48 h and compare its performance to traditional scoring systems. Methods We developed an ensemble model, iREAD, that generates a probability score at ICU discharge, representing the likelihood of the patient being readmitted to the ICU within 48 h, using data from Seoul National University Hospital (SNUH) and validated it using the MIMIC-III and eICU-CRD datasets. From September 2007 to August 2021, a total of 70,842 patients were included from SNUH. The MIMIC-III datasets comprised 43,237 patients admitted to ICUs between 2001 and 2012 at Beth Israel Deaconess Medical Center, and the eICU-CRD datasets included 90,271 ICU admissions across 208 hospitals between 2014 and 2015. Patients younger than 18, those who died in ICUs, or who refused life-sustaining treatment were excluded from the final analysis. The model's performance was evaluated using the area under the receiver operating characteristic curve (AUROC) and compared to the traditional scores and conventional machine learning models. Kaplan-Meier analysis was performed to compare the outcome between the high-risk and low-risk groups. Findings We developed the iREAD, that utilized 30 input features, encompassing demographics, length of stay, vital signs, GCS, and laboratory values. iREAD demonstrated superior performance compared with other models across all cohorts (all P < 0.001). In the internal validation, iREAD achieved AUROCs of 0.771 (95% CI 0.743-0.798), 0.834 (0.821-0.846), and 0.820 (0.808-0.832) for early (≤48 h), late (>48 h), and overall ICU readmissions, respectively. External validations with MIMIC-III and eICU-CRD also showed modest performance with AUROCs of 0.768 (0.748-0.787) and 0.725 (0.712-0.739) for overall readmission in MIMIC-III and eICU-CRD respectively, demonstrating superior performance compared to other models (All P < 0.001; higher than other models). Kaplan-Meier analysis revealed that over 40% of high-risk patients predicted by iREAD were readmitted within 48 h, representing a more than four-fold increase in predictive performance compared to the traditional scores. Interpretation iREAD demonstrates superior performance in predicting ICU readmission within 48 h after discharge compared to traditional scoring systems or conventional machine learning models in both internal and external validations. While the performance degradation observed in the external validations suggests the need for further prospective validation on diverse patient populations, the robust performance and ability to identify high-risk patients have the potential to guide clinical decision-making. Funding This work was supported by the Korea Health Technology Research & Development Project through the Korea Health Industry Development Institute, funded by the Ministry of Health and Welfare, Republic of Korea (grant number RS-2021-KH114109).
Collapse
Affiliation(s)
- Leerang Lim
- Department of Anesthesiology and Pain Medicine, Seoul National University College of Medicine, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Republic of Korea
| | - Mincheol Kim
- VUNO, 479 Gangnam-daero, Seocho-gu, Seoul, 06541, Republic of Korea
- Department of Digital Health, Samsung Advanced Institute for Health Sciences & Technology, Sungkyunkwan University, 115 Irwon-ro, Gangnam-gu, Seoul, 06351, Republic of Korea
| | - Kyungjae Cho
- VUNO, 479 Gangnam-daero, Seocho-gu, Seoul, 06541, Republic of Korea
| | - Dongjoon Yoo
- VUNO, 479 Gangnam-daero, Seocho-gu, Seoul, 06541, Republic of Korea
- Department of Critical Care Medicine and Emergency Medicine, Inha University College of Medicine, 100 Inha-ro, Michuhol-gu, Incheon, 22212, Republic of Korea
| | - Dayeon Sim
- Department of Anesthesiology and Pain Medicine, Seoul National University College of Medicine, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Republic of Korea
| | - Ho Geol Ryu
- Department of Anesthesiology and Pain Medicine, Seoul National University College of Medicine, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Republic of Korea
- Department of Critical Care Medicine, Seoul National University College of Medicine, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Republic of Korea
| | - Hyung-Chul Lee
- Department of Anesthesiology and Pain Medicine, Seoul National University College of Medicine, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Republic of Korea
| |
Collapse
|
5
|
Tschoellitsch T, Maletzky A, Moser P, Seidl P, Böck C, Tomic Mahečić T, Thumfart S, Giretzlehner M, Hochreiter S, Meier J. Machine learning prediction of unexpected readmission or death after discharge from intensive care: A retrospective cohort study. J Clin Anesth 2024; 99:111654. [PMID: 39405923 DOI: 10.1016/j.jclinane.2024.111654] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2024] [Revised: 09/03/2024] [Accepted: 10/08/2024] [Indexed: 11/26/2024]
Abstract
BACKGROUND Intensive care units (ICUs) harbor the sickest patients with the utmost needs of medical care. Discharge from ICU needs to consider the reason for admission and stability after ICU care. Organ dysfunction or instability after ICU discharge constitute potentially life-threatening situations for patients. METHODS This is a single center, observational, retrospective cohort study conducted at ICUs at the Kepler University Hospital in Linz, Austria. Patients aged 18 years and above admitted to the study center's ICUs between 2010-01-01 and 2019-10-31 were included in the study. Patients transferred to another ICU, discharged to a different hospital or home, or that died during their ICU stay were excluded. We used machine learning (ML) models to predict unplanned ICU readmission or death using an internal dataset or MIMIC-IV as training data and compared the models with the Stability and Workload Index for Transfer (SWIFT) score. Further, we evaluated the influence of features on the models using Shapley Additive Explanations. RESULTS The best ML models achieved an area under the curve of the receiver operating characteristic (AUC-ROC) of 0.721 ± 0.029 and a high negative predictive value (NPV) of 0.990 ± 0.002. The most important features were heart rate, peripheral oxygen saturation and arterial blood pressure. Performance of the SWIFT score was worse than the ML models (best AUC-ROC 0.618 ± 0.011). CONCLUSIONS ML models were able to identify patients that will not need unplanned ICU readmission and will not die within 48 h after discharge.
Collapse
Affiliation(s)
- Thomas Tschoellitsch
- Department of Anesthesiology and Critical Care Medicine, Johannes Kepler University Linz and Kepler University Hospital, Linz, Austria.
| | - Alexander Maletzky
- Research Unit Medical Informatics, RISC Software GmbH, Hagenberg i. M., Austria.
| | - Philipp Moser
- Research Unit Medical Informatics, RISC Software GmbH, Hagenberg i. M., Austria.
| | - Philipp Seidl
- European Laboratory for Learning and Intelligent Systems Unit Linz, Linz Institute of Technology Artificial Intelligence Lab, Institute for Machine Learning, Johannes Kepler University, Linz, Austria.
| | - Carl Böck
- Institute of Signal Processing, Johannes Kepler University Linz, Austria.
| | - Tina Tomic Mahečić
- Clinic of Anaesthesiology and Intensive Care Medicine, University Hospital Centre Zagreb - Rebro, Croatia.
| | - Stefan Thumfart
- Research Unit Medical Informatics, RISC Software GmbH, Hagenberg i. M., Austria.
| | - Michael Giretzlehner
- Research Unit Medical Informatics, RISC Software GmbH, Hagenberg i. M., Austria.
| | - Sepp Hochreiter
- European Laboratory for Learning and Intelligent Systems Unit Linz, Linz Institute of Technology Artificial Intelligence Lab, Institute for Machine Learning, Johannes Kepler University, Linz, Austria.
| | - Jens Meier
- Department of Anesthesiology and Critical Care Medicine, Johannes Kepler University Linz and Kepler University Hospital, Linz, Austria.
| |
Collapse
|
6
|
Moore B, Daniels KJ, Martinez B, Sexton KW, Kalkwarf KJ, Roberts M, Bowman SM, Jensen HK. Intensive Care Unit Readmissions in a Level I Trauma Center. J Surg Res 2024:S0022-4804(24)00638-3. [PMID: 39490383 DOI: 10.1016/j.jss.2024.09.074] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/29/2024] [Revised: 08/22/2024] [Accepted: 09/16/2024] [Indexed: 11/05/2024]
Abstract
INTRODUCTION Intensive care unit (ICU) readmissions are associated with increased morbidity and mortality rates, longer hospitalization, and increased health-care expenditures. This study sought to present a large cohort of trauma patients readmitted to the ICU, characterizing risk factors and providing quality improvement strategies to limit ICU readmission. METHODS A retrospective cohort analysis was conducted on adult trauma patients admitted to the ICU at a single level I trauma center from 2014 to 2021. Patients were split into readmission and no readmission groups. Patients experiencing readmission were compared to a similar group that was not readmitted using descriptive statistics and logistic regression. RESULTS In this study, 3632 patients were included and 278 (7.7%) were readmitted to the ICU. Significant differences were found in age, Elixhauser Comorbidity score, number of days on a ventilator, and number of patients requiring ventilator support. Furthermore, logistic regression showed that increasing age and the Elixhauser Comorbidity Score were associated with an increased likelihood of ICU readmission. Over the study period, the ICU readmission rate increased while the ICU length decreased. CONCLUSIONS Age, Elixhauser Comorbidity score, and ventilator use were all significant risk factors for ICU readmission. During our study period, a concerning trend of increasing ICU readmissions and decreased ICU length of stay was found. By identifying this trend, our institution was able to employ mitigation strategies that have successfully reversed the trend in ICU readmissions, decreasing the rate below the national average.
Collapse
Affiliation(s)
- Benjamin Moore
- College of Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas
| | - Kacee J Daniels
- College of Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas
| | - Blake Martinez
- College of Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas
| | - Kevin W Sexton
- Division of Trauma and Acute Care Surgery, Department of Surgery, College of Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas; Department of Biomedical Informatics, College of Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas; College of Public Health, University of Arkansas for Medical Sciences, Little Rock, Arkansas
| | - Kyle J Kalkwarf
- Division of Trauma and Acute Care Surgery, Department of Surgery, College of Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas
| | - Matthew Roberts
- Division of Trauma and Acute Care Surgery, Department of Surgery, College of Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas
| | - Stephen M Bowman
- College of Public Health, University of Arkansas for Medical Sciences, Little Rock, Arkansas
| | - Hanna K Jensen
- Division of Trauma and Acute Care Surgery, Department of Surgery, College of Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas.
| |
Collapse
|
7
|
You SB. Ethical considerations in evaluating discharge readiness from the intensive care unit. Nurs Ethics 2024; 31:896-906. [PMID: 37950598 PMCID: PMC11370158 DOI: 10.1177/09697330231212338] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2023]
Abstract
Evaluating readiness for discharge from the intensive care unit (ICU) is a critical aspect of patient care. Whereas evidence-based criteria for ICU admission have been established, practical criteria for discharge from the ICU are lacking. Often discharge guidelines simply state that a patient no longer meets ICU admission criteria. Such discharge criteria can be interpreted differently by different healthcare providers, leaving a clinical void where misunderstandings of patients' readiness can conflict with perceptions of what readiness means for patients, families, and healthcare providers. In considering ICU discharge readiness, the use and application of ethical principles may be helpful in mitigating such conflicts and achieving desired patient outcomes. Ethical principles propose different ways of understanding what readiness might mean and how clinicians might weigh these principles in their decision-making process. This article examines the concept of discharge readiness through the lens of the most widely cited ethical principles (autonomy [respect for persons], nonmaleficence/beneficence, and justice) and provides a discussion of their application in the critical care environment. Ongoing bioethics discourse and empirical research are needed to identify factors that help determine discharge readiness within critical care environments that will ultimately promote safe and effective ICU discharges for patients and their families.
Collapse
Affiliation(s)
- Sang Bin You
- NewCourtland Center for Transitions and Health, University of Pennsylvania School of Nursing, Philadelphia, PA, USA
| |
Collapse
|
8
|
Kumar R, Singh BP, Arshad Z, Srivastava VK, Prakash R, Singh MK. Determinants of Readmission in the Intensive Care Unit: A Prospective Observational Study. Cureus 2024; 16:e62840. [PMID: 39036166 PMCID: PMC11260421 DOI: 10.7759/cureus.62840] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 06/21/2024] [Indexed: 07/23/2024] Open
Abstract
Background The antecedents of readmission among survivors of intensive care units (ICUs) are complex and comprise an array of elements that impact the rehabilitation process after leaving the ICU. The aforementioned determinants may comprise socioeconomic factors, access to follow-up healthcare, the nature and severity of the initial illness or injury, the presence of comorbidities, the sufficiency of transitional care and rehabilitation services, and patient and family support systems. Added to this, the risk of readmission may be increased by complications that develop during the ICU stay, including but not limited to infections, organ dysfunction, and psychological distress. Comprehending these determinants is of the utmost importance for healthcare providers in order to execute focused interventions that seek to diminish readmission rates, enhance patient outcomes, and elevate the standard of care for survivors of ICUs. Objective The objective of the study is to determine the factors associated with readmission among ICU survivors and the cause of readmission. Methodology This prospective observational study was conducted in a tertiary-level ICU. The duration of the study was one year and we enrolled 108 ICU survivors in our study. We have recorded patient demographic data, comorbidity, primary diagnosis, previous treatment history (vasopressor, sedation), causes of readmission, duration of previous ICU stay, and outcome of readmitted patient (discharge, death, and transfer to lower facility). Result The incidence of readmission in our ICU is 10.4%; 50-70 age groups are more prone to readmission of which the male sex is predominant (64.81%). In our study, hypertension (cardiac, 18.52%) and diabetes mellitus (11.11%) were the most common comorbidities reported in readmitted patients. The majority of patients who get readmission suffered from blunt trauma abdomen. In the majority of readmitted patients, sedation was used in the previous admission for ventilation and patient comfort (66.67%). Most of the readmitted patients (68.51%) have a previous ICU stay of more than five days. Patients were readmitted mainly because of respiratory (30.56%) and neurological (25%) complications. In this study, readmitted patients have high mortality (59.26%). Conclusion In a tertiary care ICU, the incidence rate of readmitted patients was 10.4%. Respiratory and neurological problems were the main cause of readmission. In readmitted patients, mortality was high up to 59.26%. Old age, male sex, prolonged ICU stay, comorbidities like hypertension, blunt trauma abdomen, use of sedation, and prolonged mechanical ventilation in previous ICU admission are major risk factors for ICU readmission.
