To evaluate temporal trends in gender, etiology, severity, outcomes, cost and median length of stay (MLS) in patients with acute pancreatitis (AP) in a third-tier Chinese city.

Patients with AP admitted to a university hospital between January 2013 and December 2021. Relationships between etiology, prevalence of severe acute pancreatitis (SAP) and survey years were investigated by joinpoint regression analysis.

A total of 5459 (male 62.3%) patients with AP were included. Between January 2013 and December 2021, we observed: (a) the prevalence of biliary diseases-related AP was stable, while the prevalence of hypertriglyceridemia (HTG)-associated AP (Ptrend = 0.04) and alcohol-associated AP (Ptrend < 0.0001) both increased; (b) there was an increase in crude prevalence of SAP from 4.97% to 12.2% between 2013 and 2021 (Ptrend < 0.0001); (c) compared to female populations, male gender had a higher prevalence of AP; (d) there was a decrease in MLS from 11 days to 8 days (Ptrend < 0.0001) and in median cost of hospitalization (MCH) for all patients (from 20,166 to 12,845 YUAN) (Ptrend < 0.0001); (e) the overall in-hospital mortality rate was 1.28% (70/5459) for patients with AP. There was no statistically significant in the time trend of mortality during the study period (Ptrend = 0.5873). At multivariate analysis, survey year was associated with prevalence of SAP after adjustment by age and biliary diseases (OR: 1.07; 95% CI: 1.03-1.12). Based on the stratification by severity of disease, the decrease of MLS and MCH was more significant in non-SAP vs. SAP patients.

Over the observational period, the proportion of male patients with AP, prevalence of age-adjusted rate of HTG and alcohol-associated AP and SAP increased, while MLS and MCH for all patients decreased, and the time trend of mortality of AP was stable.

The integration of Artificial Intelligence (AI) with the Internet of Medical Things (IoMT) has revolutionized disease prediction and detection, but challenges such as data heterogeneity, privacy concerns, and model generalizability hinder its full potential in healthcare. This review examines these challenges and evaluates the effectiveness of AI-IoMT techniques in predicting chronic and terminal diseases, including cardiovascular conditions, Alzheimer's disease, and cancers. We analyze a range of Machine Learning (ML) and Deep Learning (DL) approaches (e.g., XGBoost, Random Forest, CNN, LSTM), alongside advanced strategies like federated learning, transfer learning, and blockchain, to improve model robustness, data security, and interoperability. Findings highlight that transfer learning and ensemble methods enhance model adaptability across clinical settings, while blockchain and federated learning effectively address privacy and data standardization. Ultimately, the review emphasizes the importance of data harmonization, secure frameworks, and multi-disease models as critical research directions for scalable, comprehensive AI-IoMT solutions in healthcare.

COVID-19 is a disease in which early prognosis of severity is critical for desired patient outcomes and for the management of limited resources like intensive care unit beds and ventilation equipment. Many prognostic statistical tools have been developed for the prediction of disease severity, but it is still unclear which ones should be used in practice. We aim to guide clinicians in choosing the best available tools to make optimal decisions and assess their role in resource management and assess what can be learned from the COVID-19 scenario for development of prediction models in similar medical applications. Using the five major medical databases: MEDLINE (via PubMed), Embase, Cochrane Library (CENTRAL), Cochrane COVID-19 Study Register, and Scopus, we conducted a comprehensive systematic review of prediction tools between 2020 January and 2023 April for hospitalized COVID-19 patients. We identified both the relevant confounding factors of tool performance using the MetaForest algorithm and the best tools-comparing linear, machine learning, and deep learning methods-with mixed-effects meta-regression models. The risk of bias was evaluated using the PROBAST tool. Our systematic search identified eligible 27,312 studies, out of which 290 were eligible for data extraction, reporting on 430 independent evaluations of severity prediction tools with ~ 2.8 million patients. Neural Network-based tools have the highest performance with a pooled AUC of 0.893 (0.748-1.000), 0.752 (0.614-0.853) sensitivity, 0.914 (0.849-0.952) specificity, using clinical, laboratory, and imaging data. The relevant confounders of performance are the geographic region of patients, the rate of severe cases, and the use of C-Reactive Protein as input data. 88% of studies have a high risk of bias, mostly because of deficiencies in the data analysis. All investigated tools in use aid decision-making for COVID-19 severity prediction, but Machine Learning tools, specifically Neural Networks clearly outperform other methods, especially in cases when the basic characteristics of severe and non-severe patient groups are similar, and without the need for more data. When highly specific biomarkers are not available-such as in the case of COVID-19-practitioners should abandon general clinical severity scores and turn to disease specific Machine Learning tools.

The Hungarian Pancreatic Study Group (HPSG) was established with the aim of advancing pancreatology. Our summary outlines the methodologies, key results, and future directions of the HPSG. Methodological elements included, the formation of strategic national and international collaborations, the establishment of patient registries and biobanks, and a strong focus on education and guideline development. Key results encompassed, pioneering research on pancreatic ductal function and the role of cystic fibrosis transmembrane conductance regulator (CFTR) in inflammation, significant advancements in understanding acute and chronic pancreatitis, and the execution of numerous clinical trials to explore new therapeutic approaches. Despite challenges, such as securing funding and translating research into clinical practice, the HPSG's commitment to patient care and scientific innovation has been unwavering. The group aims to deepen research into pancreatic cancer and chronic pancreatitis, conduct more randomized controlled trials (RCTs), and expand its efforts internationally by involving global staff and patients. The authors hope that this summary inspires others to undertake similar initiatives and contribute to the global advancement of medical research and patient care in pancreatology.

Increased systemic concentrations of YKL-40 are seen in various inflammatory conditions. We explored the relationship between the serum YKL-40 concentrations and subsequent disease severity in patients with acute pancreatitis (AP).

