|
1
|
van de Klundert J, Perez-Galarce F, Olivares M, Pengel L, de Weerd A. The comparative performance of models predicting patient and graft survival after kidney transplantation: A systematic review. Transplant Rev (Orlando) 2025; 39:100934. [PMID: 40339177 DOI: 10.1016/j.trre.2025.100934] [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: 02/05/2025] [Revised: 04/25/2025] [Accepted: 04/26/2025] [Indexed: 05/10/2025]
Abstract
BACKGROUND Cox proportional hazard models have long been the model of choice for survival prediction after kidney transplantation. In recent years, a variety of novel model types have been proposed. We investigate the prediction performance across different model types, including machine learning models and traditional model types. METHODS A systematic review was conducted following PROBAST and CHARMS, also considering extensions to TRIPOD+AI and PROBAST+AI, for data collection and risk of bias assessment. The review only included publications that reported on prediction performance for models of different types. A comparative analysis tested performance differences between the model types. RESULTS The review included 37 publications which presented 134 comparative studies. The designs of many studies left room for improvement and most studies had high risk of bias. The collected data admitted testing of performance differences for 22 pairs of model types, ten of which yielded significant differences. Support Vector Machines and Logistic Regression were never found to outperform other model types. Other comparisons, however, provide inconclusive comparative performance results and none of the model types performed consistently and significantly better than alternatives. CONCLUSIONS Rigorous review of current evidence and comparative performance evidence finds no significant kidney transplant survival prediction performance differences that Cox Proportional Hazard models are being outperformed. The design of many of the studies implies high risk of bias and more and better designed studies which reutilize best performing models are needed. This enables to resolve model biases, reporting issues, and to increase the power of comparative performance analysis.
Collapse
Affiliation(s)
| | - Francisco Perez-Galarce
- Department of Computer Science, School of Engineering, Pontifica Universidad Catolica, Santiago, Chile; Facultad de Ingeniería y Negocios, Universidad de Las Américas, Sede Providencia, Manuel Montt 948, Santiago, Chile
| | - Marcelo Olivares
- Faculty of Economics and Business, Universidad de Chile, Santiago, Chile
| | - Liset Pengel
- Erasmus MC Transplant Institute, University Medical Center Rotterdam, the Netherlands
| | - Annelies de Weerd
- Erasmus MC Transplant Institute, University Medical Center Rotterdam, Department of Internal Medicine, the Netherlands
| |
Collapse
|
|
2
|
Li R. Should we adopt a "laparoscopy first" strategy? A comparison of 30-day outcomes between converted open from laparoscopic and planned open colectomy for volvulus. Updates Surg 2025:10.1007/s13304-025-02133-0. [PMID: 40025297 DOI: 10.1007/s13304-025-02133-0] [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: 07/11/2024] [Accepted: 02/24/2025] [Indexed: 03/04/2025]
Abstract
While the majority of colectomy for volvulus is performed by an open approach, laparoscopy can be used as a potentially safer alternative. However, conversion to open is needed when the laparoscopic approach is unsuccessful. This study aimed to compare the 30-day outcomes of patients who had converted open from laparoscopy vs planned open colectomy for volvulus to assess a possible "laparoscopy first" strategy. In addition, this study identified risk factors associated with the conversion during laparoscopy. National Surgical Quality Improvement Program (NSQIP) targeted colectomy database from 2012 to 2022 was utilized. Patients with volvulus as the primary indication for laparoscopic and open colectomy were selected. Patients who had a conversion from laparoscopic to open surgery and planned open surgery were further identified. A 1:5 propensity-score matching was applied to converted open and planned open to match sex, race and ethnicity, age, baseline characteristics, preoperative preparation, and indication for surgery (if emergent). Thirty-day postoperative outcomes were examined. There were 1774 (22.10%) and 6254 (77.90%) patients who underwent laparoscopic and planned open colectomy for volvulus, respectively. From laparoscopy, 336 (18.94%) patients were converted to open surgery and 1,680 planned open cases were matched to the converted open cases. After propensity-score matching, patients underwent converted open and planned open had a comparable mortality rate (5.06% vs 3.99%, p = 0.37). However, patients who underwent converted open surgery had higher risks of renal complications (2.68% vs 0.60%, p < 0.01), bleeding requiring transfusion (9.82% vs 6.55%, p = 0.04), and wound complications (17.86% vs 12.26%, p = 0.01). Risk factors associated with conversion from laparoscopic to open colectomy included perforation (aOR = 4.767, p < 0.01), obstruction (aOR = 2.223, p < 0.01), sepsis 48 h before surgery (aOR = 2.952, p < 0.01), chronic kidneys disease (aOR = 1.602, p = 0.01) and preoperative infection (aOR = 1.489, p = 0.03). These identified risk factors demonstrated both strong discriminative (c-statistics = 0.713) and predictive (Brier score = 0.132) powers for open conversion. While laparoscopy for colonic volvulus may offer safer outcomes, a ubiquitous "laparoscopy first" strategy may be approached with caution. The increased risks of complications upon conversion to open surgery, particularly in patients with identified risk factors, suggest that careful patient selection may be crucial.
Collapse
Affiliation(s)
- Renxi Li
- The George Washington University School of Medicine and Health Sciences, 2300 I St NW, Washington, D.C., 20052, USA.
| |
Collapse
|
|
3
|
Li R, Sidawy A, Nguyen BN. Predictors of 30 Day Ischaemic Colitis after Endovascular Repair of Non-ruptured Infrarenal Abdominal Aortic Aneurysm. Eur J Vasc Endovasc Surg 2025; 69:496-497. [PMID: 39613225 DOI: 10.1016/j.ejvs.2024.11.349] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/24/2024] [Revised: 11/11/2024] [Accepted: 11/20/2024] [Indexed: 12/01/2024]
Affiliation(s)
- Renxi Li
- The George Washington University School of Medicine and Health Sciences, Washington, DC, USA.
| | - Anton Sidawy
- The George Washington University Hospital, Department of Surgery, Washington, DC, USA
| | - Bao-Ngoc Nguyen
- The George Washington University Hospital, Department of Surgery, Washington, DC, USA
| |
Collapse
|
|
4
|
Raji CG, Chandra SSV, Gracious N, Pillai YR, Sasidharan A. Advanced prognostic modeling with deep learning: assessing long-term outcomes in liver transplant recipients from deceased and living donors. J Transl Med 2025; 23:188. [PMID: 39956905 PMCID: PMC11830213 DOI: 10.1186/s12967-025-06183-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/29/2024] [Accepted: 01/29/2025] [Indexed: 02/18/2025] Open
Abstract
BACKGROUND Predicting long-term outcomes in liver transplantation remain a challenging endeavor. This research aims to harness the power of deep learning to develop an advanced prognostic model for assessing long-term outcomes, with a specific focus on distinguishing between deceased and living donor transplantation. METHODS A comprehensive dataset from UNOS encompassing clinical, demographic, and transplant-related variables of liver transplant recipients from deceased and living donors was utilized. The main dataset has been transformed into Deceased Donor-Recipient and Living Donor-Recipient dataset. After manual extraction, the dimensionality reduction was performed with Principal component analysis in both datasets and top ranked 23 attributes were collected. A Deeplearning4j Multilayer Perceptron classifier has been employed and long-term survival analysis has been conducted with the help of liver follow-up data. The performance evaluation is done separately in datasets and evaluated the survival probabilities of 23 years. RESULTS UNOS database comprises 410 attributes and 353,589 records from 1998 to 2023. The outcome from the deep learning model was compared with actual graft survival to ensure the accuracy. The model trained 23 attributes and obtained Sensitivity, Specificity and accuracy values were 99.9, 99.9 and 99.91% using R-Living donor dataset. The Sensitivity, Specificity and Accuracy value obtained using R-Deceased donor dataset were 99.7, 99.7 and 99.86%. The short term and long-term survival prediction after liver transplantation has been done successfully with Dl4jMLP classifier with appropriate selection of attributes irrespective of donor type. This study's finding suggesting that the distinction between deceased and living donor transplantation does not significantly affect survival prediction after liver transplantation is noteworthy. CONCLUSIONS The utility of the Deeplearning4j model in survival prediction after liver transplantation has been validated in this study. Based on the findings, deceased donor transplantation could be promoted over living donor transplantation.
Collapse
Affiliation(s)
- C G Raji
- Department of Computer Science, Assumption College Autonomous, Changanassery, Kerala, India
- Department of Computer Science, University of Kerala, Thiruvananthapuram, Kerala, India
| | - S S Vinod Chandra
- Department of Computer Science, University of Kerala, Thiruvananthapuram, Kerala, India
| | - Noble Gracious
- Kerala State Organ and Tissue Transplant Organization (KSOTTO), Government Medical College, Thiruvananthapuram, Kerala, India.