Collapse
Affiliation(s)
- Ratnesh Kumar
- Anesthesiology and Critical Care, King George's Medical University, Lucknow, IND
| | - Brijesh P Singh
- Anesthesiology and Critical Care, King George's Medical University, Lucknow, IND
| | - Zia Arshad
- Anesthesiology and Critical Care, King George's Medical University, Lucknow, IND
| | - Vinod K Srivastava
- Anesthesiology and Critical Care, King George's Medical University, Lucknow, IND
| | - Ravi Prakash
- Anesthesiology and Critical Care, King George's Medical University, Lucknow, IND
| | - Manish K Singh
- Anesthesiology and Critical Care, King George's Medical University, Lucknow, IND
| |
Collapse
|
9
|
Lee J, Im C. Time-to-surgery paradigms: wait time and surgical outcomes in critically Ill patients who underwent emergency surgery for gastrointestinal perforation. BMC Surg 2024; 24:159. [PMID: 38760752 PMCID: PMC11100233 DOI: 10.1186/s12893-024-02452-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2024] [Accepted: 05/13/2024] [Indexed: 05/19/2024] Open
Abstract
BACKGROUND Waiting time for emergency abdominal surgery have been known to be linked to mortality. However, there is no clear consensus on the appropriated timing of surgery for gastrointestinal perforation. We investigated association between wait time and surgical outcomes in emergency abdominal surgery. METHODS This single-center retrospective cohort study evaluated adult patients who underwent emergency surgery for gastrointestinal perforations between January 2003 and September 2021. Risk-adjusted restricted cubic splines modeled the probability of each mortality according to wait time. The inflection point when mortality began to increase was used to define early and late surgery. Outcomes among propensity-score matched early and late surgical patients were compared using percent absolute risk differences (RDs, with 95% CIs). RESULTS Mortality rates began to rise after 16 h of waiting. However, early and late surgery groups showed no significant differences in 30-day mortality (11.4% vs. 5.7%), ICU stay duration (4.3 ± 7.5 vs. 4.3 ± 5.2 days), or total hospital stay (17.4 ± 17.0 vs. 24.7 ± 23.4 days). Notably, patients waiting over 16 h had a significantly higher ICU readmission rate (8.6% vs. 31.4%). The APACHE II score was a significant predictor of 30-day mortality. CONCLUSIONS Although we were unable to reveal significant differences in mortality in the subgroup analysis, we were able to find an inflection point of 16 h through the RCS curve technique. TRIAL REGISTRATION Formal consent was waived due to the retrospective nature of the study, and ethical approval was obtained from the institutional research committee of our institution (B-2110-714-107) on 6 October 2021.
Collapse
Affiliation(s)
- Junghyun Lee
- Department of Surgery, Yongin Severance Hostpital, Yongin, Korea
- Yonsei University College of Medicine, Seoul, Korea
| | - Chami Im
- Department of Surgery, Seoul National University Bundang Hospital, Seongnam, Korea.
- Seoul National University College of Medicine, Seoul, Korea.
| |
Collapse
|
10
|
Sharp EA, Wang L, Hall M, Berry JG, Forster CS. Frequency, Characteristics, and Outcomes of Patients Requiring Early PICU Readmission. Hosp Pediatr 2023; 13:678-688. [PMID: 37476936 PMCID: PMC10375031 DOI: 10.1542/hpeds.2022-007100] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/22/2023]
Abstract
OBJECTIVES Readmission to the PICU is associated with worse outcomes, but factors associated with PICU readmission within the same hospitalization remain unclear. We sought to describe the prevalence of, and identify factors associated with, early PICU readmission. METHODS We performed a retrospective analysis of PICU admissions for patients aged 0 to 26 years in 48 tertiary care children's hospitals between January 1, 2016 and December 31, 2019 in the Pediatric Health Information System. We defined early readmission as return to the PICU within 2 calendar days of floor transfer during the same hospitalization. Generalized linear mixed models were used to analyze associations between patient and clinical variables, including complex chronic conditions (CCC) and early PICU readmission. RESULTS The results included 389 219 PICU admissions; early PICU readmission rate was 2.5%. Factors with highest odds of early PICU readmission were CCC, with ≥4 CCCs (reference: no CCC[s]) as highest odds of readmission (adjusted odds ratio [95% confidence interval]: 4.2 [3.8-4.5]), parenteral nutrition (2.3 [2.1-2.4]), and ventriculoperitoneal shunt (1.9 [1.7-2.2]). Factors with decreased odds of PICU readmission included extracorporeal membrane oxygenation (0.4 [0.3-0.6]) and cardiopulmonary resuscitation (0.8 [0.7-0.9]). Patients with early PICU readmissions had longer overall length of stay (geometric mean [geometric SD]: 18.2 [0.9] vs 5.0 [1.1] days, P < .001) and increased odds of mortality (1.7 [1.5-1.9]). CONCLUSIONS Although early PICU readmissions within the same hospitalization are uncommon, they are associated with significantly worse clinical outcomes. Patients with medical complexity and technology dependence are especially vulnerable.
Collapse
Affiliation(s)
- Eleanor A. Sharp
- Department of Pediatrics, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania
| | - Li Wang
- Clinical and Translational Science Institute, Office of Clinical Research, University of Pittsburgh, Pittsburgh, Pennsylvania
| | - Matt Hall
- Children’s Hospital Association, Lenexa, Kansas
| | - Jay G. Berry
- Complex Care, Division of General Pediatrics, Department of Medicine, Boston Children’s Hospital, Harvard Medical School, Boston, Massachusetts
| | - Catherine S. Forster
- Department of Pediatrics, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania
| |
Collapse
|
11
|
Hachen M, Musy SN, Fröhlich A, Jeitziner MM, Kindler A, Perrodin S, Zante B, Zúñiga F, Simon M. Developing a reflection and analysis tool (We-ReAlyse) for readmissions to the intensive care unit: A quality improvement project. Intensive Crit Care Nurs 2023; 77:103441. [PMID: 37178615 DOI: 10.1016/j.iccn.2023.103441] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/06/2023] [Revised: 03/29/2023] [Accepted: 04/14/2023] [Indexed: 05/15/2023]
Abstract
BACKGROUND Readmissions to the intensive care unit are associated with poorer patient outcomes and health prognoses, alongside increased lengths of stay and mortality risk. To improve quality of care and patients' safety, it is essential to understand influencing factors relevant to specific patient populations and settings. A standardized tool for systematic retrospective analysis of readmissions would help healthcare professionals understand risks and reasons affecting readmissions; however, no such tool exists. PURPOSE This study's purpose was to develop a tool (We-ReAlyse) to analyze readmissions to the intensive care unit from general units by reflecting on affected patients' pathways from intensive care discharge to readmission. The results will highlight case-specific causes of readmission and potential areas for departmental- and institutional-level improvements. METHOD A root cause analysis approach guided this quality improvement project. The tool's iterative development process included a literature search, a clinical expert panel, and a testing in January and February 2021. RESULTS The We-ReAlyse tool guides healthcare professionals to identify areas for quality improvement by reflecting the patient's pathway from the initial intensive care stay to readmission. Ten readmissions were analyzed by using the We-ReAlyse tool, resulting in key insights about possible root causes like the handover process, patient's care needs, the resources on the general unit and the use of different electronic healthcare record systems. CONCLUSIONS The We-ReAlyse tool provides a visualization/objectification of issues related to intensive care readmissions, gathering data upon which to base quality improvement interventions. Based on the information on how multi-level risk profiles and knowledge deficits contribute to readmission rates, nurses can target specific quality improvements to reduce those rates. IMPLICATIONS FOR CLINICAL PRACTICE AND RESEARCH With the We-ReAlyse tool, we have the opportunity to collect detailed information about ICU readmissions for an in-depth analysis. This will allow health professionals in all involved departments to discuss and either correct or cope with the identified issues. In the long term, this will allow continuous, concerted efforts to reduce and prevent ICU readmissions. To obtain more data for analysis and to further refine and simplify the tool, it may be applied to larger samples of ICU readmissions. Furthermore, to test its generalizability, the tool should be applied to patients from other departments and other hospitals. Adapting it to an electronic version would facilitate the timely and comprehensive collection of necessary information. Finally, the tool's emphasis comprises reflecting on and analyzing ICU readmissions, allowing clinicians to develop interventions targeting the identified problems. Therefore, future research in this area will require the development and evaluation of potential interventions.
Collapse
Affiliation(s)
- Martina Hachen
- Department of Visceral Surgery and Medicine, Inselspital, Bern University Hospital, University of Bern, Switzerland.
| | - Sarah N Musy
- Institute of Nursing Science, University of Basel, Basel, Switzerland.
| | - Annina Fröhlich
- Department of Visceral Surgery and Medicine, Inselspital, Bern University Hospital, University of Bern, Switzerland.
| | - Marie-Madlen Jeitziner
- Institute of Nursing Science, University of Basel, Basel, Switzerland; Department of Intensive Care Medicine, Inselspital, University Hospital Bern, Bern, Switzerland.
| | - Angela Kindler
- Department of Physiotherapy, Inselspital, University Hospital Bern, Bern, Switzerland.
| | - Stéphanie Perrodin
- Department of Visceral Surgery and Medicine, Inselspital, Bern University Hospital, University of Bern, Switzerland.
| | - Bjoern Zante
- Department of Intensive Care Medicine, Inselspital, University Hospital Bern, Bern, Switzerland.
| | - Franziska Zúñiga
- Institute of Nursing Science, University of Basel, Basel, Switzerland.
| | - Michael Simon
- Institute of Nursing Science, University of Basel, Basel, Switzerland.
| |
Collapse
|
12
|
Endeshaw AS, Fekede MS, Gesso AS, Aligaz EM, Aweke S. Survival status and predictors of mortality among patients admitted to surgical intensive care units of Addis Ababa governmental hospitals, Ethiopia: A multicenter retrospective cohort study. Front Med (Lausanne) 2023; 9:1085932. [PMID: 36816723 PMCID: PMC9932811 DOI: 10.3389/fmed.2022.1085932] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2022] [Accepted: 12/21/2022] [Indexed: 02/05/2023] Open
Abstract
Introduction Critical care is a serious global healthcare burden. Although a high number of surgical patients are being admitted to the surgical intensive care unit (SICU), the mortality remained high, particularly in low and middle-income countries. However, there is limited data in Ethiopia. Therefore, this study aimed to investigate the survival status and predictors of mortality in surgical patients admitted to the SICUs of Addis Ababa governmental hospitals, Ethiopia. Methods A multicenter retrospective cohort study was conducted on 410 surgical patients admitted to the SICUs of three government hospitals in Addis Ababa selected using a simple random sampling from February 2017 to February 2020. The data were entered into Epidata version 4.6 and imported to STATA/MP version 16 for further analysis. Bi-variable and multivariable Cox regression models were fitted in the analysis to determine the predictor variables. A hazard ratio (HR) with a 95% confidence interval (CI) was computed, and variables with a p-value <0.05 were considered statistically significant. Results From a sample of 410 patients, 378 were included for final analysis and followed for a median follow-up of 5 days. The overall mortality among surgical patients in the SICU was 44.97% with an incidence rate of 5.9 cases per 100 person-day observation. Trauma (AHR = 1.83, 95% CI: 1.19-2.08), Glasgow coma score (GCS) <9 (AHR = 2.06, 95% CI: 1.28-3.31), readmission to the SICU (AHR = 3.52, 95% CI: 2.18-5.68), mechanical ventilation (AHR = 2.52, 95% CI: 1.23-5.15), and creatinine level (AHR = 1.09, 95% CI: 1.01-1.18) were found to be significantly associated with mortality in the SICU. Conclusion The mortality of surgical patients in the SICU was high. Trauma, GCS <9 upon admission, readmission to the SICU, mechanical ventilation, and increased in the creatinine level on admission to the SICU were the identified predictors of mortality in the SICU.
Collapse
Affiliation(s)
- Amanuel Sisay Endeshaw
- Department of Anesthesia, School of Medicine, College of Medicine and Health Sciences, Bahir Dar University, Bahir Dar, Ethiopia
| | - Mulualem Sitot Fekede
- Department of Anesthesia, School of Medicine, College of Health Sciences, Addis Ababa University, Addis Ababa, Ethiopia,*Correspondence: Mulualem Sitot Fekede, ✉
| | - Ashenafi Seifu Gesso
- Department of Anesthesia, School of Medicine, College of Health Sciences, Addis Ababa University, Addis Ababa, Ethiopia
| | - Esubalew Muluneh Aligaz
- Department of Anesthesia, School of Medicine, College of Medicine and Health Sciences, Bahir Dar University, Bahir Dar, Ethiopia
| | - Senait Aweke
- Department of Anesthesia, School of Medicine, College of Health Sciences, Addis Ababa University, Addis Ababa, Ethiopia
| |
Collapse
|
13
|
Yin YL, Sun MR, Zhang K, Chen YH, Zhang J, Zhang SK, Zhou LL, Wu YS, Gao P, Shen KK, Hu ZJ. Status and Risk Factors in Patients Requiring Unplanned Intensive Care Unit Readmission Within 48 Hours: A Retrospective Propensity-Matched Study in China. Risk Manag Healthc Policy 2023; 16:383-391. [PMID: 36936882 PMCID: PMC10015949 DOI: 10.2147/rmhp.s399829] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/13/2022] [Accepted: 02/24/2023] [Indexed: 03/12/2023] Open
Abstract
Aim This study investigated the current status and related risk factors of 48-hour unplanned return to the intensive care unit (ICU) to reduce the return rate and improve the quality of critical care management. Methods Data were collected from 2365 patients discharged from the comprehensive ICU. Multivariate and 1:1 propensity score matching analyses were performed. Results Forty patients (1.69%) had unplanned readmission to the ICU within 48 hours after transfer. The primary reason for return was respiratory failure (16 patients, 40%). Furthermore, respiratory failure (odds ratio [OR] = 5.994, p = 0.02) and the number of organ failures (OR = 5.679, p = 0.006) were independent risk factors for unplanned ICU readmission. Receiver operating characteristic curves were drawn for the predictive value of the number of organ injuries during a patient's unplanned transfer to the ICU (area under the curve [AUC] = 0.744, sensitivity = 60%, specificity = 77.5%). Conclusion The reason for patient transfer and the number of organ injuries during the process were independent risk factors for patients who were critically ill. The number of organs damaged had a predictive value on whether the patient would return to the ICU within 48 hours.
