{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T18:06:14Z","timestamp":1790100374851,"version":"4.0.1"},"reference-count":37,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:00:00Z","timestamp":1790035200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2025M772297"],"award-info":[{"award-number":["2025M772297"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>Organ failure (OF) is the most important determinant of prognosis in acute pancreatitis (AP) and its duration defines disease severity. Early identification of individuals at high risk of developing OF is crucial. We aimed to develop machine-learning models, benchmarked against a feedforward multilayer-perceptron (MLP) neural network, to predict new-onset OF at admission using static admission-day variables. In this study, data were extracted from MIMIC-IV (development cohort) and a multicentre AP cohort from two Chinese tertiary teaching hospitals (evaluation cohort), which excluded mild AP and therefore comprised patients requiring ICU-level or high-dependency care. Features were selected with Boruta and LASSO. Five machine-learning models and one multilayer-perceptron benchmark were developed in MIMIC-IV and externally evaluated in the Xiangya cohort without updating. SHapley Additive exPlanations (SHAP) were used to visualize decision-making patterns and individual prediction interpretations. The best-performing model was deployed as an interactive, web-based tool. We found that in the discovery cohort, 341 (23.9%) of 1429 AP patients developed new-onset OF within 28 days of admission while 45 of 216 patients (20.8%) in the validation cohort developed OF. Boruta and LASSO algorithms identified six key predictors including blood urea nitrogen, platelets, triglyceride-glucose index, albumin, white blood cells, and partial thromboplastin time, which were used to construct the ML and MLP models. XGBoost gave the best discrimination on external evaluation (AUC 0.837, 95% CI 0.771\u20130.902). Logistic recalibration improved calibration, and the recalibrated XGBoost model was implemented as a web-based research prototype (Decent app). In conclusion, XGBoost predicted new-onset OF with good discrimination in a severity-enriched AP cohort, and SHAP made individual predictions interpretable. Model selection, threshold selection and recalibration all used the evaluation cohort, so the deployed model still requires an independent cohort. Prospective usability and clinical-impact studies are needed before clinical use.<\/jats:p>","DOI":"10.1371\/journal.pdig.0001735","type":"journal-article","created":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T17:30:03Z","timestamp":1790098203000},"page":"e0001735","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and external evaluation of an interpretable machine-learning model for early prediction of organ failure in higher-risk acute pancreatitis patients: A multicentre cohort study"],"prefix":"10.1371","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5622-7488","authenticated-orcid":true,"given":"Di","family":"Wu","sequence":"first","affiliation":[{"name":"First Affiliated Hospital with Nanjing Medical University","place":["Nanjing, Jiangsu, China"],"department":["Pancreas Center"]},{"name":"Central South University","place":["Changsha, Hunan, China"],"department":["Department of Geriatric Gastroenterology, Xiangya Hospital"]},{"name":"University of Liverpool","place":["Liverpool, United Kingdom"],"department":["Institute of Systems, Molecular and Integrative Biology"]},{"name":"Central South University","place":["Changsha, Hunan, China"],"department":["Emergency Department, the Third Xiangya Hospital"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhao","family":"Cai","sequence":"additional","affiliation":[{"name":"West China Centre of Excellence for Pancreatitis, Institute of Integrated Traditional Chinese and Western Medicine, West China-Liverpool Biomedical Research Centre","place":["Chengdu, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunmei","family":"Chen","sequence":"additional","affiliation":[{"name":"The Seventh Affiliated Hospital of Sun Yat-Sen University","place":["Shenzhen, Guangdong, China"],"department":["Pediatric Hematology Laboratory, Division of Hematology\/Oncology, Department of Pediatrics"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minting","family":"Chen","sequence":"additional","affiliation":[{"name":"Southern Medical University","place":["Guangzhou, Guangdong, China"],"department":["Department of Ophthalmology, Nanfang Hospital"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Lv","sequence":"additional","affiliation":[{"name":"The Affiliated Jiangning Hospital of Nanjing Medical University","place":["Nanjing, Jiangsu, China"],"department":["Department of Information Center"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yilin","family":"Huang","sequence":"additional","affiliation":[{"name":"Central South University","place":["Changsha, Hunan, China"],"department":["Department of Geriatric Gastroenterology, Xiangya