Consecutive adults with AP were prospectively enrolled, and classified as having mild, moderate or severe disease. On admission and 48 h later, C-reactive protein (CRP), YKL-40, interleukin-6 and 8 (IL-6, IL-8), and tumor necrosis factor alpha (TNF-α) concentrations were measured. Patients were also classified as those with low (<50 ng/mL, in the range seen in 30 age and sex-matched non-AP subjects), high (≥190 ng/mL, seen in most of the other inflammatory conditions), and intermediate YKL-40 (50-189 ng/mL).

Incidence of mild, moderate and severe AP among the 150 enrolled patients was 80 (53.3 %), 59 (39.3 %), and 11 (7.4 %), respectively. Both on admission and 48 h later, high YKL-40 (vs. intermediate or low) was strongly associated with higher odds of a more severe AP, independently of the concurrent IL-8 and TNF-α concentrations (OR around 3.5-4.0, or higher). On admission, the association was independent also of the concurrent CRP, whereas the association between the later concentrations and the outcome was conditional on CRP - uncertain at low, strong at high CRP. The high YKL-40 - outcome association at both time-points was conditional on concurrent IL-6: uncertain if IL-6 was low, strong if IL-6 was high.

Serum YKL-40 is a plausible candidate for further evaluation as an early biochemical indicator of subsequent AP severity, particularly if considered jointly with CRP and/or IL-6.

Acute pancreatitis (AP) can rapidly progress from a stable condition to multiple organ failure with high mortality. We aimed to describe the characteristics of AP patients requiring admission to a critical care facility and to identify predictors of disease progression.

We conducted a post-hoc analysis using prospectively collected data from AP patients admitted to the high dependency unit (HDU) and intensive care unit (ICU) at the University of Pécs, Hungary, from 2016 to 2019. Patients were categorized according to critical care needs and severity. Daily records of organ function, organ support and laboratory parameters were kept. Descriptive analysis and predictive models were developed to forecast the need for escalated critical care and mortality.

Analysis of 92 cases (65 % male, mean age 63 (range 19-92) years) revealed a median critical care stay of 8 days (range 1-69) and a mortality rate of 47 %. Naive Bayes prediction models using admission C-reactive protein (CRP) and amylase levels achieved 75 % accuracy in predicting mortality and a 65 % probability of requiring HDU and/or ICU admission. CRP levels increased significantly (47 vs 62 mg/l, p: 0.015) from 48 to 24 h before critical care admission, contrasting with controls, resulting in significantly higher CRP levels in critical care patients (62 vs 32 mg/l, p: 0.007) 24 h before admission.

Our findings suggest that on-admission CRP and amylase cannot reliably predict progression of AP. However, elevated and increasing levels of CRP and amylase may indicate the need for early HDU admission to enable closer monitoring.

An accurate prognostic tool is essential to aid clinical decision-making (e.g., patient triage) and to advance personalized medicine. However, such a prognostic tool is lacking for acute pancreatitis (AP). Increasingly machine learning (ML) techniques are being used to develop high-performing prognostic models in AP. However, methodologic and reporting quality has received little attention. High-quality reporting and study methodology are critical for model validity, reproducibility, and clinical implementation. In collaboration with content experts in ML methodology, we performed a systematic review critically appraising the quality of methodology and reporting of recently published ML AP prognostic models.

Using a validated search strategy, we identified ML AP studies from the databases MEDLINE and EMBASE published between January 2021 and December 2023. We also searched pre-print servers medRxiv, bioRxiv, and arXiv for pre-prints registered between January 2021 and December 2023. Eligibility criteria included all retrospective or prospective studies that developed or validated new or existing ML models in patients with AP that predicted an outcome following an episode of AP. Meta-analysis was considered if there was homogeneity in the study design and in the type of outcome predicted. For risk of bias (ROB) assessment, we used the Prediction Model Risk of Bias Assessment Tool. Quality of reporting was assessed using the Transparent Reporting of a Multivariable Prediction Model of Individual Prognosis or Diagnosis-Artificial Intelligence (TRIPOD+AI) statement that defines standards for 27 items that should be reported in publications using ML prognostic models. The search strategy identified 6,480 publications of which 30 met the eligibility criteria. Studies originated from China (22), the United States (4), and other (4). All 30 studies developed a new ML model and none sought to validate an existing ML model, producing a total of 39 new ML models. AP severity (23/39) or mortality (6/39) were the most common outcomes predicted. The mean area under the curve for all models and endpoints was 0.91 (SD 0.08). The ROB was high for at least one domain in all 39 models, particularly for the analysis domain (37/39 models). Steps were not taken to minimize over-optimistic model performance in 27/39 models. Due to heterogeneity in the study design and in how the outcomes were defined and determined, meta-analysis was not performed. Studies reported on only 15/27 items from TRIPOD+AI standards, with only 7/30 justifying sample size and 13/30 assessing data quality. Other reporting deficiencies included omissions regarding human-AI interaction (28/30), handling low-quality or incomplete data in practice (27/30), sharing analytical codes (25/30), study protocols (25/30), and reporting source data (19/30).

There are significant deficiencies in the methodology and reporting of recently published ML based prognostic models in AP patients. These undermine the validity, reproducibility, and implementation of these prognostic models despite their promise of superior predictive accuracy.

Research Registry (reviewregistry1727).

Ariel Dynamic Acute Pancreatitis Tracker (ADAPT) is an artificial intelligence tool using mathematical algorithms to predict severity and manage fluid resuscitation needs based on the physiologic parameters of individual patients. Our aim was to assess whether adherence to ADAPT fluid recommendations vs standard management impacted clinical outcomes in a large prospective cohort.

We analyzed patients consecutively admitted to the Los Angeles General Medical Center between June 2015 and November 2022 whose course was richly characterized by capturing more than 100 clinical variables. We inputted these data into the ADAPT system to generate resuscitation fluid recommendations and compared with the actual fluid resuscitation within the first 24 hours from presentation. The primary outcome was the difference in organ failure in those who were over-resuscitated (>500 mL) vs adequately resuscitated (within 500 mL) with respect to the ADAPT fluid recommendation. Additional outcomes included intensive care unit admission, systemic inflammatory response syndrome (SIRS) at 48 hours, local complications, and pancreatitis severity.