Collapse
Affiliation(s)
- Yan-Ling Yin
- Department of ICU, the Fourth Hospital of Hebei Medical University, Shijiazhuang City, Hebei Province, People’s Republic of China
| | - Mei-Rong Sun
- Department of ICU, the Fourth Hospital of Hebei Medical University, Shijiazhuang City, Hebei Province, People’s Republic of China
| | - Kun Zhang
- Department of ICU, the Fourth Hospital of Hebei Medical University, Shijiazhuang City, Hebei Province, People’s Republic of China
| | - Yu-Hong Chen
- Department of ICU, the Fourth Hospital of Hebei Medical University, Shijiazhuang City, Hebei Province, People’s Republic of China
| | - Jie Zhang
- Department of ICU, the Fourth Hospital of Hebei Medical University, Shijiazhuang City, Hebei Province, People’s Republic of China
| | - Shao-Kun Zhang
- Department of ICU, the Fourth Hospital of Hebei Medical University, Shijiazhuang City, Hebei Province, People’s Republic of China
| | - Li-Li Zhou
- Department of ICU, the Fourth Hospital of Hebei Medical University, Shijiazhuang City, Hebei Province, People’s Republic of China
| | - Yan-Shuo Wu
- Department of ICU, the Fourth Hospital of Hebei Medical University, Shijiazhuang City, Hebei Province, People’s Republic of China
| | - Peng Gao
- Department of ICU, the Fourth Hospital of Hebei Medical University, Shijiazhuang City, Hebei Province, People’s Republic of China
| | - Kang-Kang Shen
- Department of ICU, the Fourth Hospital of Hebei Medical University, Shijiazhuang City, Hebei Province, People’s Republic of China
| | - Zhen-Jie Hu
- Department of ICU, the Fourth Hospital of Hebei Medical University, Shijiazhuang City, Hebei Province, People’s Republic of China
- Hebei Key Laboratory of Critical Disease Mechanism and Intervention, Shijiazhuang City, Hebei Province, People’s Republic of China
- Correspondence: Zhen-Jie Hu, Tel +86-0311-86095588, Email
| |
Collapse
|
14
|
Haruna J, Masuda Y, Tatsumi H. Transitional Care Programs for Patients with High Nursing Activity Scores Reduce Unplanned Readmissions to Intensive Care Units. MEDICINA (KAUNAS, LITHUANIA) 2022; 58:medicina58111532. [PMID: 36363489 PMCID: PMC9693432 DOI: 10.3390/medicina58111532] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/18/2022] [Revised: 10/21/2022] [Accepted: 10/24/2022] [Indexed: 11/06/2022]
Abstract
Background and Objectives: The main objective of a transitional care program (TCP) is to detect patients with early deterioration following intensive care unit (ICU) discharge in order to reduce unplanned ICU readmissions. Consensus on the effectiveness of TCPs in preventing unscheduled ICU readmissions remains lacking. In this case study assessing the effectiveness of TCP, we focused on the association of unplanned ICU readmission with high nursing activities scores (NASs), which are considered a risk factor for ICU readmission. Materials and Methods: This retrospective observational study analyzed the data of patients admitted to a single-center ICU between January 2016 and December 2019, with an NAS of >53 points at ICU discharge. The following data were extracted: patient characteristics, ICU treatment, acute physiology and chronic health evaluation II (APACHE II) score at ICU admission, Charlson comorbidity index (CCI), 28-day mortality rate, and ICU readmission rate. The primary outcome was the association between unplanned ICU readmissions and the use of a TCP. The propensity score (PS) was calculated using the following variables: age, sex, APACHE II score, and CCI. Subsequently, logistic regression analysis was performed using the PS to evaluate the outcomes. Results: A total of 143 patients were included in this study, of which 87 (60.8%) participated in a TCP. Respiratory failure was the most common cause of unplanned ICU readmission. The unplanned ICU readmission rate was significantly lower in the TCP group. In the logistic regression model, TCP (odds ratio, 5.15; 95% confidence interval, 1.46−18.2; p = 0.01) was independently associated with unplanned ICU readmission. Conclusions: TCP intervention with a focus on patients with a high NAS (>53 points) may prevent unplanned ICU readmission.
Collapse
|
15
|
Aronsson Dannewitz A, Svennblad B, Michaëlsson K, Lipcsey M, Gedeborg R. Optimized diagnosis-based comorbidity measures for all-cause mortality prediction in a national population-based ICU population. Crit Care 2022; 26:306. [PMID: 36203163 PMCID: PMC9535950 DOI: 10.1186/s13054-022-04172-0] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/15/2022] [Accepted: 09/14/2022] [Indexed: 11/17/2022] Open
Abstract
BACKGROUND We aimed to optimize prediction of long-term all-cause mortality of intensive care unit (ICU) patients, using quantitative register-based comorbidity information assessed from hospital discharge diagnoses prior to intensive care treatment. MATERIAL AND METHODS Adult ICU admissions during 2006 to 2012 in the Swedish intensive care register were followed for at least 4 years. The performance of quantitative comorbidity measures based on the 5-year history of number of hospital admissions, length of stay, and time since latest admission in 36 comorbidity categories was compared in time-to-event analyses with the Charlson comorbidity index (CCI) and the Simplified Acute Physiology Score (SAPS3). RESULTS During a 7-year period, there were 230,056 ICU admissions and 62,225 deaths among 188,965 unique individuals. The time interval from the most recent hospital stays and total length of stay within each comorbidity category optimized mortality prediction and provided clear separation of risk categories also within strata of age and CCI, with hazard ratios (HRs) comparing lowest to highest quartile ranging from 1.17 (95% CI: 0.52-2.64) to 6.41 (95% CI: 5.19-7.92). Risk separation was also observed within SAPS deciles with HR ranging from 1.07 (95% CI: 0.83-1.38) to 3.58 (95% CI: 2.12-6.03). CONCLUSION Baseline comorbidity measures that included the time interval from the most recent hospital stay in 36 different comorbidity categories substantially improved long-term mortality prediction after ICU admission compared to the Charlson index and the SAPS score. Trial registration ClinicalTrials.gov ID NCT04109001, date of registration 2019-09-26 retrospectively.
Collapse
Affiliation(s)
- Anna Aronsson Dannewitz
- grid.8993.b0000 0004 1936 9457Department of Surgical Sciences, Uppsala University, Uppsala, Sweden
| | - Bodil Svennblad
- grid.8993.b0000 0004 1936 9457Department of Surgical Sciences, Uppsala University, Uppsala, Sweden
| | - Karl Michaëlsson
- grid.8993.b0000 0004 1936 9457Department of Surgical Sciences, Uppsala University, Uppsala, Sweden
| | - Miklos Lipcsey
- grid.8993.b0000 0004 1936 9457Department of Surgical Sciences, Uppsala University, Uppsala, Sweden
| | - Rolf Gedeborg
- grid.8993.b0000 0004 1936 9457Department of Surgical Sciences, Uppsala University, Uppsala, Sweden
| |
Collapse
|
16
|
Tangonan R, Alvarado-Dyer R, Loggini A, Ammar FE, Kumbhani R, Lazaridis C, Kramer C, Goldenberg FD, Mansour A. Frequency, Risk Factors, and Outcomes of Unplanned Readmission to the Neurological Intensive Care Unit after Spontaneous Intracerebral Hemorrhage. Neurocrit Care 2022; 37:390-398. [PMID: 35072926 DOI: 10.1007/s12028-021-01415-w] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/29/2021] [Accepted: 11/30/2021] [Indexed: 10/19/2022]
Abstract
BACKGROUND Unplanned readmission to the neurological intensive care unit (ICU) is an underinvestigated topic in patients admitted after spontaneous intracerebral hemorrhage (ICH). The purpose of this study is to investigate the frequency, clinical risk factors, and outcome of bounce back to the neurological ICU in a cohort of patients admitted after ICH. METHODS This is a retrospective observational study inspecting bounce back to the neurological ICU in patients admitted with spontaneous ICH over an 8-year period. For each patient, demographics, medical history, clinical presentation, length of ICU stay, unplanned readmission to neurological ICU, cause of readmission, and mortality were reviewed. Bounce back to the neurological ICU was defined as an unplanned readmission to the neurological ICU from a general floor service during the same hospitalization. A multivariable analysis was used to define independent variables associated with bounce back to the neurological ICU as well as association between bounce back to the neurological ICU and mortality. The significance level was set at p < 0.05. RESULTS A total of 221 patients were included. Among those, 20 (9%) had a bounce back to the neurological ICU. Respiratory complications (n = 11) was the most common reason for bounce back to the neurological ICU, followed by neurological (n = 5) and cardiological (n = 4) complications. In a multivariable logistic regression, location of hemorrhage in the basal ganglia (odds ratio [OR]: 3.0, 95% confidence interval [CI]: 1.0-8.9, p = 0.03) and dysphagia at the time of transfer (OR: 3.9, 95% CI: 1.0-15.4, p = 0.04) were significantly associated with bounce back to the neurological ICU. After we controlled for ICH score, readmission to the ICU was also independently associated with higher mortality (OR: 14.1, 95% CI: 2.8-71.7, p < 0.01). CONCLUSIONS Bounce back to the neurological ICU is not an infrequent complication in patients with spontaneous ICH and is associated with higher hospital length of stay and mortality. We identified relevant and potentially modifiable risk factors associated with bounce back to the neurological ICU. Future prospective studies are necessary to develop patient-centered strategies that may improve transition from the neurological ICU to the general floor.
Collapse
Affiliation(s)
- Ruth Tangonan
- Neurosciences Intensive Care Unit, Department of Neurology, University of Chicago Medicine and Biological Sciences, 5841 S. Maryland Ave., MC 2030, Chicago, IL, 60637-1470, USA
| | - Ronald Alvarado-Dyer
- Neurosciences Intensive Care Unit, Department of Neurology, University of Chicago Medicine and Biological Sciences, 5841 S. Maryland Ave., MC 2030, Chicago, IL, 60637-1470, USA
| | - Andrea Loggini
- Southern Illinois Healthcare, Carbondale, IL, USA
- Southern Illinois University, Springfield, IL, USA
| | - Faten El Ammar
- Neurosciences Intensive Care Unit, Department of Neurology, University of Chicago Medicine and Biological Sciences, 5841 S. Maryland Ave., MC 2030, Chicago, IL, 60637-1470, USA
| | - Ruchit Kumbhani
- Neurosciences Intensive Care Unit, Department of Neurology, University of Chicago Medicine and Biological Sciences, 5841 S. Maryland Ave., MC 2030, Chicago, IL, 60637-1470, USA
| | - Christos Lazaridis
- Neurosciences Intensive Care Unit, Department of Neurology, University of Chicago Medicine and Biological Sciences, 5841 S. Maryland Ave., MC 2030, Chicago, IL, 60637-1470, USA
- Department of Neurological Surgery, University of Chicago Medicine and Biological Sciences, Chicago, IL, USA
| | - Christopher Kramer
- Neurosciences Intensive Care Unit, Department of Neurology, University of Chicago Medicine and Biological Sciences, 5841 S. Maryland Ave., MC 2030, Chicago, IL, 60637-1470, USA
- Department of Neurological Surgery, University of Chicago Medicine and Biological Sciences, Chicago, IL, USA
| | - Fernando D Goldenberg
- Neurosciences Intensive Care Unit, Department of Neurology, University of Chicago Medicine and Biological Sciences, 5841 S. Maryland Ave., MC 2030, Chicago, IL, 60637-1470, USA
- Department of Neurological Surgery, University of Chicago Medicine and Biological Sciences, Chicago, IL, USA
| | - Ali Mansour
- Neurosciences Intensive Care Unit, Department of Neurology, University of Chicago Medicine and Biological Sciences, 5841 S. Maryland Ave., MC 2030, Chicago, IL, 60637-1470, USA.
- Department of Neurological Surgery, University of Chicago Medicine and Biological Sciences, Chicago, IL, USA.
| |
Collapse
|
17
|
Haruna J, Masuda Y, Tatsumi H, Sonoda T. Nursing Activities Score at Discharge from the Intensive Care Unit Is Associated with Unplanned Readmission to the Intensive Care Unit. J Clin Med 2022; 11:jcm11175203. [PMID: 36079134 PMCID: PMC9457354 DOI: 10.3390/jcm11175203] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/12/2022] [Revised: 08/24/2022] [Accepted: 08/30/2022] [Indexed: 11/16/2022] Open
Abstract
This study evaluated the accuracy of predicting unplanned the intensive care unit (ICU) readmission using the Nursing Activities Score (NAS) at ICU discharge based on nursing workloads, and compared it to the accuracy of the prediction made using the Stability and Workload Index for Transfer (SWIFT) score. Patients admitted to the ICU of Sapporo Medical University Hospital between April 2014 and December 2017 were included, and unplanned ICU readmissions were retrospectively evaluated using the SWIFT score and the NAS. Patient characteristics, such as age, sex, the Charlson Comorbidity Index, and sequential organ failure assessment score at ICU admission, were used as covariates, and logistic regression analysis was performed to calculate the odds ratios for the SWIFT score and NAS. Among 599 patients, 58 (9.7%) were unexpectedly readmitted to the ICU. The area under the receiver operating characteristic curve of NAS (0.78) was higher than that of the SWIFT score (0.68), and cutoff values were 21 for the SWIFT and 53 for the NAS. Multivariate analysis showed that the NAS was an independent predictor of unplanned ICU readmission. The NAS was superior to the SWIFT in predicting unplanned ICU readmission. NAS may be an adjunctive tool to predict unplanned ICU readmission.
Collapse
Affiliation(s)
- Junpei Haruna
- Department of Intensive Care Medicine, School of Medicine, Sapporo Medical University, Sapporo 060-8556, Japan
- Correspondence:
| | - Yoshiki Masuda
- Department of Intensive Care Medicine, School of Medicine, Sapporo Medical University, Sapporo 060-8556, Japan
| | - Hiroomi Tatsumi
- Department of Intensive Care Medicine, School of Medicine, Sapporo Medical University, Sapporo 060-8556, Japan
| | - Tomoko Sonoda
- Department of Nursing, Tensei University, Sapporo 065-0013, Japan
| |
Collapse
|
18
|
Hegselmann S, Ertmer C, Volkert T, Gottschalk A, Dugas M, Varghese J. Development and validation of an interpretable 3 day intensive care unit readmission prediction model using explainable boosting machines. Front Med (Lausanne) 2022; 9:960296. [PMID: 36082270 PMCID: PMC9445989 DOI: 10.3389/fmed.2022.960296] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2022] [Accepted: 08/03/2022] [Indexed: 11/17/2022] Open
Abstract
Background Intensive care unit (ICU) readmissions are associated with mortality and poor outcomes. To improve discharge decisions, machine learning (ML) could help to identify patients at risk of ICU readmission. However, as many models are black boxes, dangerous properties may remain unnoticed. Widely used post hoc explanation methods also have inherent limitations. Few studies are evaluating inherently interpretable ML models for health care and involve clinicians in inspecting the trained model. Methods An inherently interpretable model for the prediction of 3 day ICU readmission was developed. We used explainable boosting machines that learn modular risk functions and which have already been shown to be suitable for the health care domain. We created a retrospective cohort of 15,589 ICU stays and 169 variables collected between 2006 and 2019 from the University Hospital Münster. A team of physicians inspected the model, checked the plausibility of each risk function, and removed problematic ones. We collected qualitative feedback during this process and analyzed the reasons for removing risk functions. The performance of the final explainable boosting machine was compared with a validated clinical score and three commonly used ML models. External validation was performed on the widely used Medical Information Mart for Intensive Care version IV database. Results The developed explainable boosting machine used 67 features and showed an area under the precision-recall curve of 0.119 ± 0.020 and an area under the receiver operating characteristic curve of 0.680 ± 0.025. It performed on par with state-of-the-art gradient boosting machines (0.123 ± 0.016, 0.665 ± 0.036) and outperformed the Simplified Acute Physiology Score II (0.084 ± 0.025, 0.607 ± 0.019), logistic regression (0.092 ± 0.026, 0.587 ± 0.016), and recurrent neural networks (0.095 ± 0.008, 0.594 ± 0.027). External validation confirmed that explainable boosting machines (0.221 ± 0.023, 0.760 ± 0.010) performed similarly to gradient boosting machines (0.232 ± 0.029, 0.772 ± 0.018). Evaluation of the model inspection showed that explainable boosting machines can be useful to detect and remove problematic risk functions. Conclusions We developed an inherently interpretable ML model for 3 day ICU readmission prediction that reached the state-of-the-art performance of black box models. Our results suggest that for low- to medium-dimensional datasets that are common in health care, it is feasible to develop ML models that allow a high level of human control without sacrificing performance.