Hospital"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8547-1730","authenticated-orcid":true,"given":"Anthony","family":"Evans","sequence":"additional","affiliation":[{"name":"University of Liverpool","place":["Liverpool, United Kingdom"],"department":["Computational Biology Facility"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan","family":"Lin","sequence":"additional","affiliation":[{"name":"University of Liverpool","place":["Liverpool, United Kingdom"],"department":["Institute of Systems, Molecular and Integrative Biology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diane","family":"Latawiec","sequence":"additional","affiliation":[{"name":"University of Liverpool","place":["Liverpool, United Kingdom"],"department":["Institute of Systems, Molecular and Integrative Biology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arjun","family":"Kattakayam","sequence":"additional","affiliation":[{"name":"University of Liverpool","place":["Liverpool, United Kingdom"],"department":["Institute of Systems, Molecular and Integrative Biology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajarshi","family":"Mukherjee","sequence":"additional","affiliation":[{"name":"University of Liverpool","place":["Liverpool, United Kingdom"],"department":["Institute of Systems, Molecular and Integrative Biology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Huang","sequence":"additional","affiliation":[{"name":"West China Centre of Excellence for Pancreatitis, Institute of Integrated Traditional Chinese and Western Medicine, West China-Liverpool Biomedical Research Centre","place":["Chengdu, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Xia","sequence":"additional","affiliation":[{"name":"West China Centre of Excellence for Pancreatitis, Institute of Integrated Traditional Chinese and Western Medicine, West China-Liverpool Biomedical Research Centre","place":["Chengdu, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Xiao","sequence":"additional","affiliation":[{"name":"Central South University","place":["Changsha, Hunan, China"],"department":["Emergency Department, the Third Xiangya Hospital"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunqiu","family":"Su","sequence":"additional","affiliation":[{"name":"First Affiliated Hospital with Nanjing Medical University, Nanjing Medical University","place":["Nanjing, Jiangsu, China"],"department":["Department of Radiology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Peng","sequence":"additional","affiliation":[{"name":"Central South University","place":["Changsha, Hunan, China"],"department":["Department of Geriatric Gastroenterology, Xiangya Hospital"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kuirong","family":"Jiang","sequence":"additional","affiliation":[{"name":"First Affiliated Hospital with Nanjing Medical University","place":["Nanjing, Jiangsu, China"],"department":["Pancreas Center"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Sutton","sequence":"additional","affiliation":[{"name":"University of Liverpool","place":["Liverpool, United Kingdom"],"department":["Institute of Systems, Molecular and Integrative Biology"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,22]]},"reference":[{"issue":"10252","key":"pdig.0001735.ref001","doi-asserted-by":"crossref","first-page":"726","DOI":"10.1016\/S0140-6736(20)31310-6","article-title":"Acute pancreatitis","volume":"396","author":"L Boxhoorn","year":"2020","journal-title":"Lancet"},{"issue":"7","key":"pdig.0001735.ref002","doi-asserted-by":"crossref","first-page":"2008","DOI":"10.1053\/j.gastro.2018.12.041","article-title":"Organ failure due to systemic injury in acute pancreatitis","volume":"156","author":"PK Garg","year":"2019","journal-title":"Gastroenterology"},{"issue":"6","key":"pdig.0001735.ref003","doi-asserted-by":"crossref","first-page":"875","DOI":"10.1097\/SLA.0b013e318256f778","article-title":"Determinant-based classification of acute pancreatitis severity: an international multidisciplinary consultation","volume":"256","author":"EP Dellinger","year":"2012","journal-title":"Ann Surg"},{"issue":"1","key":"pdig.0001735.ref004","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1136\/gutjnl-2012-302779","article-title":"Classification of acute pancreatitis--2012: revision of the Atlanta classification and definitions by international consensus","volume":"62","author":"PA Banks","year":"2013","journal-title":"Gut"},{"issue":"12","key":"pdig.0001735.ref005","doi-asserted-by":"crossref","first-page":"1251","DOI":"10.1007\/s40265-022-01766-4","article-title":"Acute pancreatitis: diagnosis and treatment","volume":"82","author":"P Szatmary","year":"2022","journal-title":"Drugs"},{"key":"pdig.0001735.ref006","article-title":"International Association of Pancreatology revised guidelines on acute pancreatitis 2025","author":"info@internationalpancreatology.org, I.A.E.I.J.W.G.E.a. and I.A.E.I.J.W. Group","year":"2025","journal-title":"Pancreatology"},{"issue":"11","key":"pdig.0001735.ref007","doi-asserted-by":"crossref","first-page":"1907","DOI":"10.1016\/j.hpb.2022.05.1347","article-title":"Predicting