Among the 1,083 patients evaluated using ADAPT, 700 were over-resuscitated, 196 were adequately resuscitated, and 187 were under-resuscitated. Adjusting for pancreatitis etiology, gender, and SIRS at admission, over-resuscitation was associated with increased respiratory failure (odd ratio [OR] 2.73, 95% confidence interval [CI] 1.06-7.03) as well as intensive care unit admission (OR 2.40, 1.41-4.11), more than 48 hours of hospital length of stay (OR 1.87, 95% CI 1.19-2.94), SIRS at 48 hours (OR 1.73, 95% CI 1.08-2.77), and local pancreatitis complications (OR 2.93, 95% CI 1.23-6.96).

Adherence to ADAPT fluid recommendations reduces respiratory failure and other adverse outcomes compared with conventional fluid resuscitation strategies for acute pancreatitis. This validation study demonstrates the potential role of dynamic machine learning tools in acute pancreatitis management.

Early identification of pancreatitis remains a significant clinical diagnostic challenge that impacts patient outcomes. The evolution of quantitative imaging followed by deep learning models has shown great promise in the non-invasive diagnosis of pancreatitis and its complications. We provide an overview of advancements in diagnostic imaging and quantitative imaging methods along with the evolution of artificial intelligence (AI). In this article, we review the current and future states of methodology and limitations of AI in improving clinical support in the context of early detection and management of pancreatitis.

To summarise the currently developed risk prediction models for medication adherence in patients with chronic diseases and evaluate their performance and applicability.

Ensuring medication adherence is crucial in effectively managing chronic diseases. Although numerous studies have endeavoured to construct risk prediction models for predicting medication adherence in patients with chronic illnesses, the reliability and practicality of these models remain uncertain.

Systematic review.

We conducted searches on PubMed, Web of Science, Cochrane, CINAHL, Embase and Medline from inception until 16 July 2023. Two authors independently screened risk prediction models for medication adherence that met the predefined inclusion criteria. The Prediction Model Risk of Bias Assessment Tool (PROBAST) was employed to evaluate both the risk of bias and clinical applicability of the included studies. This systematic review adhered to the 2020 PRISMA checklist.

The study included a total of 11 risk prediction models from 11 studies. Medication regimen and age were the most common predictors. The use of PROBAST revealed that some essential methodological details were not thoroughly reported in these models. Due to limitations in methodology, all models were rated as having a high-risk for bias.

According to PROBAST, the current models for predicting medication adherence in patients with chronic diseases exhibit a high risk of bias. Future research should prioritise enhancing the methodological quality of model development and conducting external validations on existing models.

Based on the review findings, recommendations have been provided to refine the construction methodology of prediction models with an aim of identifying high-risk individuals and key factors associated with low medication adherence in chronic diseases.

This systematic review was conducted without patient or public participation.

This study aimed to develop and validate a risk prediction model for predicting the likelihood of coagulation in patients undergoing anticoagulant-free hemodialysis (HD). Anticoagulant-free HD technique is necessary in patients with contraindications to systemic therapy. Coagulation is a complication of this technique. Unfortunately, no predictive model is currently available to assess the risk of coagulation in anticoagulant-free HD.

We retrospectively analyzed the clinical data from 299 HD sessions involving 164 patients who underwent anticoagulant-free HD between January 2022 and June 2023. To identify the risk factors for coagulation in anticoagulant-free HD, a univariate analysis was performed on 18 independent variables. Logistic regression was used to establish predictive models by identifying factors contributing to coagulation in anticoagulant-free HD. A calibration curve was drawn using regression coefficients and 1,000 bootstrap repetitions to validate our model internally. The performance of the prediction model was evaluated using receiver operating characteristic, area under the curve (AUC), and decision curve analysis (DCA).

The incidence of coagulation in patients on anticoagulant-free HD was 35.1%. Logistic regression analysis showed that platelet (PLT), hematocrit (HCT) levels, dialysate type, and age were risk factors for coagulation in anticoagulant-free HD patients (p < 0.05). The Hosmer-Lemeshow test showed p = 0.29, and the AUC is 0.76 (95% CI 0.70-0.80). The optimal critical value was 0.40, yielding a sensitivity of 61.0%, a specificity of 80.4%, and a Youden index of 0.41.

In anticoagulant-free HD, there were numerous risk factors and a 35.1% occurrence of coagulation. The constructed coagulation risk prediction model exhibited good predictive and clinical utility and could serve as a reference for the initial assessment and screening of coagulation risk in anticoagulant-free HD.

To apply CT-based deep learning (DL) models for accurate solid debris-based classification of pancreatic fluid collections (PFC) in acute pancreatitis (AP).

This retrospective study comprised four tertiary care hospitals. Consecutive patients with AP and PFCs who had computed tomography (CT) prior to drainage were screened. Those who had magnetic resonance imaging (MRI) or endoscopic ultrasound (EUS) within 20 days of CT were considered for inclusion. Axial CT images were utilized for model training. Images were labelled as those with≤30% solid debris and >30% solid debris based on MRI or EUS. Single center data was used for model training and validation. Data from other three centers comprised the held out external test cohort. We experimented with ResNet 50, Vision transformer (ViT), and MedViT architectures.