Collapse
Affiliation(s)
- Stefan Hegselmann
- Institute of Medical Informatics, University of Münster, Münster, Germany
| | - Christian Ertmer
- Department of Anesthesiology, Intensive Care and Pain Medicine, University Hospital Münster, Münster, Germany
| | - Thomas Volkert
- Department of Anesthesiology, Intensive Care and Pain Medicine, University Hospital Münster, Münster, Germany
| | - Antje Gottschalk
- Department of Anesthesiology, Intensive Care and Pain Medicine, University Hospital Münster, Münster, Germany
| | - Martin Dugas
- Institute of Medical Informatics, Heidelberg University Hospital, Heidelberg, Germany
| | - Julian Varghese
- Institute of Medical Informatics, University of Münster, Münster, Germany
| |
Collapse
|
19
|
Mahmoodpoor A, Sanaie S, Saghaleini SH, Ostadi Z, Hosseini MS, Sheshgelani N, Vahedian-Azimi A, Samim A, Rahimi-Bashar F. Prognostic value of National Early Warning Score and Modified Early Warning Score on intensive care unit readmission and mortality: A prospective observational study. Front Med (Lausanne) 2022; 9:938005. [PMID: 35991649 PMCID: PMC9386480 DOI: 10.3389/fmed.2022.938005] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/06/2022] [Accepted: 07/19/2022] [Indexed: 12/03/2022] Open
Abstract
BACKGROUND Modified Early Warning Score (MEWS) and National Early Warning Score (NEWS) are widely used in predicting the mortality and intensive care unit (ICU) admission of critically ill patients. This study was conducted to evaluate and compare the prognostic value of NEWS and MEWS for predicting ICU readmission, mortality, and related outcomes in critically ill patients at the time of ICU discharge. METHODS This multicenter, prospective, observational study was conducted over a year, from April 2019 to March 2020, in the general ICUs of two university-affiliated hospitals in Northwest Iran. MEWS and NEWS were compared based on the patients' outcomes (including mortality, ICU readmission, time to readmission, discharge type, mechanical ventilation (MV), MV duration, and multiple organ failure after readmission) using the univariable and multivariable binary logistic regression. The receiver operating characteristic (ROC) curve was used to determine the outcome predictability of MEWS and NEWS. RESULTS A total of 410 ICU patients were enrolled in this study. According to multivariable logistic regression analysis, both MEWS and NEWS were predictors of ICU readmission, time to readmission, MV status after readmission, MV duration, and multiple organ failure after readmission. The area under the ROC curve (AUC) for predicting mortality was 0.91 (95% CI = 0.88-0.94, P < 0.0001) for the NEWS and 0.88 (95% CI = 0.84-0.91, P < 0.0001) for the MEWS. There was no significant difference between the AUC of the NEWS and the MEWS for predicting mortality (P = 0.082). However, for ICU readmission (0.84 vs. 0.71), time to readmission (0.82 vs. 0.67), MV after readmission (0.83 vs. 0.72), MV duration (0.81 vs. 0.67), and multiple organ failure (0.833 vs. 0.710), the AUCs of MEWS were significantly greater (P < 0.001). CONCLUSION National Early Warning Score and MEWS values of >4 demonstrated high sensitivity and specificity in identifying the risk of mortality for the patients' discharge from ICU. However, we found that the MEWS showed superiority over the NEWS score in predicting other outcomes. Eventually, MEWS could be considered an efficient prediction score for morbidity and mortality of critically ill patients.
Collapse
Affiliation(s)
- Ata Mahmoodpoor
- Research Center for Integrative Medicine in Aging, Aging Research Institute, Tabriz University of Medical Sciences, Tabriz, Iran
| | - Sarvin Sanaie
- Research Center for Integrative Medicine in Aging, Aging Research Institute, Tabriz University of Medical Sciences, Tabriz, Iran
| | - Seied Hadi Saghaleini
- Department of Anesthesiology and Intensive Care, Faculty of Medicine, Tabriz University of Medical Sciences, Tabriz, Iran
| | - Zohreh Ostadi
- Department of Anesthesiology and Intensive Care, Faculty of Medicine, Tabriz University of Medical Sciences, Tabriz, Iran
| | | | - Naeeme Sheshgelani
- Student Research Committee, Tabriz University of Medical Sciences, Tabriz, Iran
| | - Amir Vahedian-Azimi
- Trauma Research Center, Nursing Faculty, Baqiyatallah University of Medical Sciences, Tehran, Iran
| | - Abbas Samim
- Chemical Injuries Research Center, Systems Biology and Poisonings Institute, Baqiyatallah University of Medical Sciences, Tehran, Iran
| | - Farshid Rahimi-Bashar
- Anesthesia and Critical Care Department, Hamadan University of Medical Sciences, Hamadan, Iran
| |
Collapse
|
20
|
Hu C, Li L, Li Y, Wang F, Hu B, Peng Z. Explainable Machine-Learning Model for Prediction of In-Hospital Mortality in Septic Patients Requiring Intensive Care Unit Readmission. Infect Dis Ther 2022; 11:1695-1713. [PMID: 35835943 PMCID: PMC9282631 DOI: 10.1007/s40121-022-00671-3] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/06/2022] [Accepted: 06/23/2022] [Indexed: 11/29/2022] Open
Abstract
INTRODUCTION Septic patients requiring intensive care unit (ICU) readmission are at high risk of mortality, but research focusing on the association of ICU readmission due to sepsis and mortality is limited. The aim of this study was to develop and validate a machine learning (ML) model for predicting in-hospital mortality in septic patients readmitted to the ICU using routinely available clinical data. METHODS The data used in this study were obtained from the Medical Information Mart for Intensive Care (MIMIC-IV, v1.0) database, between 2008 and 2019. The study cohort included patients with sepsis requiring ICU readmission. The data were randomly split into a training (75%) data set and a validation (25%) data set. Nine popular ML models were developed to predict mortality in septic patients readmitted to the ICU. The model with the best accuracy and area under the curve (A.C.) in the validation cohort was defined as the optimal model and was selected for further prediction studies. The SHAPELY Additive explanations (SHAP) values and Local Interpretable Model-Agnostic Explanation (LIME) methods were used to improve the interpretability of the optimal model. RESULTS A total of 1117 septic patients who had required ICU readmission during the study period were enrolled in the study. Of these participants, 434 (38.9%) were female, and the median (interquartile range [IQR]) age was 68.6 (58.4-79.2) years. The median (IQR) ICU interval duration was 2.60 (0.64-5.78) days. After feature selection, 31 of 47 clinical factors were ultimately chosen for use in model construction. Of the nine ML models tested, the best performance was achieved with the random forest (RF) model, with an A.C. of 0.81, an accuracy of 85% and a precision of 62% in the validation cohort. The SHAP summary analysis revealed that Glasgow Coma Scale score, urine output, blood urea nitrogen, lactate, platelet count and systolic blood pressure were the top six most important factors contributing to the RF model. Additionally, the LIME method demonstrated how the RF model works in terms of explaining risk of death prediction in septic patients requiring ICU readmission. CONCLUSION The ML models reported here showed a good prognostic prediction ability in septic patients requiring ICU readmission. Of the features selected, the parameters related to organ perfusion made the largest contribution to outcome prediction during ICU readmission in septic patients.
Collapse
Affiliation(s)
- Chang Hu
- Department of Critical Care Medicine, Zhongnan Hospital of Wuhan University, Wuhan, 430071, Hubei, China.,Clinical Research Center of Hubei Critical Care Medicine, Wuhan, Hubei, China.,Jiangsu Provincial Key Laboratory of Critical Care Medicine, Southeast University, Nanjing, Jiangsu, China
| | - Lu Li
- Department of Critical Care Medicine, Zhongnan Hospital of Wuhan University, Wuhan, 430071, Hubei, China.,Clinical Research Center of Hubei Critical Care Medicine, Wuhan, Hubei, China
| | - Yiming Li
- Department of Critical Care Medicine, Zhongnan Hospital of Wuhan University, Wuhan, 430071, Hubei, China.,Clinical Research Center of Hubei Critical Care Medicine, Wuhan, Hubei, China
| | - Fengyun Wang
- Department of Critical Care Medicine, Zhongnan Hospital of Wuhan University, Wuhan, 430071, Hubei, China.,Clinical Research Center of Hubei Critical Care Medicine, Wuhan, Hubei, China
| | - Bo Hu
- Department of Critical Care Medicine, Zhongnan Hospital of Wuhan University, Wuhan, 430071, Hubei, China. .,Clinical Research Center of Hubei Critical Care Medicine, Wuhan, Hubei, China. .,Jiangsu Provincial Key Laboratory of Critical Care Medicine, Southeast University, Nanjing, Jiangsu, China.
| | - Zhiyong Peng
- Department of Critical Care Medicine, Zhongnan Hospital of Wuhan University, Wuhan, 430071, Hubei, China. .,Clinical Research Center of Hubei Critical Care Medicine, Wuhan, Hubei, China.
| |
Collapse
|
21
|
Shahid A, Sept B, Kupsch S, Brundin-Mather R, Piskulic D, Soo A, Grant C, Leigh JP, Fiest KM, Stelfox HT. Development and pilot implementation of a patient-oriented discharge summary for critically Ill patients. World J Crit Care Med 2022; 11:255-268. [PMID: 36051938 PMCID: PMC9305680 DOI: 10.5492/wjccm.v11.i4.255] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/01/2022] [Revised: 05/06/2022] [Accepted: 06/18/2022] [Indexed: 02/06/2023] Open
Abstract
BACKGROUND Patients leaving the intensive care unit (ICU) often experience gaps in care due to deficiencies in discharge communication, leaving them vulnerable to increased stress, adverse events, readmission to ICU, and death. To facilitate discharge communication, written summaries have been implemented to provide patients and their families with information on medications, activity and diet restrictions, follow-up appointments, symptoms to expect, and who to call if there are questions. While written discharge summaries for patients and their families are utilized frequently in surgical, rehabilitation, and pediatric settings, few have been utilized in ICU settings. AIM To develop an ICU specific patient-oriented discharge summary tool (PODS-ICU), and pilot test the tool to determine acceptability and feasibility. METHODS Patient-partners (i.e., individuals with lived experience as an ICU patient or family member of an ICU patient), ICU clinicians (i.e., physicians, nurses), and researchers met to discuss ICU patients' specific informational needs and design the PODS-ICU through several cycles of discussion and iterative revisions. Research team nurses piloted the PODS-ICU with patient and family participants in two ICUs in Calgary, Canada. Follow-up surveys on the PODS-ICU and its impact on discharge were administered to patients, family participants, and ICU nurses. RESULTS Most participants felt that their discharge from the ICU was good or better (n = 13; 87.0%), and some (n = 9; 60.0%) participants reported a good understanding of why the patient was in ICU. Most participants (n = 12; 80.0%) reported that they understood ICU events and impacts on the patient's health. While many patients and family participants indicated the PODS-ICU was informative and useful, ICU nurses reported that the PODS-ICU was "not reasonable" in their daily clinical workflow due to "time constraint". CONCLUSION The PODS-ICU tool provides patients and their families with essential information as they discharge from the ICU. This tool has the potential to engage and empower patients and their families in ensuring continuity of care beyond ICU discharge. However, the PODS-ICU requires pairing with earlier discharge practices and integration with electronic clinical information systems to fit better into the clinical workflow for ICU nurses. Further refinement and testing of the PODS-ICU tool in diverse critical care settings is needed to better assess its feasibility and its effects on patient health outcomes.
Collapse
Affiliation(s)
- Anmol Shahid
- Department of Critical Care Medicine, University of Calgary, Calgary T2N 4Z6, Alberta, Canada
| | - Bonnie Sept
- Department of Critical Care Medicine, University of Calgary, Calgary T2N 4Z6, Alberta, Canada
| | - Shelly Kupsch
- Department of Critical Care Medicine, University of Calgary, Calgary T2N 4Z6, Alberta, Canada
| | - Rebecca Brundin-Mather
- Department of Critical Care Medicine, University of Calgary, Calgary T2N 4Z6, Alberta, Canada
| | - Danijela Piskulic
- Department of Psychiatry, Hotchkiss Brain Institute, Calgary T2N 4Z6, Alberta, Canada
| | - Andrea Soo
- Department of Critical Care Medicine, University of Calgary, Calgary T2N 4Z6, Alberta, Canada
| | - Christopher Grant
- Department of Critical Care Medicine, University of Calgary, Calgary T2N 4Z6, Alberta, Canada
| | - Jeanna Parsons Leigh
- Department of Critical Care Medicine, University of Calgary, Calgary T2N 4Z6, Alberta, Canada
- School of Health Administration, Dalhousie University, Halifax B3H 4R2, Nova Scotia, Canada
| | - Kirsten M Fiest
- Department of Critical Care Medicine, University of Calgary, Calgary T2N 4Z6, Alberta, Canada
| | - Henry T Stelfox
- Department of Critical Care Medicine, University of Calgary, Calgary T2N 4Z6, Alberta, Canada
| |
Collapse
|
22
|
Padkins M, Fanaroff A, Bennett C, Wiley B, Barsness G, van Diepen S, Katz JN, Jentzer JC. Epidemiology and Outcomes of Patients Readmitted to the Intensive Care Unit After Cardiac Intensive Care Unit Admission. Am J Cardiol 2022; 170:138-146. [PMID: 35393081 DOI: 10.1016/j.amjcard.2022.01.038] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/01/2021] [Revised: 01/06/2022] [Accepted: 01/11/2022] [Indexed: 11/01/2022]
Abstract
Readmission to the intensive care unit (ICU) during the index hospitalization is associated with poor outcomes in medical or surgical ICU survivors. Little is known about critically ill patients with acute cardiovascular conditions cared for in a cardiac intensive care unit (CICU). We sought to describe the incidence, risk factors, and outcomes of all ICU readmissions in patients who survived to CICU discharge. We retrospectively reviewed Mayo Clinic patients from 2007 to 2015 who survived the index CICU admission and identified patients with a second ICU stay during their index hospitalization; these patients were categorized as ICU transfers (patients who went directly from the CICU to another ICU) or ICU readmissions (patients initially transferred from the CICU to the ward, and then back to an ICU). Among 9,434 CICU survivors (mean age 67 years), 138 patients (1.5%) had a second ICU stay during the index hospitalization: 60 ICU transfers (0.6%) and 78 ICU readmissions (0.8%). The most common indications for ICU readmission were respiratory failure and procedure/surgery. On multivariable modeling, respiratory failure, severe acute kidney injury, and Charlson Comorbidity Index at the time of discharge from the index ICU stay were associated with ICU readmission. Death during the first ICU readmission (n = 78) occurred in 7.7% of patients. In-hospital mortality was higher for patients with a second ICU stay. In conclusion, few CICU survivors have a second ICU stay during their index hospitalization; these patients are at a higher risk of in-hospital and 1-year mortality. Respiratory failure, severe acute kidney injury, and higher co-morbidity burden identify CICU survivors at elevated risk of ICU readmission.