- Department of Nephrology, Govt TD Medical College, Alappuzha, Kerala, India.
| | - Yamuna R Pillai
- Department of Gastroenterology, Government Medical College, Thiruvananthapuram, Kerala, India
| | - Abhishek Sasidharan
- Department of Gastroenterology, Queen Elizabeth Hospital Kings Lynn NHS Trust, Norfolk, England
| |
Collapse
|
|
5
|
Olawade DB, Marinze S, Qureshi N, Weerasinghe K, Teke J. The impact of artificial intelligence and machine learning in organ retrieval and transplantation: A comprehensive review. Curr Res Transl Med 2025; 73:103493. [PMID: 39792149 DOI: 10.1016/j.retram.2025.103493] [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: 09/23/2024] [Revised: 12/11/2024] [Accepted: 01/05/2025] [Indexed: 01/12/2025]
Abstract
This narrative review examines the transformative role of Artificial Intelligence (AI) and Machine Learning (ML) in organ retrieval and transplantation. AI and ML technologies enhance donor-recipient matching by integrating and analyzing complex datasets encompassing clinical, genetic, and demographic information, leading to more precise organ allocation and improved transplant success rates. In surgical planning, AI-driven image analysis automates organ segmentation, identifies critical anatomical features, and predicts surgical outcomes, aiding pre-operative planning and reducing intraoperative risks. Predictive analytics further enable personalized treatment plans by forecasting organ rejection, infection risks, and patient recovery trajectories, thereby supporting early intervention strategies and long-term patient management. AI also optimizes operational efficiency within transplant centers by predicting organ demand, scheduling surgeries efficiently, and managing inventory to minimize wastage, thus streamlining workflows and enhancing resource allocation. Despite these advancements, several challenges hinder the widespread adoption of AI and ML in organ transplantation. These include data privacy concerns, regulatory compliance issues, interoperability across healthcare systems, and the need for rigorous clinical validation of AI models. Addressing these challenges is essential to ensuring the reliable, safe, and ethical use of AI in clinical settings. Future directions for AI and ML in transplantation medicine include integrating genomic data for precision immunosuppression, advancing robotic surgery for minimally invasive procedures, and developing AI-driven remote monitoring systems for continuous post-transplantation care. Collaborative efforts among clinicians, researchers, and policymakers are crucial to harnessing the full potential of AI and ML, ultimately transforming transplantation medicine and improving patient outcomes while enhancing healthcare delivery efficiency.
Collapse
Affiliation(s)
- David B Olawade
- Department of Allied and Public Health, School of Health, Sport and Bioscience, University of East London, London, United Kingdom; Department of Research and Innovation, Medway NHS Foundation Trust, Gillingham ME7 5NY, United Kingdom; Department of Public Health, York St John University, London, United Kingdom; School of Health and Care Management, Arden University, Arden House, Middlemarch Park, Coventry CV3 4FJ, United Kingdom.
| | - Sheila Marinze
- Department of Surgery, Medway NHS Foundation Trust, Gillingham ME7 5NY, United Kingdom
| | - Nabeel Qureshi
- Department of Surgery, Medway NHS Foundation Trust, Gillingham ME7 5NY, United Kingdom
| | - Kusal Weerasinghe
- Department of Research and Innovation, Medway NHS Foundation Trust, Gillingham ME7 5NY, United Kingdom
| | - Jennifer Teke
- Department of Research and Innovation, Medway NHS Foundation Trust, Gillingham ME7 5NY, United Kingdom; Faculty of Medicine, Health and Social Care, Canterbury Christ Church University, United Kingdom
| |
Collapse
|
|
6
|
Assis de Souza A, Stubbs AP, Hesselink DA, Baan CC, Boer K. Cherry on Top or Real Need? A Review of Explainable Machine Learning in Kidney Transplantation. Transplantation 2025; 109:123-132. [PMID: 38773859 DOI: 10.1097/tp.0000000000005063] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/24/2024]
Abstract
Research on solid organ transplantation has taken advantage of the substantial acquisition of medical data and the use of artificial intelligence (AI) and machine learning (ML) to answer diagnostic, prognostic, and therapeutic questions for many years. Nevertheless, despite the question of whether AI models add value to traditional modeling approaches, such as regression models, their "black box" nature is one of the factors that have hindered the translation from research to clinical practice. Several techniques that make such models understandable to humans were developed with the promise of increasing transparency in the support of medical decision-making. These techniques should help AI to close the gap between theory and practice by yielding trust in the model by doctors and patients, allowing model auditing, and facilitating compliance with emergent AI regulations. But is this also happening in the field of kidney transplantation? This review reports the use and explanation of "black box" models to diagnose and predict kidney allograft rejection, delayed graft function, graft failure, and other related outcomes after kidney transplantation. In particular, we emphasize the discussion on the need (or not) to explain ML models for biological discovery and clinical implementation in kidney transplantation. We also discuss promising future research paths for these computational tools.
Collapse
Affiliation(s)
- Alvaro Assis de Souza
- Department of Internal Medicine, Erasmus MC Transplant Institute, University Medical Center Rotterdam, Rotterdam, the Netherlands
| | - Andrew P Stubbs
- Department of Pathology and Clinical Bioinformatics, Erasmus MC Stubbs Group, University Medical Center Rotterdam, Rotterdam, the Netherlands
| | - Dennis A Hesselink
- Department of Internal Medicine, Erasmus MC Transplant Institute, University Medical Center Rotterdam, Rotterdam, the Netherlands
| | - Carla C Baan
- Department of Internal Medicine, Erasmus MC Transplant Institute, University Medical Center Rotterdam, Rotterdam, the Netherlands
| | - Karin Boer
- Department of Internal Medicine, Erasmus MC Transplant Institute, University Medical Center Rotterdam, Rotterdam, the Netherlands
| |
Collapse
|
|
7
|
Belčič Mikič T, Arnol M. The Use of Machine Learning in the Diagnosis of Kidney Allograft Rejection: Current Knowledge and Applications. Diagnostics (Basel) 2024; 14:2482. [PMID: 39594148 PMCID: PMC11592658 DOI: 10.3390/diagnostics14222482] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2024] [Revised: 10/31/2024] [Accepted: 11/04/2024] [Indexed: 11/28/2024] Open
Abstract
Kidney allograft rejection is one of the main limitations to long-term kidney transplant survival. The diagnostic gold standard for detecting rejection is a kidney biopsy, an invasive procedure that can often give imprecise results due to complex diagnostic criteria and high interobserver variability. In recent years, several additional diagnostic approaches to rejection have been investigated, some of them with the aid of machine learning (ML). In this review, we addressed studies that investigated the detection of kidney allograft rejection over the last decade using various ML algorithms. Various ML techniques were used in three main categories: (a) histopathologic assessment of kidney tissue with the aim to improve the diagnostic accuracy of a kidney biopsy, (b) assessment of gene expression in rejected kidney tissue or peripheral blood and the development of diagnostic classifiers based on these data, (c) radiologic assessment of kidney tissue using diffusion-weighted magnetic resonance imaging and the construction of a computer-aided diagnostic system. In histopathology, ML algorithms could serve as a support to the pathologist to avoid misclassifications and overcome interobserver variability. Diagnostic platforms based on biopsy-based transcripts serve as a supplement to a kidney biopsy, especially in cases where histopathologic diagnosis is inconclusive. ML models based on radiologic evaluation or gene signature in peripheral blood may be useful in cases where kidney biopsy is contraindicated in addition to other non-invasive biomarkers. The implementation of ML-based diagnostic methods is usually slow and undertaken with caution considering ethical and legal issues. In summary, the approach to the diagnosis of rejection should be individualized and based on all available diagnostic tools (including ML-based), leaving the responsibility for over- and under-treatment in the hands of the clinician.
Collapse
Affiliation(s)
- Tanja Belčič Mikič
- Department of Nephrology, University Medical Centre Ljubljana, Zaloška 7, 1000 Ljubljana, Slovenia;
- Faculty of Medicine, University of Ljubljana, Vrazov trg 2, 1000 Ljubljana, Slovenia
| | - Miha Arnol
- Department of Nephrology, University Medical Centre Ljubljana, Zaloška 7, 1000 Ljubljana, Slovenia;
- Faculty of Medicine, University of Ljubljana, Vrazov trg 2, 1000 Ljubljana, Slovenia
| |
Collapse
|
|
8
|
Li R, Sidawy A, Nguyen BN. Development and Validation of a 30-Day Point-Scoring Risk Calculator for Open Groin Vascular Surgery: The George Washington Groin Score. J Surg Res 2024; 303:295-304. [PMID: 39393117 DOI: 10.1016/j.jss.2024.09.008] [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: 01/17/2024] [Revised: 07/30/2024] [Accepted: 09/04/2024] [Indexed: 10/13/2024]
Abstract
BACKGROUND Open groin vascular surgeries are important in managing peripheral arterial diseases. Given its inherent risks and the diverse patient profiles, there is a need for risk assessment tools. This study aimed to develop a 30-d point-scoring risk calculator for patients undergoing open groin vascular surgeries. METHODS Patients underwent open groin vascular surgery, including aortobifemoral, axillofemoral, femorofemoral, iliofemoral, femoral-popliteal, and femoral-tibial bypass as well as thromboendarterectomy, were identified in American College of Surgeons National Surgical Quality Improvement Program database from 2005 to 2021. Patients were randomly sampled into experimental (2/3) and validation (1/3) groups. The George Washington (GW) groin score, a weighted point-scoring system, was developed for 30-d mortality from multivariable regression on preoperative risk variables by Sullivan's method. GW groin score was subjected to internal and external validation. Furthermore, the effectiveness of GW groin score was evaluated in 30-d major surgical complications. RESULTS A total of 129,424 patients were analyzed, with 86,715 allocated to experimental group and 42,709 to validation group. GW groin score is derived as follows: aortobifemoral bypass (2 points), axillofemoral bypass (1 point), age (>75 y, 2 points; 65-75 y, 1 point), disseminated cancer (2 points), emergent presentation (1 point), American Society of Anesthesiology score 4 or 5 (1 point), dialysis (1 point), and preoperative sepsis (1 point).GW groin score exhibited robust discrimination (c-statistic = 0.794, 95% CI = 0.786-0.803) and calibration (Brier score = 0.029). The transition from individual preoperative variables (c-statistic = 0.809, 95% CI = 0.801-0.818) to the point-scoring system was successful and external validation of the score was confirmed (c-statistic = 0.789, 95% CI = 0.777-0.801, Brier score = 0.030). Furthermore, GW groin score can effectively discriminate major surgical complications. CONCLUSIONS This study developed GW groin score, a concise and comprehensive 10-point risk calculator. This well-validated score demonstrates robust discriminative and predictive abilities for 30-d mortality and major surgical complications following open groin vascular surgeries. GW groin score can anticipate potential perioperative complications and guide treatment decisions.