Overall, we recruited 152 patients (129 training/validation and 23 testing). There were 1334, 334 and 512 images in the training, validation, and test cohorts, respectively. In the overall training and validation cohorts, ViT and MedVit models had high diagnostic performance (sensitivity 92.4-98.7%, specificity 89.7-98.4%, and AUC 0.908-0.980). The sensitivity (85.3-98.6%), specificity (69.4-99.4%), and AUC (0.779-0.984) of all the models was high in all the subgroups in the training and validation cohorts. In the overall external test cohort, MedViT had the best diagnostic performance (sensitivity 75.2%, specificity 75.3%, and AUC 0.753). MedVit had sensitivity, specificity, and AUC of 75.2%, 74.3%, and 0.748, in walled off necrosis and 79%, 74.2%, 75.3%, and 0.767 for collections >5 cm.

DL-models have moderate diagnostic performance for solid-debris based classification of WON and collections greater than 5 cm on CT.

Chronic liver diseases (CLD) affect 1.5 billion patients worldwide, with dramatically increasing incidence in recent decades. It has been hypothesized that the chronic hyperinflammation associated with CLD may increase the risk of a more severe course of acute pancreatitis (AP). This study aims to investigate the underlying impact of CLD on the outcomes of AP. A systematic search was conducted in Embase, Medline, and Central databases until October 2022. Studies investigating patients with acute pancreatitis and CLD, were included in the meta-analysis. A total of 14,963 articles were screened, of which 36 were eligible to be included. CLD was a risk factor for increased mortality with an odds ratio (OR) of 2.53 (CI 1.30 to 4.93, p = 0.01). Furthermore, renal, cardiac, and respiratory failures were more common in the CLD group, with ORs of 1.92 (CI 1.3 to 2.83, p = 0.01), 2.11 (CI 0.93 to 4.77, p = 0.062) and 1.99 (CI 1.08 to 3.65, p = 0.033), respectively. Moreover, the likelihood of developing Systemic Inflammatory Response Syndrome (SIRS) was significantly higher, with an OR of 1.95 (CI 1.03 to 3.68, p = 0.042). CLD is an important risk factor for worse outcomes in AP pancreatitis, leading to higher mortality and increased rates of local and systemic complications.

The purpose of this study is to explore whether machine learning can be used to establish an effective model for the diagnosis of Parkinson's disease (PD) by using texture features extracted from cerebellar gray matter and white matter, so as to identify subtle changes that cannot be observed by the naked eye.

This study involved a data collection period from June 2010 to March 2023, including 374 subjects from two cohorts. The Parkinson's Progression Markers Initiative (PPMI) served as the training set, with control group and PD patients (HC: 102 and PD: 102) from 24 global sites. Our institution's data was utilized as the test set (HC: 91 and PD: 79). Machine learning was employed to establish multiple models for PD diagnosis based on texture features of the cerebellum's gray and white matter. Results underwent evaluation through 5-fold cross-validation analysis, calculating the area under the receiver operating characteristic curve (AUC) for each model. The performance of each model was compared using the Delong test, and the interpretability of the optimized model was further augmented by employing Shapley additive explanations (SHAP).

The AUCs for all pipelines in the validation dataset were compared using FeAture Explorer (FAE) software. Among the models established by Kruskal-Wallis (KW) and logistic regression via Lasso (LRLasso), the AUC was highest using the "one-standard error" rule. 'WM_original_glrlm_GrayLevelNonUniformity' was considered the most stable and predictive feature.

The texture features of cerebellar gray matter and white matter combined with machine learning may have potential value in the diagnosis of Parkinson's disease, in which the heterogeneity of white matter may be a more valuable imaging marker.

To evaluate troponin I, creatine kinase isoenzyme, and the new Japanese Severity Score(JSS) for predicting Severe Acute Pancreatitis-Associated myocardial Injury(SACI).

This retrospective study included 136 patients with Severe Acute Pancreatitis, hospitalized in grade-III hospital from June 1, 2015, to October 31, 2022; selected using convenience sampling method and divided into SACI occurrence (n =34) and SACI non-occurrence (n =102) groups. New JSS evaluated predictive value of each SACI index. Binary logistic regression model compared risk factors and constructed a prediction model. Area under receiver operating characteristic curve (AUC) and Hosmer-Lemeshow goodness of fit test evaluated model's prediction efficiency and calibration ability.

The incidence of SACI was 25%. Univariate analysis found that troponin I and creatine kinase isoenzyme were significantly different (P < 0.05) and independent risk factors for SACI. The new JSS, troponin I, and creatine kinase isoenzyme were included in the prediction model. The prediction model had a good calibration ability, and its predicted value and the actual observed value were not significantly different (Hosmer-Lemeshow χ2 = 5.408, P = 0.368). AUC of the model was 0.803 (95% CI: 0.689-0.918), and the optimal threshold of the prediction model was 0.318 with the maximum Youden index (0.488). The AUC for internal validation was 0.788 (95% CI: 0.657-0.876), and external validation was 0.761 (95% CI: 0.622-0.832).

Troponin I and creatine kinase isoenzymes combined with the new JSS have a high predictive value for SACI, improving the early prediction and treatment of at-risk patients.

Predicting the severity of acute pancreatitis (AP) early poses a challenge in clinical practice. While there are well-established clinical scoring tools, their actual predictive performance remains uncertain. Various studies have explored the application of machine-learning methods for early AP prediction. However, a more comprehensive evidence-based assessment is needed to determine their predictive accuracy. Hence, this systematic review and meta-analysis aimed to evaluate the predictive accuracy of machine learning in assessing the severity of AP.

PubMed, EMBASE, Cochrane Library, and Web of Science were systematically searched until December 5, 2023. The risk of bias in eligible studies was assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Subgroup analyses, based on different machine learning types, were performed. Additionally, the predictive accuracy of mainstream scoring tools was summarized.