Collapse
Affiliation(s)
- Mitchell Padkins
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota
| | - Alexander Fanaroff
- Department of Cardiovascular Medicine, University of Pennsylvania, Philadelphia, Pennsylvania
| | - Courtney Bennett
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota
| | - Brandon Wiley
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota
| | - Gregory Barsness
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota
| | - Sean van Diepen
- Department of Critical Care Medicine and Division of Cardiology, Department of Medicine, University of Alberta Hospital, Edmonton, Alberta
| | - Jason N Katz
- Department of Cardiovascular Disease and Department of Medicine, Duke University, Durham, North Carolina
| | - Jacob C Jentzer
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota.
| |
Collapse
|
23
|
Predictive Model for ICU Readmission Based on Discharge Summaries Using Machine Learning and Natural Language Processing. INFORMATICS 2022. [DOI: 10.3390/informatics9010010] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022] Open
Abstract
Predicting ICU readmission risk will help physicians make decisions regarding discharge. We used discharge summaries to predict ICU 30-day readmission risk using text mining and machine learning (ML) with data from the Medical Information Mart for Intensive Care III (MIMIC-III). We used Natural Language Processing (NLP) and the Bag-of-Words approach on discharge summaries to build a Document-Term-Matrix with 3000 features. We compared the performance of support vector machines with the radial basis function kernel (SVM-RBF), adaptive boosting (AdaBoost), quadratic discriminant analysis (QDA), least absolute shrinkage and selection operator (LASSO), and Ridge Regression. A total of 4000 patients were used for model training and 6000 were used for validation. Using the bag-of-words determined by NLP, the area under the receiver operating characteristic (AUROC) curve was 0.71, 0.68, 0.65, 0.69, and 0.65 correspondingly for SVM-RBF, AdaBoost, QDA, LASSO, and Ridge Regression. We then used the SVM-RBF model for feature selection by incrementally adding features to the model from 1 to 3000 bag-of-words. Through this exhaustive search approach, only 825 features (words) were dominant. Using those selected features, we trained and validated all ML models. The AUROC curve was 0.74, 0.69, 0.67, 0.70, and 0.71 respectively for SVM-RBF, AdaBoost, QDA, LASSO, and Ridge Regression. Overall, this technique could predict ICU readmission relatively well.
Collapse
|
24
|
Azevedo AV, Tonietto TA, Boniatti MM. Nursing workload on the day of discharge from the intensive care unit is associated with readmission. Intensive Crit Care Nurs 2021; 69:103162. [PMID: 34895796 DOI: 10.1016/j.iccn.2021.103162] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/08/2021] [Revised: 09/02/2021] [Accepted: 09/23/2021] [Indexed: 11/16/2022]
Abstract
PURPOSE To verify whether there is an association between the Nursing Activities Score (NAS) on the day of discharge from the intensive care unit and readmission.. MATERIALS AND METHODS A retrospective cohort study of all patients admitted to the intensive care unit of Hospital Ernesto Dornelles, Porto Alegre, Brazil, who were discharged to the ward from October 2018 to December 2019. We collected demographic and clinical variables of the patients and the Nursing Activities Scoreon the day of discharge. Patients were followed up until the day of hospital discharge or death. RESULTS We included 1045 patients in the final sample. One hundred eighty-eight (18.0%) patients were readmitted, in addition there were two (0.2%) unexpected deaths that occurred in the ward. The median NAS was 59.9 (50.9-67.3), which was higher in the bivariate analysis in patients who were readmitted (64.0, 55.7-71.4) than in patients who were not readmitted (58.7, 49.7-66.1) (p < 0.001). Patients with a Nursing Activities Score ≥ 60.0 and < 60.0 had rates of readmission of 23.4% and 12.7%, respectively (p < 0.001). After multivariable adjustment, the Nursing Activities Score at discharge maintained an association with readmission. In addition, in the Cox regression, the Nursing Activities Score as a dichotomous variable was independently associated with readmission (adjusted HR 1.560; CI 1.146-2.125; p = 0.005). CONCLUSIONS We found that the nursing workload, assessed by the Nursing Activities Score at the time of discharge from the intensive care unit, was associated with risk of readmission..
Collapse
Affiliation(s)
| | - Tiago A Tonietto
- Critical Care Department, Hospital de Clínicas de Porto Alegre, Brazil
| | | |
Collapse
|
25
|
Park HS, Lee SH, Kim KM, Cho WS, Kang HS, Kim JE, Ha EJ. Readmission into intensive care unit in patients with aneurysmal subarachnoid hemorrhage. J Cerebrovasc Endovasc Neurosurg 2021; 23:327-333. [PMID: 34763380 PMCID: PMC8743824 DOI: 10.7461/jcen.2021.e2021.06.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2021] [Accepted: 06/23/2021] [Indexed: 11/23/2022] Open
Abstract
Objective Aneurysmal subarachnoid hemorrhage (aSAH) is a devastating cerebrovascular event; patients are routinely admitted to the intensive care unit (ICU) for initial management. Because complications may be delayed, unplanned ICU readmissions can occur. Therefore, in this study we evaluate the rate of and factors associated with readmission after aSAH and identify if readmission is associated with poor clinical outcomes. Methods We retrospectively reviewed the medical records of all patients receiving surgical or endovascular treatment for aSAH and admitted to the ICU between January 2008 and December 2019. We categorized patients by readmission and analyzed their clinical parameters. Results Of the 345 patients who transferred to ward-level care after an initial ICU stay (Group 2), 27 (7.3%) were readmitted to the ICU (Group 1). History of hypertension (HTN), initial Glasgow Coma Scale (GCS) score, modified Fisher grade, and vasospasm therapy during first ICU stay were significantly different between the groups. The most common reason for readmission was delayed cerebral ischemia (DCI; 70.3%; OR 5.545; 95% CI 1.25-24.52; p=0.024). Comorbid HTN (OR 5.311; 95% CI 1.75-16.12; p=0.03) and vasospasm therapy during first ICU stay (OR 7.234; 95% CI 2.41-21.7; p<0.01) also were associated with readmission. Readmitted patients had longer hospital stay and lower GCS scores at discharge (p<0.01). Conclusions DCI was the most common cause of ICU readmission in patients with aSAH. Readmission may indicate clinical deterioration, and patients who are at a high risk for DCI should be monitored to prevent readmission.
Collapse
Affiliation(s)
- Hye Seok Park
- Department of Neurosurgery, Seoul National University Hospital, Seoul National University College of Medicine, Seoul, Korea
| | - Sung Ho Lee
- Department of Neurosurgery, Seoul National University Hospital, Seoul National University College of Medicine, Seoul, Korea
| | - Kang Min Kim
- Department of Neurosurgery, Seoul National University Hospital, Seoul National University College of Medicine, Seoul, Korea
| | - Won-Sang Cho
- Department of Neurosurgery, Seoul National University Hospital, Seoul National University College of Medicine, Seoul, Korea
| | - Hyun-Seung Kang
- Department of Neurosurgery, Seoul National University Hospital, Seoul National University College of Medicine, Seoul, Korea
| | - Jeong Eun Kim
- Department of Neurosurgery, Seoul National University Hospital, Seoul National University College of Medicine, Seoul, Korea
| | - Eun Jin Ha
- Department of Critical Care Medicine, Seoul National University Hospital, Seoul, Korea
| |
Collapse
|
26
|
Asking "Meaning Questions" in Evidence-Based Reviews and the Utility of Qualitative Findings in Practice. Dimens Crit Care Nurs 2021; 40:288-294. [PMID: 34398565 DOI: 10.1097/dcc.0000000000000488] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022] Open
Abstract
Evidence-based practice (EBP) systematic reviews are mostly conducted using etiology, diagnosis, therapy, prevention, and prognosis question format. "Meaning" or qualitative questions are very rarely used. The purpose of this article is to discuss qualitative findings' contribution to EBP through asking "meaning questions" in conducting systematic reviews and the utilization of the results to practice. Two EBP systematic review exemplars using meaning questions including the relevance and utilization of qualitative findings in health care decision-making, practice, and policy are presented. There is a need to instill an evidence-based mindset into systematic reviews that balance scientific knowledge gained through empirical research and evidence from qualitative studies. This is turn will increase awareness among clinicians and decision makers on the different ways in which qualitative evidence can be used and applied in practice.
Collapse
|
27
|
林 瑜, 吴 静, 蔺 轲, 胡 永, 孔 桂. [Prediction of intensive care unit readmission for critically ill patients based on ensemble learning]. BEIJING DA XUE XUE BAO. YI XUE BAN = JOURNAL OF PEKING UNIVERSITY. HEALTH SCIENCES 2021; 53:566-572. [PMID: 34145862 PMCID: PMC8220041 DOI: 10.19723/j.issn.1671-167x.2021.03.021] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Subscribe] [Scholar Register] [Received: 07/05/2019] [Indexed: 05/21/2023]
Abstract
OBJECTIVE To develop machine learning models for predicting intensive care unit (ICU) readmission using ensemble learning algorithms. METHODS A publicly accessible American ICU database, medical information mart for intensive care (MIMIC)-Ⅲ as the data source was used, and the patients were selected by the inclusion and exclusion criteria. A set of variables that had the predictive ability of outcome including demographics, vital signs, laboratory tests, and comorbidities of patients were extracted from the dataset. We built the ICU readmission prediction models based on ensemble learning methods including random forest, adaptive boosting (AdaBoost), and gradient boosting decision tree (GBDT), and compared the prediction performance of the machine learning models with a conventional Logistic regression model. Five-fold cross validation was used to train and validate the prediction models. Average sensitivity, positive prediction value, negative prediction value, false positive rate, false negative rate, area under the receiver operating characteristic curve (AUROC) and Brier score were used as performance measures. After constructing the prediction models, top 10 predictive variables based on importance ranking were identified by the model with the best discrimination. RESULTS Among these ICU readmission prediction models, GBDT (AUROC=0.858) had better performance than random forest (AUROC=0.827), and was slightly superior to AdaBoost (AUROC=0.851) in terms of AUROC. Compared with Logistic regression (AUROC=0.810), the discrimination of the three ensemble learning models was much better. The feature importance provided by GBDT showed that the top ranking variables included vital signs and laboratory tests. The patients with ICU readmission had higher mean arterial pressure, systolic blood pressure, diastolic blood pressure, and heart rate than the patients without ICU readmission. Meanwhile, the patients readmitted to ICU experienced lower urine output and higher serum creatinine. Overall, the patients having repeated admissions during their hospitalization showed worse heart function and renal function compared with the patients without ICU readmission. CONCLUSION The ensemble learning based ICU readmission prediction models had better performance than Logistic regression model. Such ensemble learning models have the potential to aid ICU physicians in identifying those patients with high risk of ICU readmission and thus help improve overall clinical outcomes.
Collapse
Affiliation(s)
- 瑜 林
- 北京大学健康医疗大数据国家研究院,北京 100191National Institute of Health Data Science, Peking University, Beijing 100191, China
- 北京大学公共卫生学院流行病与卫生统计系,北京 100191Department of Epidemiology and Biostatistics, Peking University School of Public Health, Beijing 100191, China
| | - 静依 吴
- 北京大学信息技术高等研究院,杭州 311215Advanced Institute of Information Technology, Peking University, Hangzhou 311215, China
| | - 轲 蔺
- 北京大学健康医疗大数据国家研究院,北京 100191National Institute of Health Data Science, Peking University, Beijing 100191, China
- 北京大学公共卫生学院流行病与卫生统计系,北京 100191Department of Epidemiology and Biostatistics, Peking University School of Public Health, Beijing 100191, China
| | - 永华 胡
- 北京大学公共卫生学院流行病与卫生统计系,北京 100191Department of Epidemiology and Biostatistics, Peking University School of Public Health, Beijing 100191, China
- 北京大学医学信息学中心,北京 100191Peking University Medical Informatics Center, Beijing 100191, China
| | - 桂兰 孔
- 北京大学健康医疗大数据国家研究院,北京 100191National Institute of Health Data Science, Peking University, Beijing 100191, China
- 北京大学信息技术高等研究院,杭州 311215Advanced Institute of Information Technology, Peking University, Hangzhou 311215, China
- KONG Gui-lan, e-mail,
| |
Collapse
|
28
|
Williams AA, Jallo J, Yoo EJ. Improving the Quality of Visualization Dashboards in Critical Care: A Mixed-Methods Study. Am J Med Qual 2021; 36:215-220. [PMID: 32812436 DOI: 10.1177/1062860620946109] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
Intensive care units (ICUs) lack both standardized performance indicators to better understand the effectiveness of interventions and uniform platforms to present these indicators. The goal of this study was to identify ICU metrics meaningful to stakeholders to help guide the development of a local visualization dashboard. Individual ICU directors were interviewed to collate their input on metrics important to their units. These qualitative data were used to develop a dashboard draft, after which the authors surveyed 20 stakeholders from different hospital departments for feedback on its content and structure. The varied survey results reinforced the inherent difficulties of adapting previously developed measurement tools while also selecting ICU performance measures that are simultaneously widely accepted yet relevant to local practice. These results also call attention to the importance of interdisciplinary input in quality dashboard development, thereby enabling more successful implementation and utilization for ICU quality improvement.
Collapse
Affiliation(s)
- Asia A Williams
- Drexel University, Philadelphia, PA Thomas Jefferson University Hospital, Philadelphia, PA
| | | | | |
Collapse
|
29
|
Lee SI, Koh Y, Huh JW, Hong SB, Lim CM. Factors and Outcomes of Intensive Care Unit Readmission in Elderly Patients. Gerontology 2021; 68:280-288. [PMID: 34107481 DOI: 10.1159/000516297] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2020] [Accepted: 03/26/2021] [Indexed: 11/19/2022] Open
Abstract
INTRODUCTION An increase in age has been observed among patients admitted to the intensive care unit (ICU). Age is a well-known risk factor for ICU readmission and mortality. However, clinical characteristics and risk factors of ICU readmission of elderly patients (≥65 years) have not been studied. METHODS This retrospective single-center cohort study was conducted in a total of 122-bed ICU of a tertiary care hospital in Seoul, Korea. A total of 85,413 patients were enrolled in this hospital between January 1, 2007, and December 31, 2017. The odds ratio of readmission and in-hospital mortality was calculated by logistic regression analysis. RESULTS Totally, 29,503 patients were included in the study group, of which 2,711 (9.2%) had ICU readmissions. Of the 2,711 readmitted patients, 472 patients were readmitted more than once (readmitted 2 or more times to the ICU, 17.4%). In the readmitted patient group, there were more males, higher sequential organ failure assessment (SOFA) scores, and hospitalized for medical reasons. Length of stay (LOS) in ICU and in-hospital were longer, and 28-day and in-hospital mortality was higher in readmitted patients than in nonreadmitted patients. Risk factors of ICU readmission included the ICU admission due to medical reason, SOFA score, presence of chronic heart disease, diabetes mellitus, chronic kidney disease, transplantation, use of mechanical ventilation, and initial ICU LOS. ICU readmission and age (over 85 years) were independent predictors of in-hospital mortality on multivariable analysis. The delayed ICU readmission group (>72 h) had higher in-hospital mortality than the early readmission group (≤72 h) (20.6 vs. 16.2%, p = 0.005). CONCLUSIONS ICU readmissions occurred in 9.2% of elderly patients and were associated with poor prognosis and higher mortality.