Collapse
Affiliation(s)
- Renxi Li
- The George Washington University School of Medicine and Health Sciences, Washington, District of Columbia.
| | - Anton Sidawy
- Department of Surgery, The George Washington University Hospital, Washington, District of Columbia
| | - Bao-Ngoc Nguyen
- Department of Surgery, The George Washington University Hospital, Washington, District of Columbia
| |
Collapse
|
|
9
|
Kotsifa E, Mavroeidis VK. Present and Future Applications of Artificial Intelligence in Kidney Transplantation. J Clin Med 2024; 13:5939. [PMID: 39407999 PMCID: PMC11478249 DOI: 10.3390/jcm13195939] [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: 09/03/2024] [Revised: 09/27/2024] [Accepted: 10/02/2024] [Indexed: 10/15/2024] Open
Abstract
Artificial intelligence (AI) has a wide and increasing range of applications across various sectors. In medicine, AI has already made an impact in numerous fields, rapidly transforming healthcare delivery through its growing applications in diagnosis, treatment and overall patient care. Equally, AI is swiftly and essentially transforming the landscape of kidney transplantation (KT), offering innovative solutions for longstanding problems that have eluded resolution through traditional approaches outside its spectrum. The purpose of this review is to explore the present and future applications of artificial intelligence in KT, with a focus on pre-transplant evaluation, surgical assistance, outcomes and post-transplant care. We discuss its great potential and the inevitable limitations that accompany these technologies. We conclude that by fostering collaboration between AI technologies and medical practitioners, we can pave the way for a future where advanced, personalised care becomes the standard in KT and beyond.
Collapse
Affiliation(s)
- Evgenia Kotsifa
- Second Propaedeutic Department of Surgery, National and Kapodistrian University of Athens, General Hospital of Athens “Laiko”, Agiou Thoma 17, 157 72 Athens, Greece
| | - Vasileios K. Mavroeidis
- Department of Transplant Surgery, North Bristol NHS Trust, Southmead Hospital, Bristol BS10 5NB, UK
| |
Collapse
|
|
10
|
Li R. Development and validation of a 30-day point-scoring risk calculator for small bowel obstruction surgery. Updates Surg 2024; 76:2293-2302. [PMID: 38728005 DOI: 10.1007/s13304-024-01875-7] [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: 02/29/2024] [Accepted: 05/05/2024] [Indexed: 11/07/2024]
Abstract
Small bowel obstruction (SBO) is one of the most frequent causes of general emergency surgery. The 30-day mortality rate post-surgery ranges widely from 2 to 30%, contingent upon the patient population, which renders risk assessment tools helpful. this study aimed to develop a 30-day point-scoring risk calculator designed for patients undergoing SBO surgery. Patients who underwent SBO surgery were identified in the ACS-NSQIP database from 2005 to 2021. Patients were randomly sampled into an experimental (2/3) and a validation (1/3) group. A weighted point scoring system was developed for the risk of 30-day mortality, utilizing multivariable regression on preoperative risk variables based on Sullivan's method. The risk scores underwent both internal and external validation. Furthermore, the efficacy of the risk score was evaluated in 30-day major surgical complications. A total of 93,517 patients were identified, with 63,521 and 29,996 assigned to the experimental and validation groups, respectively. The risk calculator is structured to assign points based on age (> 85 years, 4 points; 75-85 years, 3 points; 65-75 years, 2 points; 55-65 years, 1 point), disseminated cancer (2 points), American Society of Anesthesiology (ASA) score of 4 or 5 (1 point), preoperative sepsis (1 point), hypoalbuminemia (1 point), and fully dependent functional status (1 point). The risk calculator showed strong discrimination (c-statistic = 0.825, 95% CI 0.818-0.831) and good calibration (Brier score = 0.043) in the experimental group. The point scoring system was successfully translated from individual preoperative variables (c-statistic = 0.840, 95% CI 0.834-0.847) and was externally validated in ACS-NSQIP (c-statistic = 0.827, 95% = CI 0.834-0.847, Brier score = 0.043). The SBO risk score can effectively discriminate major surgical complications including major adverse cardiovascular events (c-statistic = 0.734), cardiac complications (c-statistic = 0.732), stroke (c-statistic = 0.725), pulmonary complications (c-statistic = 0.727), renal complications (c-statistic = 0.692), bleeding (c-statistic 0.674), sepsis (c-statistic = 0.670), with high predictive accuracy (all Brier scores < 0.1). This study developed and validated a concise yet robust 10-point risk scoring system for patients undergoing SBO surgery. It can be informative to determine treatment plans and to prepare for potential perioperative complications in patients undergoing SBO surgery.
Collapse
Affiliation(s)
- Renxi Li
- The George Washington University School of Medicine and Health Sciences, 2300 I St NW, Washington, DC, 20052, USA.
- Department of Surgery, The George Washington University Hospital, Washington, DC, USA.
- Department of Surgery, University of Minnesota Medical School, Minneapolis, MN, USA.
| |
Collapse
|
|
11
|
Li R, Sidawy A, Nguyen BN. Locoregional Anesthesia Has Lower Risks of Cardiac Complications Than General Anesthesia After Prolonged Endovascular Repair of Abdominal Aortic Aneurysms. J Cardiothorac Vasc Anesth 2024; 38:1506-1513. [PMID: 38631930 DOI: 10.1053/j.jvca.2024.03.025] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/22/2024] [Revised: 02/27/2024] [Accepted: 03/18/2024] [Indexed: 04/19/2024]
Abstract
OBJECTIVES Although general anesthesia is the primary anesthesia in endovascular aneurysm repair (EVAR), some studies suggest locoregional anesthesia could be a feasible alternative for eligible patients. However, most evidence was from retrospective studies and was subjected to an inherent selection bias that general anesthesia is often chosen for more complex and prolonged cases. To mitigate this selection bias, this study aimed to compare 30-day outcomes of prolonged, nonemergent, intact, infrarenal EVAR in patients undergoing locoregional or general anesthesia. In addition, risk factors associated with prolonged operative time in EVAR were identified. DESIGN Retrospective large-scale national registry study. SETTING American College of Surgeons National Surgical Quality Improvement Program targeted database from 2012 to 2022. PARTICIPANTS A total of 4,075 out of 16,438 patients (24.79%) had prolonged EVAR. Among patients with prolonged EVAR, 324 patients (7.95%) were under locoregional anesthesia. There were 3,751 patients (92.05%) under general anesthesia, and 955 of them were matched to the locoregional anesthesia cohort. INTERVENTIONS Patients undergoing infrarenal EVAR were included. Exclusion criteria included age <18 years, emergency cases, ruptured abdominal aortic aneurysm, and acute intraoperative conversion to open. Only cases with prolonged operative times (>157 minutes) were selected. A 1:3 propensity-score matching was used to address demographics, baseline characteristics, aneurysm diameter, distant aneurysm extent, and concomitant procedures between patients under locoregional and general anesthesia. Thirty-day postoperative outcomes were assessed. Moreover, factors associated with prolonged EVAR were identified by multivariate logistic regression. MEASUREMENTS AND MAIN RESULTS Except for general anesthesia contraindications, patients undergoing locoregional or general anesthesia exhibited largely similar preoperative characteristics. After propensity-score matching, patients under locoregional and general anesthesia had a lower risk of myocardial infarction (0.93% v 2.83%, p = 0.04), but comparable 30-day mortality (3.72% v 2.72%, p = 0.35) and other complications. Specific concomitant procedures, aneurysm anatomy, and comorbidities associated with prolonged EVAR were identified. CONCLUSIONS Locoregional anesthesia can be a safe and effective alternative to general anesthesia, particularly in EVAR cases with anticipated complexity and prolonged operative times, as it offers the potential benefit of reduced cardiac complications. Risk factors associated with prolonged EVAR can aid in preoperative risk stratification and inform the decision-making process regarding anesthesia choice.