This systematic review ultimately included 33 original studies. The pooled c-index in both the training and validation sets was 0.87 (95 % CI: 0.84-0.89) and 0.88 (95 % CI: 0.86-0.90), respectively. The sensitivity in the training set was 0.81 (95 % CI: 0.77-0.84), and in the validation set, it was 0.79 (95 % CI: 0.71-0.85). The specificity in the training set was 0.84 (95 % CI: 0.78-0.89), and in the validation set, it was 0.90 (95 % CI: 0.86-0.93). The primary model incorporated was logistic regression; however, its predictive accuracy was found to be inferior to that of neural networks, random forests, and xgboost. The pooled c-index of the APACHE II, BISAP, and Ranson were 0.74 (95 % CI: 0.68-0.80), 0.77 (95 % CI: 0.70-0.85), and 0.74 (95 % CI: 0.68-0.79), respectively.

Machine learning demonstrates excellent accuracy in predicting the severity of AP, providing a reference for updating or developing a straightforward clinical prediction tool.

Aim to establish a multimodal model for predicting severe acute pancreatitis (SAP) using machine learning (ML) and deep learning (DL).

In this multicentre retrospective study, patients diagnosed with acute pancreatitis at admission were enrolled from January 2017 to December 2021. Clinical information within 24 h and CT scans within 72 h of admission were collected. First, we trained Model α based on clinical features selected by least absolute shrinkage and selection operator analysis. Second, radiomics features were extracted from 3D-CT scans and Model β was developed on the features after dimensionality reduction using principal component analysis. Third, Model γ was trained on 2D-CT images. Lastly, a multimodal model, namely PrismSAP, was constructed based on aforementioned features in the training set. The predictive accuracy of PrismSAP was verified in the validation and internal test sets and further validated in the external test set. Model performance was evaluated using area under the curve (AUC), accuracy, sensitivity, specificity, recall, precision and F1-score.

A total of 1,221 eligible patients were randomly split into a training set (n = 864), a validation set (n = 209) and an internal test set (n = 148). Data of 266 patients were for external testing. In the external test set, PrismSAP performed best with the highest AUC of 0.916 (0.873-0.960) among all models [Model α: 0.709 (0.618-0.800); Model β: 0.749 (0.675-0.824); Model γ: 0.687 (0.592-0.782); MCTSI: 0.778 (0.698-0.857); RANSON: 0.642 (0.559-0.725); BISAP: 0.751 (0.668-0.833); SABP: 0.710 (0.621-0.798)].

The proposed multimodal model outperformed any single-modality models and traditional scoring systems.

Acute pancreatitis (AP) is a complex and life-threatening disease. Early recognition of factors predicting morbidity and mortality is crucial. We aimed to develop and validate a pragmatic model to predict the individualized risk of early intensive care unit (ICU) admission for patients with AP.

The 2019 Nationwide Readmission Database was used to identify patients hospitalized with a primary diagnosis of AP without ICU admission. A matched comparison cohort of AP patients with ICU admission within 7 days of hospitalization was identified from the National Inpatient Sample after 1:N propensity score matching. The least absolute shrinkage and selection operator (LASSO) regression was used to select predictors and develop an ICU acute pancreatitis risk (IAPR) score validated by 10-fold cross-validation.

A total of 1513 patients hospitalized for AP were included. The median age was 50.0 years (interquartile range: 39.0-63.0). The three predictors that were selected included hypoxia (area under the curve [AUC] 0.78), acute kidney injury (AUC 0.72), and cardiac arrhythmia (AUC 0.61). These variables were used to develop a nomogram that displayed excellent discrimination (AUC 0.874) (bootstrap bias-corrected 95% confidence interval 0.824-0.876). There was no evidence of miscalibration (test statistic = 2.88; P = 0.09). For high-risk patients (total score >6 points), the sensitivity was 68.94% and the specificity was 92.66%.

This supervised machine learning-based model can help recognize high-risk AP hospitalizations. Clinicians may use the IAPR score to identify patients with AP at high risk of ICU admission within the first week of hospitalization.

Acute pancreatitis (AP) is a leading gastrointestinal disease that causes hospitalization. Initial management in the first 72 h after the diagnosis of AP is pivotal, which can influence the clinical outcomes of the disease. Initial management, including assessment of disease severity, fluid resuscitation, pain control, nutritional support, antibiotic use, and endoscopic retrograde cholangiopancreatography (ERCP) in gallstone pancreatitis, plays a fundamental role in AP treatment. Recent updates for fluid resuscitation, including treatment goals, the type, rate, volume, and duration, have triggered a paradigm shift from aggressive hydration with normal saline to goal-directed and non-aggressive hydration with lactated Ringer's solution. Evidence of the clinical benefit of early enteral feeding is becoming definitive. The routine use of prophylactic antibiotics is generally limited, and the procalcitonin-based algorithm of antibiotic use has recently been investigated to distinguish between inflammation and infection in patients with AP. Although urgent ERCP (within 24 h) should be performed for patients with gallstone pancreatitis and cholangitis, urgent ERCP is not indicated in patients without cholangitis. The management approach for patients with local complications of AP, particularly those with infected necrotizing pancreatitis, is discussed in detail, including indications, timing, anatomical considerations, and selection of intervention methods. Furthermore, convalescent treatment, including cholecystectomy in gallstone pancreatitis, lipid-lowering medications in hypertriglyceridemia-induced AP, and alcohol intervention in alcoholic pancreatitis, is also important for improving the prognosis and preventing recurrence in patients with AP. This review focuses on recent updates on the initial and convalescent management strategies for AP.

Acute pancreatitis is a common gastrointestinal emergency. Approximately 20% of patients with acute pancreatitis develop organ failure, which is significantly associated with adverse outcomes. This study aimed to establish an early prediction model for persistent organ failure in acute pancreatitis patients using 24-hour admission indicators.

Clinical data and 24-h laboratory indicators of patients diagnosed with acute pancreatitis from January 1, 2017 to January 1, 2022 in Shanxi Bethune Hospital were collected. Patients from 2017 to 2021 were used as the training cohort to establish the prediction model, and patients from 2021 to 2022 were used as the validation cohort. Univariate logistic regression and LASSO regression were used to establish prediction models. The performance of the model was evaluated using area under the curve (AUC), calibration curves, and decision curve analysis (DCA), and subsequently validated in the validation group.