Collapse
Affiliation(s)
- Song-I Lee
- Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Asan Medical Center, College of Medicine, University of Ulsan, Seoul, Republic of Korea, .,Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Chungnam National University Hospital, Chungnam National University School of Medicine, Daejeon, Republic of Korea,
| | - Younsuck Koh
- Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Asan Medical Center, College of Medicine, University of Ulsan, Seoul, Republic of Korea
| | - Jin Won Huh
- Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Asan Medical Center, College of Medicine, University of Ulsan, Seoul, Republic of Korea
| | - Sang-Bum Hong
- Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Asan Medical Center, College of Medicine, University of Ulsan, Seoul, Republic of Korea
| | - Chae-Man Lim
- Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Asan Medical Center, College of Medicine, University of Ulsan, Seoul, Republic of Korea
| |
Collapse
|
30
|
Kramer AA, Zimmerman JE, Knaus WA. Severity of Illness and Predictive Models in Society of Critical Care Medicine's First 50 Years: A Tale of Concord and Conflict. Crit Care Med 2021; 49:728-740. [PMID: 33729716 DOI: 10.1097/ccm.0000000000004924] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
Affiliation(s)
| | - Jack E Zimmerman
- The George Washington University School of Medicine, Washington, DC
| | | |
Collapse
|
31
|
Haribhakti N, Agarwal P, Vida J, Panahon P, Rizwan F, Orfanos S, Stoll J, Baig S, Cabrera J, Kostis JB, Ananth CV, Kostis WJ, Scardella AT. A Simple Scoring Tool to Predict Medical Intensive Care Unit Readmissions Based on Both Patient and Process Factors. J Gen Intern Med 2021; 36:901-907. [PMID: 33483824 PMCID: PMC8041987 DOI: 10.1007/s11606-020-06572-w] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/29/2020] [Accepted: 12/29/2020] [Indexed: 10/22/2022]
Abstract
BACKGROUND Although many predictive models have been developed to risk assess medical intensive care unit (MICU) readmissions, they tend to be cumbersome with complex calculations that are not efficient for a clinician planning a MICU discharge. OBJECTIVE To develop a simple scoring tool that comprehensively takes into account not only patient factors but also system and process factors in a single model to predict MICU readmissions. DESIGN Retrospective chart review. PARTICIPANTS We included all patients admitted to the MICU of Robert Wood Johnson University Hospital, a tertiary care center, between June 2016 and May 2017 except those who were < 18 years of age, pregnant, or planned for hospice care at discharge. MAIN MEASURES Logistic regression models and a scoring tool for MICU readmissions were developed on a training set of 409 patients, and validated in an independent set of 474 patients. KEY RESULTS Readmission rate in the training and validation sets were 8.8% and 9.1% respectively. The scoring tool derived from the training dataset included the following variables: MICU admission diagnosis of sepsis, intubation during MICU stay, duration of mechanical ventilation, tracheostomy during MICU stay, non-emergency department admission source to MICU, weekend MICU discharge, and length of stay in the MICU. The area under the curve of the scoring tool on the validation dataset was 0.76 (95% CI, 0.68-0.84), and the model fit the data well (Hosmer-Lemeshow p = 0.644). Readmission rate was 3.95% among cases in the lowest scoring range and 50% in the highest scoring range. CONCLUSION We developed a simple seven-variable scoring tool that can be used by clinicians at MICU discharge to efficiently assess a patient's risk of MICU readmission. Additionally, this is one of the first studies to show an association between MICU admission diagnosis of sepsis and MICU readmissions.
Collapse
Affiliation(s)
- Nirav Haribhakti
- Division of Pulmonary and Critical Care Medicine, Rutgers Robert Wood Johnson Medical School, 125 Paterson Street, Suite 5200B, New Brunswick, NJ, 08901, USA.
| | - Pallak Agarwal
- Division of Pulmonary and Critical Care Medicine, Rutgers Robert Wood Johnson Medical School, 125 Paterson Street, Suite 5200B, New Brunswick, NJ, 08901, USA
| | - Julia Vida
- Department of Computer Science, Rutgers, The State University of New Jersey, New Brunswick, NJ, USA
| | - Pamela Panahon
- Division of Pulmonary and Critical Care Medicine, Rutgers Robert Wood Johnson Medical School, 125 Paterson Street, Suite 5200B, New Brunswick, NJ, 08901, USA
| | - Farsha Rizwan
- Division of Pulmonary and Critical Care Medicine, Rutgers Robert Wood Johnson Medical School, 125 Paterson Street, Suite 5200B, New Brunswick, NJ, 08901, USA
| | - Sarah Orfanos
- Division of Pulmonary and Critical Care Medicine, Rutgers Robert Wood Johnson Medical School, 125 Paterson Street, Suite 5200B, New Brunswick, NJ, 08901, USA
| | - Jonathan Stoll
- Division of Pulmonary and Critical Care Medicine, Rutgers Robert Wood Johnson Medical School, 125 Paterson Street, Suite 5200B, New Brunswick, NJ, 08901, USA
| | - Saqib Baig
- Division of Pulmonary, Allergy, and Critical Care, Thomas Jefferson University Hospitals, Philadelphia, PA, USA
| | - Javier Cabrera
- Department of Statistics and Biostatistics, Rutgers, The State University of New Jersey, New Brunswick, NJ, USA.,Cardiovascular Institute, Rutgers Robert Wood Johnson Medical School, New Brunswick, NJ, USA
| | - John B Kostis
- Cardiovascular Institute, Rutgers Robert Wood Johnson Medical School, New Brunswick, NJ, USA
| | - Cande V Ananth
- Cardiovascular Institute, Rutgers Robert Wood Johnson Medical School, New Brunswick, NJ, USA.,Division of Epidemiology and Biostatistics, Department of Obstetrics, Gynecology, and Reproductive Sciences, Rutgers, The State University of New Jersey, New Brunswick, NJ, USA.,Department of Biostatistics and Epidemiology, Rutgers School of Public Health, Piscataway, NJ, USA
| | - William J Kostis
- Cardiovascular Institute, Rutgers Robert Wood Johnson Medical School, New Brunswick, NJ, USA
| | - Anthony T Scardella
- Division of Pulmonary and Critical Care Medicine, Rutgers Robert Wood Johnson Medical School, 125 Paterson Street, Suite 5200B, New Brunswick, NJ, 08901, USA
| |
Collapse
|
32
|
Kramer AA. Using genetic algorithms to identify deleterious patterns of physiologic data for near real-time prediction of mortality in critically ill patients. INFORMATICS IN MEDICINE UNLOCKED 2021. [DOI: 10.1016/j.imu.2021.100754] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022] Open
|
33
|
Moshynskyy AI, Mailman JF, Sy EJ. After-Hours/Nighttime Transfers Out of the Intensive Care Unit and Patient Outcomes: A Systematic Review and Meta-Analysis. J Intensive Care Med 2020; 37:211-221. [PMID: 33356770 DOI: 10.1177/0885066620984410] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
PURPOSE We evaluated the effects of after-hours/nighttime patient transfers out of the ICU on patient outcomes, by performing a systematic review and meta-analysis (PROSPERO CRD 42017074082). DATA SOURCES MEDLINE, PubMed, EMBASE, Google Scholar, CINAHL, and the Cochrane Library from 1987-November 2019. Conference abstracts from the Society of Critical Care Medicine, American Thoracic Society, CHEST, Critical Care Canada Forum, and European Society of Intensive Care Medicine from 2011-2019. DATA EXTRACTION Observational or randomized studies of adult ICU patients were selected if they compared after-hours transfer out of the ICU to daytime transfer on patient outcomes. Case reports, case series, letters, and reviews were excluded. Study year, country, design, co-variates for adjustment, definitions of after-hours, mortality rates, ICU readmission rates, and hospital length of stay (LOS) were extracted. DATA SYNTHESIS We identified 3,398 studies. Thirty-one observational studies (1,418,924 patients) were selected for the systematic review and meta-analysis. Included studies had varying definitions of after-hours, with the after-hours period starting anytime between 16:00-22:00 and ending between 06:00-09:00. Approximately 16% of transfers occurred after-hours. After-hours transfers were associated with increased in-hospital mortality for both unadjusted (odds ratio [OR] 1.51, 95% confidence interval [CI] 1.30-1.75, I2 = 96%, number of studies [n] = 26, P < 0.001, low certainty) and adjusted (OR 1.32, 95% CI 1.25-1.38, I 2 = 33%, n = 10, P < 0.001, low certainty) data, compared to daytime transfers. They were also associated with increased ICU readmission (pooled unadjusted OR 1.28, 95% CI 1.18-1.38, I2 = 85%, n = 17, P < 0.001, low certainty) and longer hospital LOS (standardized mean difference 0.13, 95% CI 0.09-0.18, I 2 = 93%, n = 9, P < 0.001, low certainty), compared to daytime transfers. CONCLUSIONS After-hours transfers out of the ICU are associated with increased in-hospital mortality, ICU readmission, and hospital LOS, across many settings. While the certainty of evidence is low, future research is needed to reduce the number and effects of after-hours transfers.
Collapse
Affiliation(s)
- Anton I Moshynskyy
- College of Medicine, University of Saskatchewan, Regina, Saskatchewan, Canada
| | - Jonathan F Mailman
- College of Medicine, University of Saskatchewan, Regina, Saskatchewan, Canada.,Department of Critical Care, Saskatchewan Health Authority, Regina, Saskatchewan, Canada.,Department of Pharmacy Services, Saskatchewan Health Authority, Regina, Saskatchewan, Canada
| | - Eric J Sy
- College of Medicine, University of Saskatchewan, Regina, Saskatchewan, Canada.,Department of Critical Care, Saskatchewan Health Authority, Regina, Saskatchewan, Canada
| |
Collapse
|
34
|
Improving ICU transitional care by combining quality management and nursing science – two scientific fields meet in a systematic literature review. INTERNATIONAL JOURNAL OF QUALITY AND SERVICE SCIENCES 2020. [DOI: 10.1108/ijqss-03-2020-0033] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
Purpose
The purpose of this literature review was to explore to what extent quality management (QM) and nursing science offer complementary perspectives to provide better quality care, by looking at QM core concepts and tools.
Design/methodology/approach
A systematic literature review was conducted. Papers published in academic journals between January 2013 and December 2019 were included. A deductive content analysis was chosen using QM core values as an analytical framework.
Findings
The results showed that QM core values, methodologies and tools were found in the reviewed articles about intensive care unit (ICU) transitional care. The results indicated that core values in QM and the core competencies within nursing science in ICU transitional care are mutually dependent upon each other and exist as a whole. ICU transitional care is, however, a complex interpersonal process, characterized by differences in organizational cultures and core values and involving multidisciplinary teams that collaborate across hospital units. The QM core value that was least observed was committed leadership.
Research limitations/implications
Combining QM and nursing science can contribute to a deeper understanding of how to improve the ICU transitional care process by bringing complementary perspectives.
Practical implications
The included articles portray how QM is applied in ICU transitional care. Implications for future research focus on enhancing the understanding of how QM and nursing science can bring complementary perspectives in order to improve ICU transitional care and how QM values, methodologies and tools can be used in ICU transitional care. Committed leadership and team collaboration in ICU transitional care are areas that call for further research.
Originality/value
The findings contribute to the body of literature by providing important insights in terms of how QM core values, methodologies and tools are present in research about ICU transitional care and how the two research subjects, namely, QM and nursing science, bring complementary perspectives.
Collapse
|
35
|
Hammer M, Grabitz SD, Teja B, Wongtangman K, Serrano M, Neves S, Siddiqui S, Xu X, Eikermann M. A Tool to Predict Readmission to the Intensive Care Unit in Surgical Critical Care Patients-The RISC Score. J Intensive Care Med 2020; 36:1296-1304. [PMID: 32840427 DOI: 10.1177/0885066620949164] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/28/2023]
Abstract
BACKGROUND Readmission to the Intensive Care Unit (ICU) is associated with a high risk of in-hospital mortality and higher health care costs. Previously published tools to predict ICU readmission in surgical ICU patients have important limitations that restrict their clinical implementation. We sought to develop a clinically intuitive score that can be implemented to predict readmission to the ICU after surgery or trauma. We designed the score to emphasize modifiable predictors. METHODS In this retrospective cohort study, we included surgical patients requiring critical care between June 2015 and January 2019 at Beth Israel Deaconess Medical Center, Harvard Medical School, MA, USA. We used logistic regression to fit a prognostic model for ICU readmission from a priori defined, widely available candidate predictors. The score performance was compared with existing prediction instruments. RESULTS Of 7,126 patients, 168 (2.4%) were readmitted to the ICU during the same hospitalization. The final score included 8 variables addressing demographical factors, surgical factors, physiological parameters, ICU treatment and the acuity of illness. The maximum score achievable was 13 points. Potentially modifiable predictors included the inability to ambulate at ICU discharge, substantial positive fluid balance (>5 liters), severe anemia (hemoglobin <7 mg/dl), hyperglycemia (>180 mg/dl), and long ICU length of stay (>5 days). The score yielded an area under the receiver operating characteristic curve of 0.78 (95% CI 0.74-0.82) and significantly outperformed previously published scores. The performance of the underlying model was confirmed by leave-one-out cross-validation. CONCLUSION The RISC-score is a clinically intuitive prediction instrument that helps identify surgical ICU patients at high risk for ICU readmission. The simplicity of the score facilitates its clinical implementation across surgical divisions.
Collapse
Affiliation(s)
- Maximilian Hammer
- Department of Anesthesia, Critical Care and Pain Medicine, Beth Israel Deaconess Medical Center, 1811Harvard Medical School, Boston, MA, USA
| | - Stephanie D Grabitz
- Department of Anesthesia, Critical Care and Pain Medicine, Beth Israel Deaconess Medical Center, 1811Harvard Medical School, Boston, MA, USA
| | - Bijan Teja
- Department of Anesthesia, Critical Care and Pain Medicine, Beth Israel Deaconess Medical Center, 1811Harvard Medical School, Boston, MA, USA
| | - Karuna Wongtangman
- Department of Anesthesia, Critical Care and Pain Medicine, Beth Israel Deaconess Medical Center, 1811Harvard Medical School, Boston, MA, USA
| | - Marjorie Serrano
- Cardiovascular Intensive Care Unit, Beth Israel Deaconess Medical Center, 1811Harvard Medical School, Boston, MA, USA
| | - Sara Neves
- Department of Anesthesia, Critical Care and Pain Medicine, Beth Israel Deaconess Medical Center, 1811Harvard Medical School, Boston, MA, USA
| | - Shahla Siddiqui
- Department of Anesthesia, Critical Care and Pain Medicine, Beth Israel Deaconess Medical Center, 1811Harvard Medical School, Boston, MA, USA
| | - Xinling Xu
- Department of Anesthesia, Critical Care and Pain Medicine, Beth Israel Deaconess Medical Center, 1811Harvard Medical School, Boston, MA, USA
| | - Matthias Eikermann
- Department of Anesthesia, Critical Care and Pain Medicine, Beth Israel Deaconess Medical Center, 1811Harvard Medical School, Boston, MA, USA
| |
Collapse
|
36
|
Bulgarelli L, Deliberato RO, Johnson AEW. Prediction on critically ill patients: The role of "big data". J Crit Care 2020; 60:64-68. [PMID: 32763775 DOI: 10.1016/j.jcrc.2020.07.017] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/07/2020] [Revised: 07/11/2020] [Accepted: 07/15/2020] [Indexed: 12/12/2022]
Abstract
Accurate outcome prediction in Intensive Care Units (ICUs) would allow for better treatment planning, risk adjustment of study populations, and overall improvements in patient care. In the past, prognostic models have focused on mortality using simple ordinal severity of illness scores which could be tabulated manually by a human. With the improvements in computing power and proliferation of electronic medical records, entirely new approaches have become possible. Here we review the latest advances in outcome prediction, paying close attention to methods which are widely applicable and provide a high-level overview of the challenges the field currently faces.