Collapse
Affiliation(s)
- Renxi Li
- George Washington University School of Medicine and Health Sciences, Washington, DC.
| | - Anton Sidawy
- George Washington University Hospital, Department of Surgery, Washington, DC
| | - Bao-Ngoc Nguyen
- George Washington University Hospital, Department of Surgery, Washington, DC
| |
Collapse
|
|
12
|
Li R, Sidawy A, Nguyen BN. Development of a comorbidity index for patients undergoing abdominal aortic aneurysm repair. J Vasc Surg 2024; 79:547-554. [PMID: 37890642 DOI: 10.1016/j.jvs.2023.10.039] [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: 08/18/2023] [Revised: 10/18/2023] [Accepted: 10/19/2023] [Indexed: 10/29/2023]
Abstract
BACKGROUND Endovascular aneurysm repair (EVAR) and open surgical repair (OSR) are two modalities to treat patients with abdominal aortic aneurysm (AAA). Alternative to individual comorbidity adjustment, a summary comorbidity index is a weighted composite score of all comorbidities that can be used as standard metric to control for comorbidity burden in clinical studies. This study aimed to develop summary comorbidity indices for patients who underwent AAA repair. METHODS Patients who went under EVAR or OSR were identified in National Inpatient Sample (NIS) between the last quarter of 2015 to 2020. In each group, patients were randomly sampled into experimental (2/3) and validation (1/3) groups. The weights of Elixhauser comorbidities were determined from a multivariable logistic regression and single comorbidity indices were developed for EVAR and OAR groups, respectively. RESULTS There were 34,668 patients underwent EVAR (2.19% mortality) and 4792 underwent OSR (10.98% mortality). Both comorbidity indices had moderate discriminative power (EVAR c-statistic, 0.641; 95% confidence interval [CI], 0.616-0.665; OSR c-statistic, 0.600; 95% CI, 0.563-0.630) and good calibration (EVAR Brier score, 0.021; OSR Brier score, 0.096). The indices had significantly better discriminative power (DeLong P <.001) than the Elixhauser Comorbidity Index (ECI) (EVAR c-statistic, 0.572; 95% CI, 0.546-0.597; OSR c-statistic, 0.502; 95% CI, 0.472-0.533). For internal validation, both indices had similar performance compared with individual comorbidity adjustment (EVAR DeLong P = .650; OSR DeLong P = .431). These indices demonstrated good external validation, exhibiting comparable performance to their respective validation groups (EVAR DeLong P = .891; OSR DeLong P = .757). CONCLUSIONS ECI, the comorbidity index formulated for the general population, exhibited suboptimal performance in patients who underwent AAA repair. In response, we developed summary comorbidity indices for both EVAR and OSR for AAA repair, which were internally and externally validated. The EVAR and OSR comorbidity indices outperformed the ECI in discriminating in-hospital mortality rates. They can standardize comorbidity measurement for clinical studies in AAA repair, especially for studies with small samples such as single-institute data sources to facilitate replication and comparison of results across studies.
Collapse
Affiliation(s)
- Renxi Li
- George Washington University School of Medicine and Health Sciences, Washington, DC.
| | - Anton Sidawy
- Department of Surgery, George Washington University Hospital, Washington, DC
| | - Bao-Ngoc Nguyen
- Department of Surgery, George Washington University Hospital, Washington, DC
| |
Collapse
|
|
13
|
He S, Li X, Zhao Z, Li B, Tan X, Guo H, Chen Y, Lu X. A novel method to predict white blood cells after kidney transplantation based on machine learning. Digit Health 2024; 10:20552076241288107. [PMID: 39484657 PMCID: PMC11526406 DOI: 10.1177/20552076241288107] [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: 01/14/2024] [Accepted: 09/13/2024] [Indexed: 11/03/2024] Open
Abstract
Background Abnormal white blood cell count after kidney transplantation is an important adverse clinical outcome. The abnormal white blood cell count in patients after surgery may be caused by the use of immunosuppressive agents and other factors. A lower white blood cell count than normal will greatly increase the probability of adverse outcomes such as infection and reduce the success rate of surgery. Objective To establish a machine learning prediction model of leukocyte drop to abnormal level after kidney transplantation, and provide reference for clinical treatment. Methods A total of 546 kidney transplant patients were selected as the study subjects. The time correlation feature of the ratio of the duration time of each variable to the total time in different intervals was innovatively introduced. Least absolute shrinkage and selection operator algorithm was used for correlation analysis of 85 candidate variables, and the top 20 variables were retained in the end. Eight machine learning algorithms, including Logistic-L1, Logistic-L2, support vector machine, decision tree, random forest, multilayer perceptron, extreme gradient boosting and light gradient boosting machine, were used for the five-fold cross-validation on all data sets, and the algorithm with the best performance was selected as the final prediction algorithm based on the average area under the curve. Results As the final prediction model, the accuracy, sensitivity, specificity and area under the curve values of the multilayer perceptron model in test set were 71.34%, 61.18%, 82.28% and 77.30%, respectively. The most important factors affecting leukopenia after surgery were the proportion of time of lymphocyte less than normal, blood group AB, gender, and platelet CV. Conclusions The multilayer perceptron model explored in this study shows significant potential in predicting abnormal white blood cell counts after kidney transplantation. This model can help stratify risk following transplantation, subject to external and/or prospective validation.
Collapse
Affiliation(s)
- Songping He
- Digital Manufacturing Equipment National Engineering Research Center, Huazhong University of Science and Technology, Wuhan, China
| | - Xiangxi Li
- National NC System Engineering Research Center, Huazhong University of Science and Technology, Wuhan, China
| | - Zunyuan Zhao
- National NC System Engineering Research Center, Huazhong University of Science and Technology, Wuhan, China
| | - Bin Li
- Digital Manufacturing Equipment National Engineering Research Center, Huazhong University of Science and Technology, Wuhan, China
| | - Xin Tan
- Wuhan Intelligent Equipment Industrial Institute Co., Ltd, Wuhan, China
| | - Hui Guo
- Institute of Organ Transplantation, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology; Key Laboratory of Organ Transplantation, Ministry of Education; NHC Key Laboratory of Organ Transplantation; Key Laboratory of Organ Transplantation, Chinese Academy of Medical Sciences, Wuhan, China
| | - Yanyan Chen
- Big Data and Artificial Intelligence Office, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Xia Lu
- Institute of Organ Transplantation, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology; Key Laboratory of Organ Transplantation, Ministry of Education; NHC Key Laboratory of Organ Transplantation; Key Laboratory of Organ Transplantation, Chinese Academy of Medical Sciences, Wuhan, China
| |
Collapse
|
|
14
|
Li R, Huddleston S. Development of Comorbidity Index for in-hospital mortality for patients who underwent coronary artery revascularization. THE JOURNAL OF CARDIOVASCULAR SURGERY 2023; 64:678-685. [PMID: 37987738 DOI: 10.23736/s0021-9509.23.12833-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/22/2023]
Abstract
BACKGROUND For myocardial revascularization, coronary artery bypass grafting (CAGB) and percutaneous coronary intervention (PCI) are two common modalities but with high in-hospital mortality. A Comorbidity Index is useful to predict mortality or can be used with other covariates to develop point-scoring systems. This study aimed to develop specific comorbidity indices for patients who underwent coronary artery revascularization. METHODS Patients who underwent CABG or PCI were identified in the National Inpatient Sample database between Q4 2015-2020. Patients of age <40 were excluded for congenital heart defects. Patients were randomly sampled into experimental (70%) and validation (30%) groups. Thirty-eight Elixhauser comorbidities were identified and included in multivariable regression to discriminate in-hospital mortality. Weight for each comorbidity was assigned and single indices, Li CABG Mortality Index (LCMI) and Li PCI Mortality Index (LPMI), were developed. RESULTS Mortality discrimination by LCMI approached adequacy (c-statistic=0.691, 95% CI=0.682-0.701) and was comparable to multivariable regression with comorbidities (c-statistic=0.685, 95% CI=0.675-0.694). LCMI discrimination performed significantly better than Elixhauser Comorbidity Index (ECI) (c-statistic=0.621, 95% CI=0.611-0.631) and can be further improved by adjusting age (c-statistic=0.721, 95% CI=0.712-0.730). All models were well-calibrated (Brier score=0.021-0.022). LPMI moderately discriminated in-hospital mortality (c-statistic=0.666, 95% CI=0.660-0.672) and performed significantly better than ECI (c-statistic=0.610, 95% CI=0.604-0.616). LPMI performed better than the all-comorbidity multivariable regression (c-statistic=0.658, 95% CI=0.652-0.663). After age adjustment, LPMI discrimination was significantly increased and was approaching adequacy (c-statistic=0.695, 95% CI=0.690-0.701). All models were well-calibrated (Brier score=0.025-0.026). CONCLUSIONS LCMI and LPMI effectively discriminated and predicted in-hospital mortality. These indices were validated and performed superior to ECI. These indices can standardize comorbidity measurement as alternatives to ECI to help replicate and compare results across studies.