persistent organ failure on admission in patients with acute pancreatitis: development and validation of a mobile nomogram","volume":"24","author":"N Shi","year":"2022","journal-title":"HPB (Oxford)"},{"issue":"1","key":"pdig.0001735.ref008","doi-asserted-by":"crossref","first-page":"338","DOI":"10.3390\/ijms21010338","article-title":"Multifactorial scores and biomarkers of prognosis of acute pancreatitis: applications to research and practice","volume":"21","author":"P Silva-Vaz","year":"2020","journal-title":"Int J Mol Sci"},{"issue":"1","key":"pdig.0001735.ref009","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1186\/s12933-024-02538-y","article-title":"Exploring the prognostic impact of triglyceride-glucose index in critically ill patients with first-ever stroke: insights from traditional methods and machine learning-based mortality prediction","volume":"23","author":"Y Chen","year":"2024","journal-title":"Cardiovasc Diabetol"},{"issue":"1","key":"pdig.0001735.ref010","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1186\/s40560-025-00779-x","article-title":"Association between the triglyceride-glucose index and the risk of acute kidney injury in critically ill patients with acute pancreatitis: a retrospective study","volume":"13","author":"Z Wang","year":"2025","journal-title":"J Intensive Care"},{"issue":"1","key":"pdig.0001735.ref011","doi-asserted-by":"crossref","DOI":"10.1097\/MPA.0000000000002216","article-title":"Deep learning models for severity prediction of acute pancreatitis in the early phase from abdominal nonenhanced computed tomography images","volume":"52","author":"Z Chen","year":"2023","journal-title":"Pancreas"},{"issue":"10","key":"pdig.0001735.ref012","article-title":"Machine learning models for mortality prediction in critically ill patients with acute pancreatitis-associated acute kidney injury","volume":"17","author":"Y Liu","year":"2024","journal-title":"Clin Kidney J"},{"issue":"10","key":"pdig.0001735.ref013","article-title":"Illness severity assessment of older adults in critical illness using machine learning (ELDER-ICU): an international multicentre study with subgroup bias evaluation","volume":"5","author":"X Liu","year":"2023","journal-title":"Lancet Digit Health"},{"issue":"2","key":"pdig.0001735.ref014","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.1004432","article-title":"A systematic review of machine learning-based prognostic models for acute pancreatitis: towards improving methods and reporting quality","volume":"22","author":"B Critelli","year":"2025","journal-title":"PLoS Med"},{"issue":"1","key":"pdig.0001735.ref015","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1038\/s41591-024-03425-5","article-title":"The TRIPOD-LLM reporting guideline for studies using large language models","volume":"31","author":"J Gallifant","year":"2025","journal-title":"Nat Med"},{"issue":"1","key":"pdig.0001735.ref016","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1186\/s12916-025-03994-3","article-title":"The validation of prediction models deserves more recognition","volume":"23","author":"U Mansmann","year":"2025","journal-title":"BMC Med"},{"issue":"1","key":"pdig.0001735.ref017","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"AEW Johnson","year":"2023","journal-title":"Sci Data"},{"key":"pdig.0001735.ref018","doi-asserted-by":"crossref","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"GS Collins","year":"2024","journal-title":"BMJ"},{"issue":"12","key":"pdig.0001735.ref019","doi-asserted-by":"crossref","first-page":"2685","DOI":"10.1177\/09622802211047346","article-title":"Multiple imputation with missing data indicators","volume":"30","author":"LJ Beesley","year":"2021","journal-title":"Stat Methods Med Res"},{"issue":"6","key":"pdig.0001735.ref020","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1177\/0272989X06295361","article-title":"Decision curve analysis: a novel method for evaluating prediction models","volume":"26","author":"AJ Vickers","year":"2006","journal-title":"Med Decis Making"},{"issue":"10","key":"pdig.0001735.ref021","doi-asserted-by":"crossref","first-page":"2221","DOI":"10.1093\/humrep\/deae181","article-title":"A nomogram and risk stratification to predict subsequent pregnancy loss in patients with recurrent pregnancy loss","volume":"39","author":"M Li","year":"2024","journal-title":"Hum Reprod"},{"issue":"9","key":"pdig.0001735.ref022","doi-asserted-by":"crossref","first-page":"1025","DOI":"10.1016\/j.jclinepi.2014.05.003","article-title":"The Hospital-patient One-year Mortality Risk score accurately predicted long-term death risk in hospitalized patients","volume":"67","author":"C van Walraven","year":"2014","journal-title":"J Clin Epidemiol"},{"issue":"1","key":"pdig.0001735.ref023","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1186\/s12874-025-02473-w","article-title":"Artificial intelligence methods applied to longitudinal data from electronic health records for prediction of cancer: a scoping review","volume":"25","author":"V Moglia","year":"2025","journal-title":"BMC Med Res Methodol"},{"key":"pdig.0001735.ref024","unstructured":"Kuhn M. Tidymodels: a collection of packages for modeling and machine learning using tidyverse principles. 