Collapse
Affiliation(s)
- Lucas Bulgarelli
- MIT Critical Data, Laboratory for Computational Physiology, Harvard-MIT Health Sciences & Technology, Massachusetts Institute of Technology, Cambridge, USA; Big Data Analytics Department, Hospital Israelita Albert Einstein, São Paulo, Brazil.
| | - Rodrigo Octávio Deliberato
- MIT Critical Data, Laboratory for Computational Physiology, Harvard-MIT Health Sciences & Technology, Massachusetts Institute of Technology, Cambridge, USA; Department of Clinical Data Science Research, Endpoint Health, Inc., USA
| | - Alistair E W Johnson
- MIT Critical Data, Laboratory for Computational Physiology, Harvard-MIT Health Sciences & Technology, Massachusetts Institute of Technology, Cambridge, USA
| |
Collapse
|
37
|
Balshi AN, Huwait BM, Noor ASN, Alharthy AM, Madi AF, Ramadan OE, Balahmar A, Mhawish HA, Marasigan BR, Alcazar AM, Rana MA, Aletreby WT. Modified Early Warning Score as a predictor of intensive care unit readmission within 48 hours: a retrospective observational study. Rev Bras Ter Intensiva 2020; 32:301-307. [PMID: 32667433 PMCID: PMC7405753 DOI: 10.5935/0103-507x.20200047] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/17/2019] [Accepted: 02/17/2020] [Indexed: 12/23/2022] Open
Abstract
OBJECTIVE To evaluate the hypothesis that the Modified Early Warning Score (MEWS) at the time of intensive care unit discharge is associated with readmission and to identify the MEWS that most reliably predicts intensive care unit readmission within 48 hours of discharge. METHODS This was a retrospective observational study of the MEWSs of discharged patients from the intensive care unit. We compared the demographics, severity scores, critical illness characteristics, and MEWSs of readmitted and non-readmitted patients, identified factors associated with readmission in a logistic regression model, constructed a Receiver Operating Characteristic (ROC) curve of the MEWS in predicting the probability of readmission, and presented the optimum criterion with the highest sensitivity and specificity. RESULTS The readmission rate was 2.6%, and the MEWS was a significant predictor of readmission, along with intensive care unit length of stay > 10 days and tracheostomy. The ROC curve of the MEWS in predicting the readmission probability had an AUC of 0.82, and a MEWS > 6 carried a sensitivity of 0.78 (95%CI 0.66 - 0.9) and specificity of 0.9 (95%CI 0.87 - 0.93). CONCLUSION The MEWS is associated with intensive care unit readmission, and a score > 6 has excellent accuracy as a prognostic predictor.
Collapse
Affiliation(s)
- Ahmed Naji Balshi
- Critical Care Department, King Saud Medical City, Riyadh, Saudi Arabia
| | | | | | | | - Ahmed Fouad Madi
- Critical Care Department, King Saud Medical City, Riyadh, Saudi Arabia
| | | | - Abdullah Balahmar
- Critical Care Department, King Saud Medical City, Riyadh, Saudi Arabia
| | - Huda A Mhawish
- Critical Care Department, King Saud Medical City, Riyadh, Saudi Arabia
| | | | | | - Muhammad Asim Rana
- Internal Medicine and Critical Care Department, Bahria Town International Hospital, Lahore, Pakistan
| | | |
Collapse
|
38
|
Lavoie P, Clarke SP, Clausen C, Purden M, Emed J, Cosencova L, Frunchak V. Nursing handoffs and clinical judgments regarding patient risk of deterioration: A mixed-methods study. J Clin Nurs 2020; 29:3790-3801. [PMID: 32644241 DOI: 10.1111/jocn.15409] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2020] [Revised: 06/09/2020] [Accepted: 06/21/2020] [Indexed: 11/30/2022]
Abstract
AIMS AND OBJECTIVES To explore how change-of-shift handoffs relate to nurses' clinical judgments regarding patient risk of deterioration. BACKGROUND The transfer of responsibility for patients' care comes with an exchange of information about their condition during change-of-shift handoff. However, it is unclear how this exchange affects nurses' clinical judgments regarding patient risk of deterioration. DESIGN A sequential explanatory mixed-methods study reported according to the STROBE and COREQ guidelines. METHODS Over four months, 62 nurses from one surgical and two medical units at a single Canadian hospital recorded their handoffs at change of shift. After each handoff, the two nurses involved each rated the patient's risk of experiencing cardiac arrest or being transferred to an intensive care unit in the next 24 hr separately. The information shared in handoffs was subjected to content analysis; code frequencies were contrasted per nurses' ratings of patient risk to identify characteristics of information that facilitated or hindered nurses' agreement. RESULTS Out of 444 recorded handoffs, there were 125 in which at least one nurse judged that a patient was at risk of deterioration; nurses agreed in 32 cases (25.6%) and disagreed in 93 (74.4%). These handoffs generally included information on abnormal vital signs, breathing problems, chest pain, alteration of mental status or neurological symptoms. However, the quantity and seriousness of clinical cues, recent transfers from intensive care units, pain without a clear cause, signs of delirium and nurses' knowledge of patient were found to affect nurses' agreement. CONCLUSIONS Nurses exchanged more information regarding known indicators of deterioration in handoffs when they judged that patients were at risk. Disagreements most often involved incoming nurses rating patient risk as higher. RELEVANCE TO CLINICAL PRACTICE This study suggests a need to sensitise nurses to the impact of certain cues at report on their colleagues' subsequent clinical judgments. Low levels of agreement between nurses underscore the importance of exchanging impressions regarding the likely evolution of a patient's situation to promote continuity of care.
Collapse
Affiliation(s)
- Patrick Lavoie
- Faculty of Nursing, Université de Montréal, Montreal, QC, Canada.,Montreal Heart Institute Research Center, Montreal, QC, Canada
| | - Sean P Clarke
- Rory Meyers College of Nursing, New York University, New York, NY, USA
| | - Christina Clausen
- Center for Nursing Research, Jewish General Hospital, Montreal, QC, Canada.,Ingram School of Nursing, McGill University, Montreal, QC, Canada.,Department of Nursing, Jewish General Hospital, Montreal, QC, Canada
| | - Margaret Purden
- Center for Nursing Research, Jewish General Hospital, Montreal, QC, Canada.,Ingram School of Nursing, McGill University, Montreal, QC, Canada
| | - Jessica Emed
- Ingram School of Nursing, McGill University, Montreal, QC, Canada.,Department of Nursing, Jewish General Hospital, Montreal, QC, Canada
| | - Lidia Cosencova
- Center for Nursing Research, Jewish General Hospital, Montreal, QC, Canada
| | - Valerie Frunchak
- Ingram School of Nursing, McGill University, Montreal, QC, Canada.,Department of Nursing, Jewish General Hospital, Montreal, QC, Canada
| |
Collapse
|
39
|
Mcneill H, Khairat S. Impact of Intensive Care Unit Readmissions on Patient Outcomes and the Evaluation of the National Early Warning Score to Prevent Readmissions: Literature Review. JMIR Perioper Med 2020; 3:e13782. [PMID: 33393911 PMCID: PMC7709858 DOI: 10.2196/13782] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2019] [Revised: 06/02/2019] [Accepted: 02/04/2020] [Indexed: 01/22/2023] Open
Abstract
Background Intensive care unit (ICU) readmissions have been shown to increase a patient’s in-hospital mortality and length of stay (LOS). Despite this, no methods have been set in place to prevent readmissions from occurring. Objective The aim of this literature review was to evaluate the impact of ICU readmission on patient outcomes and to evaluate the effect of using a risk stratification tool, the National Early Warning Score (NEWS), on ICU readmissions. Methods A database search was performed on PubMed, Cumulative Index of Nursing and Allied Health Literature, Google Scholar, and ProQuest. In the initial search, 2028 articles were retrieved; after inclusion and exclusion criteria were applied, 12 articles were ultimately used in this literature review. Results This literature review found that patients readmitted to the ICU have an increased mortality rate and LOS at the hospital. The sample sizes in the reviewed studies ranged from 158 to 745,187 patients. Readmissions were most commonly associated with respiratory issues about 18% to 59% of the time. The NEWS has been shown to detect early clinical deterioration in a patient within 24 hours of transfer, with a 95% CI of 0.89 to 0.94 (P<.001), a sensitivity of 93.6% , and a specificity of 82.2%. Conclusions ICU readmissions are associated with worse patient outcomes, including hospital mortality and increased LOS. Without the use of an objective screening tool, the provider has been solely responsible for the decision of patient transfer. Assessment with the NEWS could be helpful in decreasing the frequency of inappropriate transfers and ultimately ICU readmission.
Collapse
Affiliation(s)
- Heidi Mcneill
- School of Nursing, University of North Carolina at Chapel Hill, Chapel Hill, NC, United States
| | - Saif Khairat
- School of Nursing, University of North Carolina at Chapel Hill, Chapel Hill, NC, United States.,Carolina Health Informatics Program, University of North Carolina at Chapel Hill, Chapel Hill, NC, United States
| |
Collapse
|
40
|
Benchmarking Deep Learning Architectures for Predicting Readmission to the ICU and Describing Patients-at-Risk. Sci Rep 2020; 10:1111. [PMID: 31980704 PMCID: PMC6981230 DOI: 10.1038/s41598-020-58053-z] [Citation(s) in RCA: 36] [Impact Index Per Article: 7.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/14/2019] [Accepted: 01/06/2020] [Indexed: 02/01/2023] Open
Abstract
To compare different deep learning architectures for predicting the risk of readmission within 30 days of discharge from the intensive care unit (ICU). The interpretability of attention-based models is leveraged to describe patients-at-risk. Several deep learning architectures making use of attention mechanisms, recurrent layers, neural ordinary differential equations (ODEs), and medical concept embeddings with time-aware attention were trained using publicly available electronic medical record data (MIMIC-III) associated with 45,298 ICU stays for 33,150 patients. Bayesian inference was used to compute the posterior over weights of an attention-based model. Odds ratios associated with an increased risk of readmission were computed for static variables. Diagnoses, procedures, medications, and vital signs were ranked according to the associated risk of readmission. A recurrent neural network, with time dynamics of code embeddings computed by neural ODEs, achieved the highest average precision of 0.331 (AUROC: 0.739, F1-Score: 0.372). Predictive accuracy was comparable across neural network architectures. Groups of patients at risk included those suffering from infectious complications, with chronic or progressive conditions, and for whom standard medical care was not suitable. Attention-based networks may be preferable to recurrent networks if an interpretable model is required, at only marginal cost in predictive accuracy.
Collapse
|
41
|
Readmissions to General ICUs in a Geographic Area of Poland Are Seemingly Associated with Better Outcomes. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2020; 17:ijerph17020565. [PMID: 31963101 PMCID: PMC7014014 DOI: 10.3390/ijerph17020565] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/22/2019] [Revised: 01/07/2020] [Accepted: 01/09/2020] [Indexed: 11/17/2022]
Abstract
BACKGROUND Various factors can contribute to high mortality rates in intensive care units (ICUs). Here, we intended to define a population of patients readmitted to general ICUs in Poland and to identify independent predictors of ICU readmission. METHODS Data derived from adult ICU admissions from the Silesian region of Poland were analyzed. First-time ICU readmissions (≤30 days from ICU discharge after index admissions) were compared with first-time ICU admissions. Pre-admission and admission variables that independently influenced the need for ICU readmission were identified. RESULTS Among the 21,495 ICU admissions, 839 were first-time readmissions (3.9%). Patients readmitted to the ICU had lower mean APACHE II (21.2 ± 8.0 vs. 23.2 ± 8.8, p < 0.001) and TISS-28 scores (33.7 ± 7.4 vs. 35.2 ± 7.8, p < 0.001) in the initial 24 h following ICU admission, compared to first-time admissions. ICU readmissions were associated with lower mortality vs. first-time admissions (39.2% vs. 44.3%, p = 0.004). Independent predictors for ICU readmission included the admission from a surgical ward (among admission sources), chronic respiratory failure, cachexia, previous stroke, chronic neurological diseases (among co-morbidities), and multiple trauma or infection (among primary reasons for ICU admission). CONCLUSIONS High mortality associated with first-time ICU admissions is associated with a lower mortality rate during ICU readmissions.
Collapse
|
42
|
Morgan M, Vernon T, Bradburn EH, Miller JA, Jammula S, Rogers FB. A Comprehensive Review of the Outcome for Patients Readmitted to the ICU Following Trauma and Strategies to Decrease Readmission Rates. J Intensive Care Med 2020; 35:936-942. [PMID: 31916876 DOI: 10.1177/0885066619899639] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
In recent years, there has been an emphasis on evaluating the outcomes of patients who have experienced an intensive care unit (ICU) readmission. This may in part be due to the Patient Protection and Affordable Care Act's Hospital Readmission Reduction Program which imposes financial sanctions on hospitals who have excessive readmission rates, informally known as bounceback rates. The financial cost associated with avoidable bounceback combined with the potentially preventable expenses can result in unnecessary financial strain. Within the hospital readmissions, there is a subset pertaining to unplanned readmission to the ICU. Although there have been studies regarding ICU bounceback, there are limited studies regarding ICU bounceback of trauma patients and even fewer proven strategies. Although many studies have concluded that respiratory complications were the most common factor influencing ICU readmissions, there is inconclusive evidence in terms of a broadly applicable strategy that would facilitate management of these patients. The purpose of this review is to highlight the outcomes of patients readmitted to the ICU and to provide an overview of possible strategies to aid in decreasing ICU readmission rates.