Collapse
Affiliation(s)
- Renxi Li
- George Washington University School of Medicine and Health Sciences, Washington, DC, USA -
- Division of Cardiovascular and Thoracic Surgery, Department of Surgery, University of Minnesota Medical School, Minneapolis, MN, USA -
| | - Stephen Huddleston
- Division of Cardiovascular and Thoracic Surgery, Department of Surgery, University of Minnesota Medical School, Minneapolis, MN, USA
| |
Collapse
|
|
15
|
Wies C, Miltenberger R, Grieser G, Jahn-Eimermacher A. Exploring the variable importance in random forests under correlations: a general concept applied to donor organ quality in post-transplant survival. BMC Med Res Methodol 2023; 23:209. [PMID: 37726680 PMCID: PMC10507897 DOI: 10.1186/s12874-023-02023-2] [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: 03/01/2023] [Accepted: 08/23/2023] [Indexed: 09/21/2023] Open
Abstract
Random Forests are a powerful and frequently applied Machine Learning tool. The permutation variable importance (VIMP) has been proposed to improve the explainability of such a pure prediction model. It describes the expected increase in prediction error after randomly permuting a variable and disturbing its association with the outcome. However, VIMPs measure a variable's marginal influence only, that can make its interpretation difficult or even misleading. In the present work we address the general need for improving the explainability of prediction models by exploring VIMPs in the presence of correlated variables. In particular, we propose to use a variable's residual information for investigating if its permutation importance partially or totally originates from correlated predictors. Hypotheses tests are derived by a resampling algorithm that can further support results by providing test decisions and p-values. In simulation studies we show that the proposed test controls type I error rates. When applying the methods to a Random Forest analysis of post-transplant survival after kidney transplantation, the importance of kidney donor quality for predicting post-transplant survival is shown to be high. However, the transplant allocation policy introduces correlations with other well-known predictors, which raises the concern that the importance of kidney donor quality may simply originate from these predictors. By using the proposed method, this concern is addressed and it is demonstrated that kidney donor quality plays an important role in post-transplant survival, regardless of correlations with other predictors.
Collapse
Affiliation(s)
- Christoph Wies
- Department of Mathematics and Natural Sciences, Darmstadt University of Applied Sciences, Schöfferstraße 3, Darmstadt, 64295, Germany
- Digital Biomarkers for Oncology, German Cancer Research Center (DKFZ), Im Neuenheimer Feld 223, Heidelberg, 69120, Germany
- Medical Facility, University Heidelberg, Im Neuenheimer Feld 672, Heidelberg, 69120, Germany
| | - Robert Miltenberger
- Department of Mathematics and Natural Sciences, Darmstadt University of Applied Sciences, Schöfferstraße 3, Darmstadt, 64295, Germany
| | - Gunter Grieser
- Department of Computer Science, Darmstadt University of Applied Sciences, Schöfferstraße 3, Darmstadt, 64295, Germany
| | - Antje Jahn-Eimermacher
- Department of Mathematics and Natural Sciences, Darmstadt University of Applied Sciences, Schöfferstraße 3, Darmstadt, 64295, Germany.
| |
Collapse
|
|
16
|
Abstract
PURPOSE OF REVIEW Optimizing deceased donor organ utilization is gaining recognition as a topical and important issue, both in the United Kingdom (UK) and globally. This review discusses pertinent issues in the field of organ utilization, with specific reference to UK data and recent developments within the UK. RECENT FINDINGS A multifaceted approach is likely required in order to improve organ utilization. Having a solid evidence-base upon which transplant clinicians and patients on national waiting lists can base decisions regarding organ utilization is imperative in order to bridge gaps in knowledge regarding the optimal use of each donated organ. A better understanding of the risks and benefits of the uses of higher risk organs, along with innovations such as novel machine perfusion technologies, can help clinician decision-making and may ultimately reduce the unnecessary discard of precious deceased donor organs. SUMMARY The issues facing the UK with regards to organ utilization are likely to be similar to those in many other developed countries. Discussions around these issues within organ donation and transplantation communities may help facilitate shared learning, lead to improvements in the usage of scarce deceased donor organs, and enable better outcomes for patients waiting for transplants.
Collapse
Affiliation(s)
- Maria Ibrahim
- Department of Nephrology and Transplantation, Manchester Royal Infirmary, Manchester University NHS Foundation Trust, Manchester
| | - Chris J Callaghan
- Department of Nephrology and Transplantation, Guy's Hospital, Guy's and St Thomas' NHS Foundation Trust, London
- NHS Blood and Transplant, Bristol, UK
| |
Collapse
|
|
17
|
Ibrahim M, Mehew J, Martin K, Forsythe J, Johnson RJ, Callaghan C. Outcomes of Declined Deceased Donor Kidney Offers That Are Subsequently Implanted: A UK Registry Study. Transplantation 2023; 107:1348-1358. [PMID: 36706063 DOI: 10.1097/tp.0000000000004467] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/28/2023]
Abstract
BACKGROUND Deceased donor kidneys are often declined for ≥1 patients but then implanted into another. Studies are needed to guide transplant clinicians and patients, especially given the increasing age and comorbidity of donors. This study compares outcomes of recipients of transplanted kidneys that were initially declined with outcomes of patients who remained on the waiting list. METHODS This UK Transplant Registry study examined named-patient, adult donation after brain death donor single kidney-only offers that were declined for donor- or organ-related reasons (DORRs), in which the kidney was subsequently transplanted from January 1, 2010, to December 31, 2018. Outcomes included graft function and survival of kidneys transplanted following DORR decline, survival and transplant status of patients who had a kidney declined, and intercenter decline rates. RESULTS A total of 4722 kidneys declined for DORRs, which eventually resulted in single kidney-only transplants, were examined. One year after the offer decline, 35% of patients for whom the organ was declined remained on the list, 55% received a deceased donor transplant at a median of 174 d after the initial offer decline, and 4% had been removed or died. For patients transplanted following offer decline, there was no significant difference in 5-y graft survival when comparing the outcomes to those recipients who received the declined kidney. There was significant variation in DORR decline rates between UK transplant units (17%-54%). CONCLUSIONS This study shows reasonable outcomes of kidneys previously declined for DORRs and supports the utilization of those considered to be of higher risk for carefully selected recipients.
Collapse
Affiliation(s)
- Maria Ibrahim
- Department of Nephrology and Transplantation, Guy's and St Thomas' NHS Foundation Trust, London, United Kingdom
- NHS Blood and Transplant, Stoke Gifford, Bristol, United Kingdom
| | - Jennifer Mehew
- NHS Blood and Transplant, Stoke Gifford, Bristol, United Kingdom
| | - Kate Martin
- NHS Blood and Transplant, Stoke Gifford, Bristol, United Kingdom
| | - John Forsythe
- NHS Blood and Transplant, Stoke Gifford, Bristol, United Kingdom
| | - Rachel J Johnson
- NHS Blood and Transplant, Stoke Gifford, Bristol, United Kingdom
| | - Chris Callaghan
- Department of Nephrology and Transplantation, Guy's and St Thomas' NHS Foundation Trust, London, United Kingdom
| |
Collapse
|
|
18
|
Quinino RM, Agena F, Modelli de Andrade LG, Furtado M, Chiavegatto Filho ADP, David-Neto E. A Machine Learning Prediction Model for Immediate Graft Function After Deceased Donor Kidney Transplantation. Transplantation 2023; 107:1380-1389. [PMID: 36872507 DOI: 10.1097/tp.0000000000004510] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/07/2023]
Abstract
BACKGROUND After kidney transplantation (KTx), the graft can evolve from excellent immediate graft function (IGF) to total absence of function requiring dialysis. Recipients with IGF do not seem to benefit from using machine perfusion, an expensive procedure, in the long term when compared with cold storage. This study proposes to develop a prediction model for IGF in KTx deceased donor patients using machine learning algorithms. METHODS Unsensitized recipients who received their first KTx deceased donor between January 1, 2010, and December 31, 2019, were classified according to the conduct of renal function after transplantation. Variables related to the donor, recipient, kidney preservation, and immunology were used. The patients were randomly divided into 2 groups: 70% were assigned to the training and 30% to the test group. Popular machine learning algorithms were used: eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine, Gradient Boosting classifier, Logistic Regression, CatBoost classifier, AdaBoost classifier, and Random Forest classifier. Comparative performance analysis on the test dataset was performed using the results of the AUC values, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score. RESULTS Of the 859 patients, 21.7% (n = 186) had IGF. The best predictive performance resulted from the eXtreme Gradient Boosting model (AUC, 0.78; 95% CI, 0.71-0.84; sensitivity, 0.64; specificity, 0.78). Five variables with the highest predictive value were identified. CONCLUSIONS Our results indicated the possibility of creating a model for the prediction of IGF, enhancing the selection of patients who would benefit from an expensive treatment, as in the case of machine perfusion preservation.