A total of 1166 patients with acute pancreatitis were included, a total of 145 patients suffered from persistent organ failure from 2017 to 2021. Data were initially selected for 100 variables, and after inclusion and exclusion, 46 variables were used for further analysis. Two prediction models were established and nomogram was drawn respectively. After comparison, the prediction values of the two models were similar (The univariate model AUC was 0.867, 95% CI (0.834-0.9). The LASSO model AUC was 0.864, 95% CI (0.828-0.895)), and the model established by LASSO regression was more parsimonious. A web calculator was developed using the model established by LASSO.

Predictive model including 6 risk indicators can be used to predict the risk of persistent organ failure in patients with acute pancreatitis.

Severe acute pancreatitis (SAP) is a dangerous condition with a high mortality rate. Many studies have found an association between adipokines and the development of SAP, but the results are controversial. Therefore, we performed a meta-analysis of the association of inflammatory adipokines with SAP.

We screened PubMed, EMBASE, Web of Science and Cochrane Library for articles on adipokines and SAP published before July 20, 2023. The quality of the literature was assessed using QUADAS criteria. Standardized mean differences (SMD) with 95% confidence intervals (CI) were calculated to assess the combined effect. Subgroup analysis, sensitivity analysis and publication bias tests were also performed on the information obtained.

Fifteen eligible studies included 1332 patients with acute pancreatitis (AP). Pooled analysis showed that patients with SAP had significantly higher serum levels of resistin (SMD = 0.78, 95% CI:0.37 to 1.19, z = 3.75, P = 0.000). The difference in leptin and adiponectin levels between SAP and mild acute pancreatitis (MAP) patients were not significant (SMD = 0.30, 95% CI: -0.08 to 0.68, z = 1.53, P = 0.127 and SMD = 0.11, 95% CI: -0.17 to 0.40, z = 0.80, P = 0.425, respectively). In patients with SAP, visfatin levels were not significantly different from that in patients with MAP (SMD = 1.20, 95% CI: -0.48 to 2.88, z = 1.40, P = 0.162).

Elevated levels of resistin are associated with the development of SAP. Resistin may serve as biomarker for SAP and has promise as therapeutic target.

Scoring systems for severe acute pancreatitis (SAP) prediction should be used in conjunction with pre-test probability to establish post-test probability of SAP, but data of this kind are lacking.

To investigate the predictive value of commonly employed scoring systems and their usefulness in modifying the pre-test probability of SAP.

Following PRISMA statement and MOOSE checklists after PROSPERO registration, PubMed was searched from inception until September 2022. Retrospective, prospective, cross-sectional studies or clinical trials on patients with acute pancreatitis defined as Revised Atlanta Criteria, reporting rate of SAP and using at least one score among Bedside Index for Severity in Acute Pancreatitis (BISAP), Acute Physiology and Chronic Health Examination (APACHE)-II, RANSON, and Systemic Inflammatory Response Syndrome (SIRS) with their sensitivity and specificity were included. Random effects model meta-analyses were performed. Pre-test probability and likelihood ratio (LR) were combined to estimate post-test probability on Fagan nomograms. Pooled severity rate was used as pre-test probability of SAP and pooled sensitivity and specificity to calculate LR and generate post-test probability. A priori hypotheses for heterogeneity were developed and sensitivity analyses planned.

43 studies yielding 14,116 acute pancreatitis patients were included: 42 with BISAP, 30 with APACHE-II, 27 with Ranson, 8 with SIRS. Pooled pre-test probability of SAP ranged 16.6%-25.3%. The post-test probability of SAP with positive/negative score was 47%/6% for BISAP, 43%/5% for APACHE-II, 48%/5% for Ranson, 40%/12% for SIRS. In 18 studies comparing BISAP, APACHE-II, and Ranson in 6740 patients with pooled pre-test probability of SAP of 18.7%, post-test probability when scores were positive was 48% for BISAP, 46% for APACHE-II, 50% for Ranson. When scores were negative, post-test probability dropped to 7% for BISAP, 6% for Ranson, 5% for APACHE-II. Quality, design, and country of origin of the studies did not explain the observed high heterogeneity.

The most commonly used scoring systems to predict SAP perform poorly and do not aid in decision-making.

Acute pancreatitis (AP) is a potentially life-threatening inflammatory disease of the pancreas, with clinical management determined by the severity of the disease. Diagnosis, severity prediction, and prognosis assessment of AP typically involve the use of imaging technologies, such as computed tomography, magnetic resonance imaging, and ultrasound, and scoring systems, including Ranson, Acute Physiology and Chronic Health Evaluation II, and Bedside Index for Severity in AP scores. Computed tomography is considered the gold standard imaging modality for AP due to its high sensitivity and specificity, while magnetic resonance imaging and ultrasound can provide additional information on biliary obstruction and vascular complications. Scoring systems utilize clinical and laboratory parameters to classify AP patients into mild, moderate, or severe categories, guiding treatment decisions, such as intensive care unit admission, early enteral feeding, and antibiotic use. Despite the central role of imaging technologies and scoring systems in AP management, these methods have limitations in terms of accuracy, reproducibility, practicality and economics. Recent advancements of artificial intelligence (AI) provide new opportunities to enhance their performance by analyzing vast amounts of clinical and imaging data. AI algorithms can analyze large amounts of clinical and imaging data, identify scoring system patterns, and predict the clinical course of disease. AI-based models have shown promising results in predicting the severity and mortality of AP, but further validation and standardization are required before widespread clinical application. In addition, understanding the correlation between these three technologies will aid in developing new methods that can accurately, sensitively, and specifically be used in the diagnosis, severity prediction, and prognosis assessment of AP through complementary advantages.