2020."},{"key":"pdig.0001735.ref025","doi-asserted-by":"crossref","unstructured":"Grinsztajn L, Oyallon E, Varoquaux G. Why do tree-based models still outperform deep learning on typical tabular data? Proceedings of the 36th International Conference on Neural Information Processing Systems. New Orleans, LA, USA: Curran Associates Inc.; 2022. Article 37 p.","DOI":"10.52202\/068431-0037"},{"issue":"6","key":"pdig.0001735.ref026","article-title":"EASY-APP: an artificial intelligence model and application for early and easy prediction of severity in acute pancreatitis","volume":"12","author":"B Kui","year":"2022","journal-title":"Clin Transl Med"},{"issue":"5","key":"pdig.0001735.ref027","doi-asserted-by":"crossref","DOI":"10.14309\/ctg.0000000000000351","article-title":"A novel 5-cytokine panel outperforms conventional predictive markers of persistent organ failure in acute pancreatitis","volume":"12","author":"C Langmead","year":"2021","journal-title":"Clin Transl Gastroenterol"},{"issue":"1","key":"pdig.0001735.ref028","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.pan.2021.10.003","article-title":"Early prediction of severe acute pancreatitis using machine learning","volume":"22","author":"R Thapa","year":"2022","journal-title":"Pancreatology"},{"issue":"1","key":"pdig.0001735.ref029","doi-asserted-by":"crossref","first-page":"4039","DOI":"10.1038\/s41467-023-39631-x","article-title":"Opportunistic detection of type 2 diabetes using deep learning from frontal chest radiographs","volume":"14","author":"A Pyrros","year":"2023","journal-title":"Nat Commun"},{"key":"pdig.0001735.ref030","article-title":"Artificial intelligence and global health equity","volume":"387","author":"RG Dychiao","year":"2024","journal-title":"BMJ"},{"issue":"3","key":"pdig.0001735.ref031","doi-asserted-by":"crossref","first-page":"1665","DOI":"10.1007\/s40121-021-00489-5","article-title":"Predictors of mortality and drug resistance among carbapenem-resistant enterobacteriaceae-infected pancreatic necrosis patients","volume":"10","author":"D Wu","year":"2021","journal-title":"Infect Dis Ther"},{"issue":"8","key":"pdig.0001735.ref032","doi-asserted-by":"crossref","first-page":"1587","DOI":"10.1016\/j.pan.2020.09.018","article-title":"Triglyceride and glucose (TyG) index is an effective biomarker to identify severe acute pancreatitis","volume":"20","author":"JM Park","year":"2020","journal-title":"Pancreatology"},{"issue":"1","key":"pdig.0001735.ref033","doi-asserted-by":"crossref","DOI":"10.1053\/j.gastro.2019.09.040","article-title":"NLRP3 inflammasome regulates development of systemic inflammatory response and compensatory anti-inflammatory response syndromes in mice with acute pancreatitis","volume":"158","author":"M Sendler","year":"2020","journal-title":"Gastroenterology"},{"issue":"1","key":"pdig.0001735.ref034","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1186\/s12902-023-01414-2","article-title":"Association between time in range 70-180 mg\/dl in early stage and severity with in patients acute pancreatitis","volume":"23","author":"C Meng","year":"2023","journal-title":"BMC Endocr Disord"},{"issue":"6","key":"pdig.0001735.ref035","doi-asserted-by":"crossref","first-page":"1158","DOI":"10.14309\/ajg.0000000000002792","article-title":"Associations of intrapancreatic fat deposition with incident diseases of the exocrine and endocrine pancreas: a UK biobank prospective cohort study","volume":"119","author":"X Dong","year":"2024","journal-title":"Am J Gastroenterol"},{"key":"pdig.0001735.ref036","doi-asserted-by":"crossref","first-page":"151451","DOI":"10.1016\/j.bbrc.2025.151451","article-title":"Multi-omics profiles reveal immune microenvironment alterations associated with PD-L1 checkpoint in acute pancreatitis in the early phase","volume":"751","author":"D Wu","year":"2025","journal-title":"Biochem Biophys Res Commun"},{"issue":"1","key":"pdig.0001735.ref037","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1186\/s12879-023-08230-y","article-title":"The impact of multi-drug resistant Pseudomonas aeruginosa infections on acute pancreatitis patients","volume":"23","author":"D Wu","year":"2023","journal-title":"BMC Infect Dis"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001735","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T17:30:14Z","timestamp":1790098214000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001735"}},"subtitle":[],"editor":[{"given":"Zhichao","family":"Zuo","sequence":"first","affiliation":[{"name":"Xiangtan Central Hospital","place":["CHINA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,22]]},"references-count":37,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,22]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0001735","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,22]]}}}