Collapse
Affiliation(s)
- Raquel M Quinino
- Renal Transplant Service, Hospital das Clinicas, University of São Paulo School of Medicine, São Paulo, Brazil
| | - Fabiana Agena
- Renal Transplant Service, Hospital das Clinicas, University of São Paulo School of Medicine, São Paulo, Brazil
| | | | - Mariane Furtado
- Department of Epidemiology, School of Public Health, University of São Paulo, São Paulo, Brazil
| | | | - Elias David-Neto
- Renal Transplant Service, Hospital das Clinicas, University of São Paulo School of Medicine, São Paulo, Brazil
| |
Collapse
|
|
19
|
Badrouchi S, Bacha MM, Hedri H, Ben Abdallah T, Abderrahim E. Toward generalizing the use of artificial intelligence in nephrology and kidney transplantation. J Nephrol 2022; 36:1087-1100. [PMID: 36547773 PMCID: PMC9773693 DOI: 10.1007/s40620-022-01529-0] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/28/2022] [Accepted: 11/20/2022] [Indexed: 12/24/2022]
Abstract
With its robust ability to integrate and learn from large sets of clinical data, artificial intelligence (AI) can now play a role in diagnosis, clinical decision making, and personalized medicine. It is probably the natural progression of traditional statistical techniques. Currently, there are many unmet needs in nephrology and, more particularly, in the kidney transplantation (KT) field. The complexity and increase in the amount of data, and the multitude of nephrology registries worldwide have enabled the explosive use of AI within the field. Nephrologists in many countries are already at the center of experiments and advances in this cutting-edge technology and our aim is to generalize the use of AI among nephrologists worldwide. In this paper, we provide an overview of AI from a medical perspective. We cover the core concepts of AI relevant to the practicing nephrologist in a consistent and simple way to help them get started, and we discuss the technical challenges. Finally, we focus on the KT field: the unmet needs and the potential role that AI can play to fill these gaps, then we summarize the published KT-related studies, including predictive factors used in each study, which will allow researchers to quickly focus on the most relevant issues.
Collapse
Affiliation(s)
- Samarra Badrouchi
- Department of Internal Medicine A, Charles Nicolle Hospital, Tunis, Tunisia ,Faculty of Medicine of Tunis, University of Tunis El Manar, Tunis, Tunisia
| | - Mohamed Mongi Bacha
- Department of Internal Medicine A, Charles Nicolle Hospital, Tunis, Tunisia ,Faculty of Medicine of Tunis, University of Tunis El Manar, Tunis, Tunisia ,Laboratory of Kidney Transplantation Immunology and Immunopathology (LR03SP01), Charles Nicolle Hospital, Tunis, Tunisia
| | - Hafedh Hedri
- Department of Internal Medicine A, Charles Nicolle Hospital, Tunis, Tunisia ,Faculty of Medicine of Tunis, University of Tunis El Manar, Tunis, Tunisia
| | - Taieb Ben Abdallah
- Department of Internal Medicine A, Charles Nicolle Hospital, Tunis, Tunisia ,Faculty of Medicine of Tunis, University of Tunis El Manar, Tunis, Tunisia ,Laboratory of Kidney Transplantation Immunology and Immunopathology (LR03SP01), Charles Nicolle Hospital, Tunis, Tunisia
| | - Ezzedine Abderrahim
- Department of Internal Medicine A, Charles Nicolle Hospital, Tunis, Tunisia ,Faculty of Medicine of Tunis, University of Tunis El Manar, Tunis, Tunisia
| |
Collapse
|
|
20
|
Jimenez AE, Porras JL, Azad TD, Shah PP, Jackson CM, Gallia G, Bettegowda C, Weingart J, Mukherjee D. Machine Learning Models for Predicting Postoperative Outcomes following Skull Base Meningioma Surgery. J Neurol Surg B Skull Base 2022; 83:635-645. [PMID: 36393884 PMCID: PMC9653296 DOI: 10.1055/a-1885-1447] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/31/2021] [Accepted: 06/20/2022] [Indexed: 10/17/2022] Open
Abstract
Objective While predictive analytic techniques have been used to analyze meningioma postoperative outcomes, to our knowledge, there have been no studies that have investigated the utility of machine learning (ML) models in prognosticating outcomes among skull base meningioma patients. The present study aimed to develop models for predicting postoperative outcomes among skull base meningioma patients, specifically prolonged hospital length of stay (LOS), nonroutine discharge disposition, and high hospital charges. We also validated the predictive performance of our models on out-of-sample testing data. Methods Patients who underwent skull base meningioma surgery between 2016 and 2019 at an academic institution were included in our study. Prolonged hospital LOS and high hospital charges were defined as >4 days and >$47,887, respectively. Elastic net logistic regression algorithms were trained to predict postoperative outcomes using 70% of available data, and their predictive performance was evaluated on the remaining 30%. Results A total of 265 patients were included in our final analysis. Our cohort was majority female (77.7%) and Caucasian (63.4%). Elastic net logistic regression algorithms predicting prolonged LOS, nonroutine discharge, and high hospital charges achieved areas under the receiver operating characteristic curve of 0.798, 0.752, and 0.592, respectively. Further, all models were adequately calibrated as determined by the Spiegelhalter Z -test ( p >0.05). Conclusion Our study developed models predicting prolonged hospital LOS, nonroutine discharge disposition, and high hospital charges among skull base meningioma patients. Our models highlight the utility of ML as a tool to aid skull base surgeons in providing high-value health care and optimizing clinical workflows.
Collapse
Affiliation(s)
- Adrian E. Jimenez
- Department of Neurosurgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, United States
| | - Jose L. Porras
- Department of Neurosurgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, United States
| | - Tej D. Azad
- Department of Neurosurgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, United States
| | - Pavan P. Shah
- Department of Neurosurgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, United States
| | - Christopher M. Jackson
- Department of Neurosurgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, United States
| | - Gary Gallia
- Department of Neurosurgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, United States
| | - Chetan Bettegowda
- Department of Neurosurgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, United States
| | - Jon Weingart
- Department of Neurosurgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, United States
| | - Debraj Mukherjee
- Department of Neurosurgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, United States
| |
Collapse
|
|
21
|
Predicting a Positive Antibody Response After 2 SARS-CoV-2 mRNA Vaccines in Transplant Recipients: A Machine Learning Approach With External Validation. Transplantation 2022; 106:e452-e460. [PMID: 35859275 PMCID: PMC9521390 DOI: 10.1097/tp.0000000000004259] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
Abstract
BACKGROUND Solid organ transplant recipients (SOTRs) are less likely to mount an antibody response to SARS-CoV-2 mRNA vaccines. Understanding risk factors for impaired vaccine response can guide strategies for antibody testing and additional vaccine dose recommendations. METHODS Using a nationwide observational cohort of 1031 SOTRs, we created a machine learning model to explore, identify, rank, and quantify the association of 19 clinical factors with antibody responses to 2 doses of SARS-CoV-2 mRNA vaccines. External validation of the model was performed using a cohort of 512 SOTRs at Houston Methodist Hospital. RESULTS Mycophenolate mofetil use, a shorter time since transplant, and older age were the strongest predictors of a negative antibody response, collectively contributing to 76% of the model's prediction performance. Other clinical factors, including transplanted organ, vaccine type (mRNA-1273 versus BNT162b2), sex, race, and other immunosuppressants, showed comparatively weaker associations with an antibody response. This model showed moderate prediction performance, with an area under the receiver operating characteristic curve of 0.79 in our cohort and 0.67 in the external validation cohort. An online calculator based on our prediction model is available at http://transplantmodels.com/covidvaccine/ . CONCLUSIONS Our machine learning model helps understand which transplant patients need closer follow-up and additional doses of vaccine to achieve protective immunity. The online calculator based on this model can be incorporated into transplant providers' practice to facilitate patient-centric, precision risk stratification and inform vaccination strategies among SOTRs.
Collapse
|
|
22
|
Bae S, Samuels JA, Flynn JT, Mitsnefes MM, Furth SL, Warady BA, Ng DK. Machine Learning-Based Prediction of Masked Hypertension Among Children With Chronic Kidney Disease. Hypertension 2022; 79:2105-2113. [PMID: 35862083 PMCID: PMC9378451 DOI: 10.1161/hypertensionaha.121.18794] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
BACKGROUND Ambulatory blood pressure monitoring (ABPM) is routinely performed in children with chronic kidney disease to identify masked hypertension, a risk factor for accelerated chronic kidney disease progression. However, ABPM is burdensome, and developing an accurate prediction of masked hypertension may allow using ABPM selectively rather than routinely. METHODS To create a prediction model for masked hypertension using clinic blood pressure (BP) and other clinical characteristics, we analyzed 809 ABPM studies with nonhypertensive clinic BP among the participants of the Chronic Kidney Disease in Children study. RESULTS Masked hypertension was identified in 170 (21.0%) observations. We created prediction models for masked hypertension via gradient boosting, random forests, and logistic regression using 109 candidate predictors and evaluated its performance using bootstrap validation. The models showed C statistics from 0.660 (95% CI, 0.595-0.707) to 0.732 (95% CI, 0.695-0.786) and Brier scores from 0.148 (95% CI, 0.141-0.154) to 0.167 (95% CI, 0.152-0.183). Using the possible thresholds identified from this model, we stratified the dataset by clinic systolic/diastolic BP percentiles. The prevalence of masked hypertension was the lowest (4.8%) when clinic systolic/diastolic BP were both <20th percentile, and relatively low (9.0%) with clinic systolic BP<20th and diastolic BP<80th percentiles. Above these thresholds, the prevalence was higher with no discernable pattern. CONCLUSIONS ABPM could be used selectively in those with low clinic BP, for example, systolic BP<20th and diastolic BP<80th percentiles, although careful assessment is warranted as masked hypertension was not completely absent even in this subgroup. Above these clinic BP levels, routine ABPM remains recommended.