Diabetes is a highly prevalent disease that was initially simplified into three major types: Type 1, type 2 and gestational diabetes. With the global rise in incidence of acute pancreatitis (AP), a lesser-known type of diabetes referred to as diabetes of the exocrine pancreas (DEP) is becoming more recognized. However, there is a poor understanding of the inherent relationship between diabetes and AP. There is established data about certain diseases affecting the exocrine function of the pancreas which can lead to diabetes. More specifically, there are well established guidelines for diagnosis and management of DEP caused be chronic pancreatitis. Conversely, the sequelae of AP leading to diabetes has limited recognition and data. The purpose of this review is to provide a comprehensive summary of the prevalence, epidemiology, pathophysiology and future research aims of AP-related diabetes. In addition, we propose a screening and diagnostic algorithm to aid clinicians in providing better care for their patients.

Fatty pancreas is associated with inflammatory and neoplastic pancreatic diseases. Magnetic resonance imaging (MRI) is the diagnostic modality of choice for measuring pancreatic fat. Measurements typically use regions of interest limited by sampling and variability. We have previously described an artificial intelligence (AI)-aided approach for whole pancreas fat estimation on computed tomography (CT). In this study, we aimed to assess the correlation between whole pancreas MRI proton-density fat fraction (MR-PDFF) and CT attenuation.

We identified patients without pancreatic disease who underwent both MRI and CT between January 1, 2015 and June 1, 2020. 158 paired MRI and CT scans were available for pancreas segmentation using an iteratively trained convolutional neural network (CNN) with manual correction. Boxplots were generated to visualize slice-by-slice variability in 2D-axial slice MR-PDFF. Correlation between whole pancreas MR-PDFF and age, BMI, hepatic fat and pancreas CT-Hounsfield Unit (CT-HU) was assessed.

Mean pancreatic MR-PDFF showed a strong inverse correlation (Spearman -0.755) with mean CT-HU. MR-PDFF was higher in males (25.22 vs 20.87; p = 0.0015) and in subjects with diabetes mellitus (25.95 vs 22.17; p = 0.0324), and was positively correlated with age and BMI. The pancreatic 2D-axial slice-to-slice MR-PDFF variability increased with increasing mean whole pancreas MR-PDFF (Spearman 0.51; p < 0.0001).

Our study demonstrates a strong inverse correlation between whole pancreas MR-PDFF and CT-HU, indicating that both imaging modalities can be used to assess pancreatic fat. 2D-axial pancreas MR-PDFF is variable across slices, underscoring the need for AI-aided whole-organ measurements for objective and reproducible estimation of pancreatic fat.

Acute pancreatitis (AP) is the third most common gastrointestinal disease resulting in hospital admission, with over 70% of AP admissions being mild cases. In the USA, it costs 2.5 billion dollars annually. The most common standard management of mild AP (MAP) still is hospital admission. Patients with MAP usually achieve complete recovery in less than a week and the severity predictor scales are reliable. The aim of this study will be to compare three different strategies for the management of MAP.

This is a randomised, controlled, three-arm multicentre trial. Patients with MAP will be randomly assigned to group A (outpatient), B (home care) or C (hospital admission). The primary endpoint of the trial will be the treatment failure rate of the outpatient/home care management for patients with MAP compared with that of hospitalised patients. The secondary endpoints will be pain relapse, diet intolerance, hospital readmission, hospital length of stay, need for intensive care unit admission, organ failure, complications, costs and patient satisfaction. The general feasibility, safety and quality checks required for high-quality evidence will be adhered to.

The study (version 3.0, 10/2022) has been approved by the Scientific and Research Ethics Committee of the 'Institut d'Investigació Sanitaria Pere Virgili-IISPV' (093/2022). This study will provide evidence as to whether outpatient/home care is similar to usual management of AP. The conclusions of this study will be published in an open-access journal.

ClinicalTrials.gov Registry (NCT05360797).

The ossification of the posterior longitudinal ligament (OPLL) in the cervical spine is commonly observed in degenerative changes of the cervical spine. Early detection of cervical OPLL and prevention of postoperative complications are of utmost importance. We gathered data from 775 patients who underwent cervical spine surgery at the First Affiliated Hospital of Guangxi Medical University, collecting a total of 84 variables. Among these patients, 144 had cervical OPLL, while 631 did not. They were randomly divided into a training cohort and a validation cohort. Multiple machine learning (ML) methods were employed to screen the variables and ultimately develop a diagnostic model. Subsequently, we compared the postoperative outcomes of patients with positive and negative cervical OPLL. Initially, we compared the advantages and disadvantages of various ML methods. Seven variables, namely Age, Gender, OPLL, AST, UA, BMI, and CHD, exhibited significant differences and were used to construct a diagnostic nomogram model. The area under the curve (AUC) values of this model in the training and validation groups were 0.76 and 0.728, respectively. Our findings revealed that 69.2% of patients who underwent cervical OPLL surgery eventually required elective anterior surgery, in contrast to 86.8% of patients who did not have cervical OPLL. Patients with cervical OPLL had significantly longer operation times and higher postoperative drainage volumes compared to those without cervical OPLL. Interestingly, preoperative cervical OPLL patients demonstrated significant increases in mean UA, age, and BMI. Furthermore, 27.1% of patients with cervical anterior longitudinal ligament ossification (OALL) also exhibited cervical OPLL, whereas this occurrence was only observed in 6.9% of patients without cervical OALL. We developed a diagnostic model for cervical OPLL using the ML method. Our findings indicate that patients with cervical OPLL are more likely to undergo posterior cervical surgery, and they exhibit elevated UA levels, higher BMI, and increased age. The prevalence of cervical anterior longitudinal ligament ossification was also significantly higher among patients with cervical OPLL.

Although there are several scoring systems currently used to predict the severity of acute pancreatitis, each of them has limitations. Determine the accuracy of a modified Ranson score in predicting disease severity and prognosis in patients with acute pancreatitis (AP).