Collapse
Affiliation(s)
- Madison Morgan
- Trauma Services, 4399Penn Medicine Lancaster General Health, Lancaster, PA, USA
| | - Tawnya Vernon
- Trauma Services, 4399Penn Medicine Lancaster General Health, Lancaster, PA, USA
| | - Eric H Bradburn
- Trauma Services, 4399Penn Medicine Lancaster General Health, Lancaster, PA, USA
| | - Jo Ann Miller
- Trauma Services, 4399Penn Medicine Lancaster General Health, Lancaster, PA, USA
| | - Shreya Jammula
- Trauma Services, 4399Penn Medicine Lancaster General Health, Lancaster, PA, USA
| | - Frederick B Rogers
- Trauma Services, 4399Penn Medicine Lancaster General Health, Lancaster, PA, USA
| |
Collapse
|
43
|
Malhotra D, Nour N, El Halik M, Zidan M. Performance and Analysis of Pediatric Index of Mortality 3 Score in a Pediatric ICU in Latifa Hospital, Dubai, UAE. DUBAI MEDICAL JOURNAL 2019. [DOI: 10.1159/000505205] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022] Open
|
44
|
Oh TK, Song IA, Jeon YT. Impact of Glasgow Coma Scale scores on unplanned intensive care unit readmissions among surgical patients. ANNALS OF TRANSLATIONAL MEDICINE 2019; 7:520. [PMID: 31807502 DOI: 10.21037/atm.2019.10.06] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Abstract
Background Physiological instability at discharge from intensive care units (ICU) is known to increase readmission rates among critically ill patients. However, associations between consciousness levels at discharge and readmission rates remain unclear. This study aimed to investigate the association between the Glasgow Coma Scale (GCS) score at discharge and unplanned ICU readmissions in surgical patients. Methods This retrospective cohort study in a single tertiary academic hospital analyzed the electronic health records of adults aged 18 years or older, who were discharged from the ICU between January 2012 and December 2018. The primary endpoint was unplanned readmission within 48 hours after discharge. Multivariable logistic regression analysis was performed. Results Among 9,512 patients, unplanned readmissions occurred in 161 (1.7%). At discharge, GCS and verbal response scores of ≤13 (vs. ≥14) were associated with 2.28-fold higher unplanned readmissions within 48 hours [odds ratio (OR): 2.35, 95% confidence interval (CI): 1.51-3.65, P<0.001]. Sensitivity analysis showed that verbal response scores of ≤4 (vs. 5) at ICU discharge were associated with 2.21-fold higher unplanned readmissions within 48 hours (OR: 2.21, 95% CI: 1.49-3.29, P<0.001), whereas eye or motor responses at time of ICU discharge were not significantly associated with unplanned readmissions (P>0.05). Conclusions In this surgical ICU population cohort, GCS scores at ICU discharge were significantly associated with unplanned readmissions within 48 hours. This association was stronger with GCS scores of ≤13 and with verbal response scores of ≤4 at time of discharge. These findings suggest that surgical ICU patients with GCS scores of ≤13 or verbal response scores of ≤4 should be monitored carefully for discharge in order to avoid unplanned ICU readmissions.
Collapse
Affiliation(s)
- Tak Kyu Oh
- Department of Anesthesiology and Pain Medicine, Seoul National University Bundang Hospital, Seongnam-si, South Korea
| | - In-Ae Song
- Department of Anesthesiology and Pain Medicine, Seoul National University Bundang Hospital, Seongnam-si, South Korea
| | - Young-Tae Jeon
- Department of Anesthesiology and Pain Medicine, Seoul National University Bundang Hospital, Seongnam-si, South Korea.,Department of Anesthesiology and Pain Medicine, College of Medicine, Seoul, South Korea
| |
Collapse
|
45
|
Abstract
OBJECTIVES To identify modifiable factors leading to unplanned readmission and characterize differences in adjusted unplanned readmission rates across hospitals. DESIGN Retrospective cohort study using prospectively collected clinical registry data SETTING:: Pediatric Cardiac Critical Care Consortium clinical registry. PATIENTS Patients admitted to a pediatric cardiac ICU at Pediatric Cardiac Critical Care Consortium hospitals. INTERVENTIONS None. MEASUREMENTS AND MAIN RESULTS We examined pediatric cardiac ICU encounters in the Pediatric Cardiac Critical Care Consortium registry from October 2013 to March 2016. The primary outcomes were early (< 48 hr from pediatric cardiac ICU transfer) and late (2-7 d) unplanned readmission. Generalized logit models identified independent predictors of unplanned readmission. We then calculated observed-to-expected ratios of unplanned readmission and identified higher-than or lower-than-expected unplanned readmission rates for those with an observed-to-expected ratios greater than or less than 1, respectively, and a 95% CI that did not cross 1. Of 11,301 pediatric cardiac ICU encounters (16 hospitals), 62% were surgical, and 18% were neonates. There were 175 (1.6%) early unplanned readmission, and 300 (2.7%) late unplanned readmission, most commonly for respiratory (31%), or cardiac (28%) indications. In multivariable analysis, unique modifiable factors were associated with unplanned readmission. Although shorter time between discontinuation of vasoactive infusions and pediatric cardiac ICU transfer was associated with early unplanned readmission, nighttime discharge was independently associated with a greater likelihood of late unplanned readmission. Two hospitals had lower-than-expected unplanned readmission in both the early and late categories, whereas two other hospitals were higher-than-expected in both. CONCLUSIONS This analysis demonstrated time from discontinuation of critical care therapies to pediatric cardiac ICU transfer as a significant, modifiable predictor of unplanned readmission. We identified two hospitals with lower-than-expected adjusted rates of both early and late unplanned readmission, suggesting that their systems are well designed to prevent unplanned readmission. This offers the possibility of disseminating best practices to other hospitals through collaborative learning.
Collapse
|
46
|
Markazi-Moghaddam N, Fathi M, Ramezankhani A. Risk prediction models for intensive care unit readmission: A systematic review of methodology and applicability. Aust Crit Care 2019; 33:367-374. [PMID: 31402266 DOI: 10.1016/j.aucc.2019.05.005] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2018] [Revised: 05/08/2019] [Accepted: 05/28/2019] [Indexed: 02/08/2023] Open
Abstract
OBJECTIVE We conducted a systematic review of primary models to predict intensive care unit (ICU) readmission. REVIEW METHODS We searched MEDLINE, PubMed, Scopus, and Embase for studies on the development of ICU readmission prediction models that are published until January 2017. Data were extracted on the source of data, participants, outcomes, candidate predictors, sample size, missing data, methods for model development, and measures of model performance and model evaluation. The quality and applicability of the included studies were assessed using the CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies. RESULTS We identified five studies describing the development of the primary prediction models of ICU readmission. Studies ranged in size from 343 to 704,963 patients with the mean age of 58.0-68.9 years. The proportion of readmission ranged from 2.5% to 9.6%. The discriminative ability of prediction models measured by area under the receiver operating characteristic curve was 0.66-0.81. None of the studies performed external validations. The quality scores ranged from 42 to 54 out of 62, and the applicability scores from 24 to 32 out of 38. CONCLUSION We identified five prediction models for ICU readmission. However, owing to the numerous methodological and reporting deficiencies in the included studies, physicians using these models should interpret the predictions with precautions until an external validation study shows the acceptable level of calibration and accuracy of these models.
Collapse
Affiliation(s)
- Nader Markazi-Moghaddam
- Department of Public Health, School of Medicine, AJA University of Medical Sciences, Tehran, Iran; Critical Care Quality Improvement Research Center, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Mohammad Fathi
- Critical Care Quality Improvement Research Center, Shahid Beheshti University of Medical Sciences, Tehran, Iran; Department of Anesthesiology, Shahid Modarres Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Azra Ramezankhani
- Prevention of Metabolic Disorders Research Center, Research Institute for Endocrine Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
| |
Collapse
|
47
|
Taniguchi LU, Ramos FJDS, Momma AK, Martins Filho APR, Bartocci JJ, Lopes MFD, Sad MH, Rodrigues CM, Pires Siqueira EM, Vieira JM. Subjective score and outcomes after discharge from the intensive care unit: a prospective observational study. J Int Med Res 2019; 47:4183-4193. [PMID: 31304841 PMCID: PMC6753551 DOI: 10.1177/0300060519859736] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022] Open
Abstract
Objective Intensive care unit (ICU) discharge is a decision process that is usually
performed subjectively. We evaluated whether a subjective score (Sabadell
score) is associated with hospital outcomes. Methods We conducted a prospective cohort study from August 2014 to May 2015 at a
tertiary-care private hospital in Brazil. We analyzed 425 patients who were
discharged alive from the ICU to the wards. We used univariate and
multivariate analysis to identify risk factors associated with a composite
endpoint of worse outcomes (later ICU readmission or ward death) during the
same hospitalization. Results Forty-three patients (10.1%) were readmitted after ICU discharge, and 19 died
in the ward. Compared with patients with successful outcomes, those with the
composite endpoint were older and more severely ill, had a nonsurgical
reason for hospitalization, more frequently came from the ward, were less
frequently independent during daily activities, had sepsis, had higher
C-reactive protein concentrations at ICU admission, and had higher Sabadell
scores at discharge. The multivariate analysis showed that sepsis and the
Sabadell score were independently and significantly associated with worse
outcomes. Conclusion Sepsis at admission and the Sabadell score were predictors of worse hospital
outcomes. The Sabadell score might be a promising predictive tool.
Collapse
Affiliation(s)
- Leandro Utino Taniguchi
- Hospital Sirio-Libanes, São Paulo, Brazil.,Emergency Medicine Discipline, Hospital das Clinicas HCFMUSP, Faculdade de Medicina, Universidade de Sao Paulo, São Paulo, Brazil
| | | | | | | | | | | | | | | | | | | |
Collapse
|
48
|
Lin YW, Zhou Y, Faghri F, Shaw MJ, Campbell RH. Analysis and prediction of unplanned intensive care unit readmission using recurrent neural networks with long short-term memory. PLoS One 2019; 14:e0218942. [PMID: 31283759 PMCID: PMC6613707 DOI: 10.1371/journal.pone.0218942] [Citation(s) in RCA: 56] [Impact Index Per Article: 9.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/27/2018] [Accepted: 06/11/2019] [Indexed: 11/18/2022] Open
Abstract
BACKGROUND Unplanned readmission of a hospitalized patient is an indicator of patients' exposure to risk and an avoidable waste of medical resources. In addition to hospital readmission, intensive care unit (ICU) readmission brings further financial risk, along with morbidity and mortality risks. Identification of high-risk patients who are likely to be readmitted can provide significant benefits for both patients and medical providers. The emergence of machine learning solutions to detect hidden patterns in complex, multi-dimensional datasets provides unparalleled opportunities for developing an efficient discharge decision-making support system for physicians and ICU specialists. METHODS AND FINDINGS We used supervised machine learning approaches for ICU readmission prediction. We used machine learning methods on comprehensive, longitudinal clinical data from the MIMIC-III to predict the ICU readmission of patients within 30 days of their discharge. We incorporate multiple types of features including chart events, demographic, and ICD-9 embeddings. We have utilized recent machine learning techniques such as Recurrent Neural Networks (RNN) with Long Short-Term Memory (LSTM), by this we have been able to incorporate the multivariate features of EHRs and capture sudden fluctuations in chart event features (e.g. glucose and heart rate). We show that our LSTM-based solution can better capture high volatility and unstable status in ICU patients, an important factor in ICU readmission. Our machine learning models identify ICU readmissions at a higher sensitivity rate of 0.742 (95% CI, 0.718-0.766) and an improved Area Under the Curve of 0.791 (95% CI, 0.782-0.800) compared with traditional methods. We perform in-depth deep learning performance analysis, as well as the analysis of each feature contribution to the predictive model. CONCLUSION Our manuscript highlights the ability of machine learning models to improve our ICU decision-making accuracy and is a real-world example of precision medicine in hospitals. These data-driven solutions hold the potential for substantial clinical impact by augmenting clinical decision-making for physicians and ICU specialists. We anticipate that machine learning models will improve patient counseling, hospital administration, allocation of healthcare resources and ultimately individualized clinical care.
Collapse
Affiliation(s)
- Yu-Wei Lin
- Department of Business Administration, University of Illinois at Urbana-Champaign, Champaign, Illinois, United States of America
| | - Yuqian Zhou
- Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Champaign, Illinois, United States of America
| | - Faraz Faghri
- Department of Computer Science, University of Illinois at Urbana-Champaign, Champaign, Illinois, United States of America
- Laboratory of Neurogenetics, National Institute on Aging, National Institutes of Health, Bethesda, Maryland, United States of America
| | - Michael J. Shaw
- Department of Business Administration, University of Illinois at Urbana-Champaign, Champaign, Illinois, United States of America
| | - Roy H. Campbell
- Department of Computer Science, University of Illinois at Urbana-Champaign, Champaign, Illinois, United States of America
| |
Collapse
|
49
|
Comfort care in trauma patients without severe head injury: In-hospital complications as a trigger for goals of care discussions. Injury 2019; 50:1064-1067. [PMID: 30745124 DOI: 10.1016/j.injury.2019.01.024] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/28/2018] [Revised: 01/08/2019] [Accepted: 01/12/2019] [Indexed: 02/02/2023]
Abstract
INTRODUCTION Many injured patients or their families make the difficult decision to withdraw life-sustaining therapies (WLST) following severe injury. While this population has been studied in the setting of severe traumatic brain injury (TBI), little is known about patients who undergo WLST without TBI. We sought to describe patients who may benefit from early involvement of end-of-life resources. METHODS Trauma Quality Improvement Program (2013-2014) patients who underwent WLST were identified. WLST patients were compared to those who died with full supportive care (FSC). Patients were excluded for death within 24 h of admission, or head AIS > 3. Intergroup comparisons were by student's t tests or Wilcoxon rank sum tests; significance for p < 0.05. RESULTS We identified 3471 total injured patients without major TBI who died > 24 h after admission. Of these death after WLST occurred in 2301 (66% of total). This group had a mean age of 66.8 years; 35.7% were women, and 95.4% sustained blunt injury. WLST patients had a higher ISS (21.6 vs. 12.5, p = 0.001), more in-hospital complications (71.4% vs. 41.6%, p = < 0.0001), and a longer ICU length of stay (8.9 days vs. 7.5 days, p = <0.0001) compared to patients who died with FSC. CONCLUSION WLST occurs in two-thirds of injured patients without severe TBI who die in the hospital. In-hospital complications are more frequent in this patient group than those who die with FSC. Early palliative care consultation may improve patient and family satisfaction after acute injury when the timeframe to leverage such services is significantly condensed.
Collapse
|
50
|
Wilson DM, Shen Y, Birch S. Who Are High Users of Hospitals in Canada? Findings From a Population-Based Study. Can J Nurs Res 2019; 51:245-254. [PMID: 30845831 DOI: 10.1177/0844562119833584] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022] Open
Abstract
Background Dying people and older people have often been thought of as high users of hospitals, but current population-based evidence is needed to confirm or refute this claim. Purpose Quantitative population-based study designed to identify and describe hospital patients who are high users. Methods Data for all 2014–2015 Canadian hospital patients (excluding Quebec) were analyzed to identify and describe high users through descriptive-comparative and regression analysis tests. Results Only a small proportion of patients are high users in relation to multiple admissions or 30+ inpatient days of care, and with considerable diversity among them and relatively few of these advanced in age or dying in hospital. Conclusions Relatively few patients are high users of hospitals. These people are most often under age 65, so they have the potential to be ill and high users for many years. Flagging would enable individualized care planning to reduce illness exacerbations or slow disease progression and address other risk factors for long or repeat hospitalizations.
Collapse
Affiliation(s)
- Donna M Wilson
- Faculty of Nursing, University of Alberta, Edmonton, AB, Canada.,Faculty of Medicine and Dentistry, University of Alberta, Edmonton, AB, Canada.,Faculty of Education & Health Sciences, University of Limerick, Limerick, Ireland
| | - Ye Shen
- School of Public Health, University of Alberta, Edmonton, Alberta, Canada
| | - Stephen Birch
- Centre for the Business and Economics of Health, University of Queensland, Brisbane, Australia
| |
Collapse
|