Collapse
Affiliation(s)
- Sunjae Bae
- Department of Surgery, Johns Hopkins University, Baltimore, Maryland
| | | | - Joseph T. Flynn
- Department of Pediatrics, University of Washington; Division of Nephrology, Seattle Children’s Hospital; Seattle, Washington
| | - Mark M. Mitsnefes
- Division of Nephrology, Department of Pediatrics, Cincinnati Children’s Hospital Medical Center, Cincinnati, Ohio
| | - Susan L. Furth
- Division of Nephrology, Department of Pediatrics, Children’s Hospital of Philadelphia, Philadelphia, Pennsylvania
- Department of Pediatrics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania
| | - Bradley A. Warady
- Division of Nephrology, Department of Pediatrics, Children’s Mercy Kansas City, Kansas City, Missouri
| | - Derek K. Ng
- Department of Epidemiology, Johns Hopkins Bloomberg School of Public Health, Baltimore, Maryland
| |
Collapse
|
|
23
|
Sharif A. Deceased Donor Characteristics and Kidney Transplant Outcomes. Transpl Int 2022; 35:10482. [PMID: 36090778 PMCID: PMC9452640 DOI: 10.3389/ti.2022.10482] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2022] [Accepted: 07/25/2022] [Indexed: 11/25/2022]
Abstract
Kidney transplantation is the therapy of choice for people living with kidney failure who are suitable for surgery. However, the disparity between supply versus demand for organs means many either die or are removed from the waiting-list before receiving a kidney allograft. Reducing unnecessary discard of deceased donor kidneys is important to maximize utilization of a scarce and valuable resource but requires nuanced decision-making. Accepting kidneys from deceased donors with heterogenous characteristics for waitlisted kidney transplant candidates, often in the context of time-pressured decision-making, requires an understanding of the association between donor characteristics and kidney transplant outcomes. Deceased donor clinical factors can impact patient and/or kidney allograft survival but risk-versus-benefit deliberation must be balanced against the morbidity and mortality associated with remaining on the waiting-list. In this article, the association between deceased kidney donor characteristics and post kidney transplant outcomes for the recipient are reviewed. While translating this evidence to individual kidney transplant candidates is a challenge, emerging strategies to improve this process will be discussed. Fundamentally, tools and guidelines to inform decision-making when considering deceased donor kidney offers will be valuable to both professionals and patients.
Collapse
Affiliation(s)
- Adnan Sharif
- Department of Nephrology and Transplantation, University Hospitals Birmingham, Queen Elizabeth Hospital, Birmingham, United Kingdom
- Institute of Immunology and Immunotherapy, University of Birmingham, Birmingham, United Kingdom
- *Correspondence: Adnan Sharif,
| |
Collapse
|
|
24
|
Stewart DE, Foutz J, Kamal L, Weiss S, McGehee HS, Cooper M, Gupta G. The Independent Effects of Procurement Biopsy Findings on Ten-Year Outcomes of Extended Criteria Donor Kidney Transplants. Kidney Int Rep 2022; 7:1850-1865. [PMID: 35967103 PMCID: PMC9366372 DOI: 10.1016/j.ekir.2022.05.027] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2022] [Accepted: 05/23/2022] [Indexed: 11/01/2022] Open
Abstract
Introduction Methods Results Conclusion
Collapse
|
|
25
|
Di Caprio D, Santos-Arteaga FJ. Enhancing the pattern recognition capacity of machine learning techniques: The importance of feature positioning. MACHINE LEARNING WITH APPLICATIONS 2022. [DOI: 10.1016/j.mlwa.2021.100196] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022] Open
|
|
26
|
Díez-Sanmartín C, Sarasa-Cabezuelo A, Andrés Belmonte A. The impact of artificial intelligence and big data on end-stage kidney disease treatments. EXPERT SYSTEMS WITH APPLICATIONS 2021; 180:115076. [DOI: 10.1016/j.eswa.2021.115076] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 08/29/2023]
|
|
27
|
Seyahi N, Ozcan SG. Artificial intelligence and kidney transplantation. World J Transplant 2021; 11:277-289. [PMID: 34316452 PMCID: PMC8290997 DOI: 10.5500/wjt.v11.i7.277] [Citation(s) in RCA: 13] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/28/2021] [Revised: 05/17/2021] [Accepted: 06/04/2021] [Indexed: 02/06/2023] Open
Abstract
Artificial intelligence and its primary subfield, machine learning, have started to gain widespread use in medicine, including the field of kidney transplantation. We made a review of the literature that used artificial intelligence techniques in kidney transplantation. We located six main areas of kidney transplantation that artificial intelligence studies are focused on: Radiological evaluation of the allograft, pathological evaluation including molecular evaluation of the tissue, prediction of graft survival, optimizing the dose of immunosuppression, diagnosis of rejection, and prediction of early graft function. Machine learning techniques provide increased automation leading to faster evaluation and standardization, and show better performance compared to traditional statistical analysis. Artificial intelligence leads to improved computer-aided diagnostics and quantifiable personalized predictions that will improve personalized patient care.
Collapse
Affiliation(s)
- Nurhan Seyahi
- Department of Nephrology, Istanbul University-Cerrahpaşa, Cerrahpaşa Medical Faculty, Istanbul 34098, Fatih, Turkey
| | - Seyda Gul Ozcan
- Department of Internal Medicine, Istanbul University-Cerrahpaşa, Cerrahpaşa Medical Faculty, Istanbul 34098, Fatih, Turkey
| |
Collapse
|
|
28
|
Clement J, Maldonado AQ. Augmenting the Transplant Team With Artificial Intelligence: Toward Meaningful AI Use in Solid Organ Transplant. Front Immunol 2021; 12:694222. [PMID: 34177958 PMCID: PMC8226178 DOI: 10.3389/fimmu.2021.694222] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2021] [Accepted: 05/27/2021] [Indexed: 11/19/2022] Open
Abstract
Advances in systems immunology, such as new biomarkers, offer the potential for highly personalized immunosuppression regimens that could improve patient outcomes. In the future, integrating all of this information with other patient history data will likely have to rely on artificial intelligence (AI). AI agents can help augment transplant decision making by discovering patterns and making predictions for specific patients that are not covered in the literature or in ways that are impossible for humans to anticipate by integrating vast amounts of data (e.g. trending across numerous biomarkers). Similar to other clinical decision support systems, AI may help overcome human biases or judgment errors. However, AI is not widely utilized in transplant to date. In this rapid review, we survey the methods employed in recent research in transplant-related AI applications and identify concerns related to implementing these tools. We identify three key challenges (bias/accuracy, clinical decision process/AI explainability, AI acceptability criteria) holding back AI in transplant. We also identify steps that can be taken in the near term to help advance meaningful use of AI in transplant (forming a Transplant AI Team at each center, establishing clinical and ethical acceptability criteria, and incorporating AI into the Shared Decision Making Model).
Collapse
Affiliation(s)
- Jeffrey Clement
- Information and Decision Sciences, Carlson School of Management, University of Minnesota, Minneapolis, MN, United States
| | | |
Collapse
|
|
29
|
Statistical methods versus machine learning techniques for donor-recipient matching in liver transplantation. PLoS One 2021; 16:e0252068. [PMID: 34019601 PMCID: PMC8139468 DOI: 10.1371/journal.pone.0252068] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/14/2021] [Accepted: 05/09/2021] [Indexed: 12/17/2022] Open
Abstract
Donor-Recipient (D-R) matching is one of the main challenges to be fulfilled nowadays. Due to the increasing number of recipients and the small amount of donors in liver transplantation, the allocation method is crucial. In this paper, to establish a fair comparison, the United Network for Organ Sharing database was used with 4 different end-points (3 months, and 1, 2 and 5 years), with a total of 39, 189 D-R pairs and 28 donor and recipient variables. Modelling techniques were divided into two groups: 1) classical statistical methods, including Logistic Regression (LR) and Naïve Bayes (NB), and 2) standard machine learning techniques, including Multilayer Perceptron (MLP), Random Forest (RF), Gradient Boosting (GB) or Support Vector Machines (SVM), among others. The methods were compared with standard scores, MELD, SOFT and BAR. For the 5-years end-point, LR (AUC = 0.654) outperformed several machine learning techniques, such as MLP (AUC = 0.599), GB (AUC = 0.600), SVM (AUC = 0.624) or RF (AUC = 0.644), among others. Moreover, LR also outperformed standard scores. The same pattern was reproduced for the others 3 end-points. Complex machine learning methods were not able to improve the performance of liver allocation, probably due to the implicit limitations associated to the collection process of the database.