AP patients admitted or transferred to our institution were allocated to a modeling group (n = 304) or a validation group (n = 192). A modified Ranson score was determined by excluding the fluid sequestration parameter and including the modified computed tomography severity index (CTSI). The diagnostic performance of the modified Ranson score was compared with the Ranson score, modified CTSI, and bedside index of severity in acute pancreatitis (BISAP) score in predicting disease severity, organ failure, pancreatic necrosis and pancreatic infection.

The modified Ranson score had significantly better accuracy that the Ranson score in predicting all four outcome measures in the modeling group and in the validation group (all p < 0.05). For the modeling group the modified Ranson score had the best accuracy for predicting disease severity and organ failure, and second-best accuracy for predicting pancreatic necrosis and pancreatic infection. For the verification group, it had the best accuracy for predicting organ failure, second-best accuracy for predicting disease severity and pancreatic necrosis, and third-best accuracy for predicting pancreatic infection.

The modified Ranson score provided better accuracy than the Ranson score in predicting disease severity, organ failure, pancreatic necrosis and pancreatic infection. Relative to the other scoring systems, the modified Ranson system was superior in predicting organ failure.

The burden of diabetic retinopathy (DR) is increasing, and the sensitive biomarkers of the disease were not enough. Studies have found that the metabolic profile, such as amino acid (AA) and acylcarnitine (AcylCN), in the early stages of DR patients might have changed, indicating the potential of metabolites to become new biomarkers. We are amid to construct a metabolite-based prediction model for DR risk. This study was conducted on type 2 diabetes (T2D) patients with or without DR. Logistic regression and extreme gradient boosting (XGBoost) prediction models were constructed using the traditional clinical features and the screening features, respectively. Assessing the predictive power of the models in terms of both discrimination and calibration, the optimal model was interpreted using the Shapley Additive exPlanations (SHAP) to quantify the effect of features on prediction. Finally, the XGBoost model incorporating AA and AcylCN variables had the best comprehensive evaluation (ROCAUC = 0.82, PRAUC = 0.44, Brier score = 0.09). C18 : 1OH lower than 0.04 μmol/L, C18 : 1 lower than 0.70 μmol/L, threonine higher than 27.0 μmol/L, and tyrosine lower than 36.0 μmol/L were associated with an increased risk of developing DR. Phenylalanine higher than 52.0 μmol/L was associated with a decreased risk of developing DR. In conclusion, our study mainly used AAs and AcylCNs to construct an interpretable XGBoost model to predict the risk of developing DR in T2D patients which is beneficial in identifying high-risk groups and preventing or delaying the onset of DR. In addition, our study proposed possible risk cut-off values for DR of C18 : 1OH, C18 : 1, threonine, tyrosine, and phenylalanine.

Non-alcoholic fatty liver disease (NAFLD) is a proven risk factor for acute pancreatitis (AP). However, NAFLD has recently been redefined as metabolic-associated fatty liver disease (MAFLD). In this post hoc analysis, we quantified the effect of MAFLD on the outcomes of AP.

We identified our patients from the multicentric, prospective International Acute Pancreatitis Registry of the Hungarian Pancreatic Study Group. Next, we compared AP patients with and without MAFLD and the individual components of MAFLD regarding in-hospital mortality and AP severity based on the revised Atlanta classification. Lastly, we calculated odds ratios (ORs) with 95% confidence intervals (CIs) using multivariate logistic regression analysis.

MAFLD had a high prevalence in AP, 39% (801/2053). MAFLD increased the odds of moderate-to-severe AP (OR = 1.43, CI: 1.09-1.89). However, the odds of in-hospital mortality (OR = 0.89, CI: 0.42-1.89) and severe AP (OR = 1.70, CI: 0.97-3.01) were not higher in the MAFLD group. Out of the three diagnostic criteria of MAFLD, the highest odds of severe AP was in the group based on metabolic risk abnormalities (OR = 2.68, CI: 1.39-5.09). In addition, the presence of one, two, and three diagnostic criteria dose-dependently increased the odds of moderate-to-severe AP (OR = 1.23, CI: 0.88-1.70, OR = 1.38, CI: 0.93-2.04, and OR = 3.04, CI: 1.63-5.70, respectively) and severe AP (OR = 1.13, CI: 0.54-2.27, OR = 2.08, CI: 0.97-4.35, and OR = 4.76, CI: 1.50-15.4, respectively). Furthermore, in patients with alcohol abuse and aged ≥60 years, the effect of MAFLD became insignificant.

MAFLD is associated with AP severity, which varies based on the components of its diagnostic criteria. Furthermore, MAFLD shows a dose-dependent effect on the outcomes of AP.

Predicting Post-Endoscopic Retrograde Cholangiopancreatography (ERCP) pancreatitis (PEP) risk can be determinant in reducing its incidence and managing patients appropriately, however studies conducted thus far have identified single-risk factors with standard statistical approaches and limited accuracy.

To build and evaluate performances of machine learning (ML) models to predict PEP probability and identify relevant features.

A proof-of-concept study was performed on ML application on an international, multicenter, prospective cohort of ERCP patients. Data were split in training and test set, models used were gradient boosting (GB) and logistic regression (LR). A 10-split random cross-validation (CV) was applied on the training set to optimize parameters to obtain the best mean Area Under Curve (AUC). The model was re-trained on the whole training set with the best parameters and applied on test set. Shapley-Additive-exPlanation (SHAP) approach was applied to break down the model and clarify features impact.

One thousand one hundred and fifty patients were included, 6.1% developed PEP. GB model outperformed LR with AUC in CV of 0.7 vs 0.585 (p-value=0.012). GB AUC in test was 0.671. Most relevant features for PEP prediction were: bilirubin, age, body mass index, procedure time, previous sphincterotomy, alcohol units/day, cannulation attempts, gender, gallstones, use of Ringer's solution and periprocedural NSAIDs.

In PEP prediction, GB significantly outperformed LR model and identified new clinical features relevant for the risk, most being pre-procedural.