Collapse
|
|
30
|
Revuelta I, Santos-Arteaga FJ, Montagud-Marrahi E, Ventura-Aguiar P, Di Caprio D, Cofan F, Cucchiari D, Torregrosa V, Piñeiro GJ, Esforzado N, Bodro M, Ugalde-Altamirano J, Moreno A, Campistol JM, Alcaraz A, Bayès B, Poch E, Oppenheimer F, Diekmann F. A hybrid data envelopment analysis-artificial neural network prediction model for COVID-19 severity in transplant recipients. Artif Intell Rev 2021; 54:4653-4684. [PMID: 33907345 PMCID: PMC8062617 DOI: 10.1007/s10462-021-10008-0] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 04/13/2021] [Indexed: 01/08/2023]
Abstract
In an overwhelming demand scenario, such as the SARS-CoV-2 pandemic, pressure over health systems may outburst their predicted capacity to deal with such extreme situations. Therefore, in order to successfully face a health emergency, scientific evidence and validated models are needed to provide real-time information that could be applied by any health center, especially for high-risk populations, such as transplant recipients. We have developed a hybrid prediction model whose accuracy relative to several alternative configurations has been validated through a battery of clustering techniques. Using hospital admission data from a cohort of hospitalized transplant patients, our hybrid Data Envelopment Analysis (DEA)—Artificial Neural Network (ANN) model extrapolates the progression towards severe COVID-19 disease with an accuracy of 96.3%, outperforming any competing model, such as logistic regression (65.5%) and random forest (44.8%). In this regard, DEA-ANN allows us to categorize the evolution of patients through the values of the analyses performed at hospital admission. Our prediction model may help guiding COVID-19 management through the identification of key predictors that permit a sustainable management of resources in a patient-centered model.
Collapse
Affiliation(s)
- Ignacio Revuelta
- Department of Nephrology and Renal Transplantation, Hospital Clínic, Villarroel 170 (Escala 10 - Planta 5), 08036 Barcelona, Spain.,Laboratori Experimental de Nefrologia i Trasplantament (LENIT), Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain.,Department of Medicine, University of Barcelona, Barcelona, Spain.,Red de Investigación Renal (REDINREN), Madrid, Spain
| | - Francisco J Santos-Arteaga
- Faculty of Economics and Management, Free University of Bolzano, Piazza Università 1, 39100 Bolzano, Italy
| | - Enrique Montagud-Marrahi
- Department of Nephrology and Renal Transplantation, Hospital Clínic, Villarroel 170 (Escala 10 - Planta 5), 08036 Barcelona, Spain
| | - Pedro Ventura-Aguiar
- Department of Nephrology and Renal Transplantation, Hospital Clínic, Villarroel 170 (Escala 10 - Planta 5), 08036 Barcelona, Spain.,Laboratori Experimental de Nefrologia i Trasplantament (LENIT), Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain.,Red de Investigación Renal (REDINREN), Madrid, Spain
| | - Debora Di Caprio
- Department of Economics and Management, University of Trento, Trento, Italy
| | - Frederic Cofan
- Department of Nephrology and Renal Transplantation, Hospital Clínic, Villarroel 170 (Escala 10 - Planta 5), 08036 Barcelona, Spain.,Department of Medicine, University of Barcelona, Barcelona, Spain
| | - David Cucchiari
- Department of Nephrology and Renal Transplantation, Hospital Clínic, Villarroel 170 (Escala 10 - Planta 5), 08036 Barcelona, Spain.,Laboratori Experimental de Nefrologia i Trasplantament (LENIT), Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain.,Red de Investigación Renal (REDINREN), Madrid, Spain
| | - Vicens Torregrosa
- Department of Nephrology and Renal Transplantation, Hospital Clínic, Villarroel 170 (Escala 10 - Planta 5), 08036 Barcelona, Spain.,Laboratori Experimental de Nefrologia i Trasplantament (LENIT), Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain.,Red de Investigación Renal (REDINREN), Madrid, Spain
| | - Gaston Julio Piñeiro
- Department of Nephrology and Renal Transplantation, Hospital Clínic, Villarroel 170 (Escala 10 - Planta 5), 08036 Barcelona, Spain.,Laboratori Experimental de Nefrologia i Trasplantament (LENIT), Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain.,Red de Investigación Renal (REDINREN), Madrid, Spain
| | - Nuria Esforzado
- Department of Nephrology and Renal Transplantation, Hospital Clínic, Villarroel 170 (Escala 10 - Planta 5), 08036 Barcelona, Spain.,Department of Medicine, University of Barcelona, Barcelona, Spain
| | - Marta Bodro
- Department of Medicine, University of Barcelona, Barcelona, Spain.,Department of Infectious Diseases, Hospital Clinic Barcelona, Barcelona, Spain.,Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain
| | - Jessica Ugalde-Altamirano
- Department of Nephrology and Renal Transplantation, Hospital Clínic, Villarroel 170 (Escala 10 - Planta 5), 08036 Barcelona, Spain.,Laboratori Experimental de Nefrologia i Trasplantament (LENIT), Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain
| | - Asuncion Moreno
- Department of Medicine, University of Barcelona, Barcelona, Spain.,Department of Infectious Diseases, Hospital Clinic Barcelona, Barcelona, Spain.,Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain
| | - Josep M Campistol
- Department of Nephrology and Renal Transplantation, Hospital Clínic, Villarroel 170 (Escala 10 - Planta 5), 08036 Barcelona, Spain.,Laboratori Experimental de Nefrologia i Trasplantament (LENIT), Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain.,Department of Medicine, University of Barcelona, Barcelona, Spain.,Red de Investigación Renal (REDINREN), Madrid, Spain
| | - Antonio Alcaraz
- Department of Medicine, University of Barcelona, Barcelona, Spain.,Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain.,Department of Urology, Hospital Clinic Barcelona, Barcelona, Spain
| | - Beatriu Bayès
- Department of Nephrology and Renal Transplantation, Hospital Clínic, Villarroel 170 (Escala 10 - Planta 5), 08036 Barcelona, Spain.,Laboratori Experimental de Nefrologia i Trasplantament (LENIT), Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain.,Department of Medicine, University of Barcelona, Barcelona, Spain
| | - Esteban Poch
- Department of Nephrology and Renal Transplantation, Hospital Clínic, Villarroel 170 (Escala 10 - Planta 5), 08036 Barcelona, Spain.,Laboratori Experimental de Nefrologia i Trasplantament (LENIT), Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain.,Department of Medicine, University of Barcelona, Barcelona, Spain
| | - Federico Oppenheimer
- Department of Nephrology and Renal Transplantation, Hospital Clínic, Villarroel 170 (Escala 10 - Planta 5), 08036 Barcelona, Spain.,Laboratori Experimental de Nefrologia i Trasplantament (LENIT), Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain.,Department of Medicine, University of Barcelona, Barcelona, Spain.,Red de Investigación Renal (REDINREN), Madrid, Spain
| | - Fritz Diekmann
- Department of Nephrology and Renal Transplantation, Hospital Clínic, Villarroel 170 (Escala 10 - Planta 5), 08036 Barcelona, Spain.,Laboratori Experimental de Nefrologia i Trasplantament (LENIT), Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain.,Department of Medicine, University of Barcelona, Barcelona, Spain.,Red de Investigación Renal (REDINREN), Madrid, Spain
| |
Collapse
|
|
31
|
Toward Advancing Long-Term Outcomes of Kidney Transplantation with Artificial Intelligence. TRANSPLANTOLOGY 2021. [DOI: 10.3390/transplantology2020012] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022] Open
Abstract
After decades of pioneering advances and improvements, kidney transplantation is now the renal replacement therapy of choice for most patients with end-stage kidney disease (ESKD). Despite this success, the high risk of premature death and frequent occurrence of graft failure remain important clinical and research challenges. The current burst of studies and other innovative initiatives using artificial intelligence (AI) for a wide range of analytical and practical applications in biomedical areas seems to correlate with the same trend observed in publications in the kidney transplantation field, and points toward the potential of such novel approaches to address the aforementioned aim of improving long-term outcomes of kidney transplant recipients (KTR). However, at the same time, this trend underscores now more than ever the old methodological challenges and potential threats that the research and clinical community needs to be aware of and actively look after with regard to AI-driven evidence. The purpose of this narrative mini-review is to explore challenges for obtaining applicable and adequate kidney transplant data for analyses using AI techniques to develop prediction models, and to propose next steps in the field. We make a call to act toward establishing the strong collaborations needed to bring innovative synergies further augmented by AI, which have the potential to impact the long-term care of KTR. We encourage researchers and clinicians to submit their invaluable research, including original clinical and imaging studies, database studies from registries, meta-analyses, and AI research in the kidney transplantation field.
Collapse
|