{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T11:23:55Z","timestamp":1787657035498,"version":"build-2736575974"},"reference-count":56,"publisher":"BMJ","issue":"3","license":[{"start":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T00:00:00Z","timestamp":1787616000000},"content-version":"unspecified","delay-in-days":55,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"National Center for Advancing Translational Sciences, National Institutes of Health","award":["UL1TR002014"],"award-info":[{"award-number":["UL1TR002014"]}]},{"DOI":"10.13039\/100000062","name":"National Institute of Diabetes and Digestive and Kidney Diseases","doi-asserted-by":"crossref","award":["1K01DK140625-01"],"award-info":[{"award-number":["1K01DK140625-01"]}],"id":[{"id":"10.13039\/100000062","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["bmjph"],"accepted":{"date-parts":[[2026,8,5]]},"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>About one-quarter of patients with acute pancreatitis (AP) will develop diabetes mellitus (DM) within 3 years, but risk factors remain unclear. This study aims to determine whether machine learning models (ML) can be trained to accurately predict new-onset DM following AP and identify key clinical features using real-world data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective cohort study used de-identified data from the TriNetX federated electronic health records (EHR) network from 1 January 2017 to 11 March 2024. A total of 58\u2009746 patients with AP (International Classification of Diseases-10 code K85) and no prior diagnosis of DM were included. New-onset DM following AP was the main outcome of interest. Five ML models were trained across four prediction windows, including logistic regression (LR), eXtreme Gradient Boosting, Adaptive Boosting, Random Forest and support vector machine. Model performance was assessed using the area under the receiver operating characteristic curve (AUROC).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among the 58\u2009746 patients with AP (mean (SD) age, 50.2 (16.6) years), the LR model demonstrated the highest overall performance, with a mean accuracy of 0.72 (SD, 0.009) and an AUROC of 0.79 (SD, 0.009). Key clinical features across models included age, pancreatic necrosis, body weight, body mass index, systolic blood pressure, number of medical visits and prior AP laboratory values such as glucose, anion gap, blood urea nitrogen (BUN) and total protein.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>In this first real-world evidence study using EHR data, we have developed and demonstrated the feasibility of using ML to predict the new onset of DM after AP. Clinical features such as age, pancreatic necrosis, prior glucose, BUN and anion gap had the highest overall importance scores and may inform tailored prevention strategies.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjph-2025-004661","type":"journal-article","created":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T11:10:18Z","timestamp":1787656218000},"page":"e004661","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning models for predicting new-onset diabetes following acute pancreatitis using real-world data"],"prefix":"10.1136","volume":"4","clinical-trial-number":[{"clinical-trial-number":"nct05197920","registry":"10.18810\/clinical-trials-gov"}],"author":[{"given":"Djibril M","family":"Ba","sequence":"first","affiliation":[{"name":"Department of Public Health Sciences, Penn State College of Medicine, Hershey, Pennsylvania, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alireza","family":"Vafaei Sadr","sequence":"additional","affiliation":[{"name":"Department of Public Health Sciences, Penn State College of Medicine, Hershey, Pennsylvania, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6875-0025","authenticated-orcid":false,"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[{"name":"Johns Hopkins Bloomberg School of Public Health, Baltimore, Maryland, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Phil A.","family":"Hart","sequence":"additional","affiliation":[{"name":"Division of Gastroenterology, Hepatology, and Nutrition, College of Medicine, The Ohio State University Wexner Medical Center, Columbus, Ohio, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nazia","family":"Raja-Khan","sequence":"additional","affiliation":[{"name":"Department of Medicine, Penn State College of Medicine, Hershey, Pennsylvania, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruizhe","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Public Health, Imperial College London, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ayesha","family":"Siddiqui","sequence":"additional","affiliation":[{"name":"Department of Medicine, Penn State College of Medicine, Hershey, Pennsylvania, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tian","family":"Qiu","sequence":"additional","affiliation":[{"name":"Department of Public Health Sciences, Penn State College of Medicine, Hershey, Pennsylvania, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jennifer","family":"Maranki","sequence":"additional","affiliation":[{"name":"Department of Medicine, Penn State College of Medicine, Hershey, Pennsylvania, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vernon M.","family":"Chinchilli","sequence":"additional","affiliation":[{"name":"Department of Public Health Sciences, Penn State College of Medicine, Hershey, Pennsylvania, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vida","family":"Abedi","sequence":"additional","affiliation":[{"name":"Department of Public Health Sciences, Penn State College of Medicine, Hershey, Pennsylvania, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,8,25]]},"reference":[{"key":"2026082504101161000_4.3.e004661.1","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2024.02.052"},{"key":"2026082504101161000_4.3.e004661.2","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2018.08.063"},{"key":"2026082504101161000_4.3.e004661.3","doi-asserted-by":"publisher","DOI":"10.1097\/MPA.0b013e3180cac24b"},{"key":"2026082504101161000_4.3.e004661.4","doi-asserted-by":"crossref","first-page":"1000","DOI":"10.1053\/j.gastro.2024.12.029","article-title":"Burden and cost of gastrointestinal, liver, and pancreatic diseases in the United States: update 2024","volume":"168","author":"Peery","year":"2025","journal-title":"Gastroenterology"},{"key":"2026082504101161000_4.3.e004661.5","unstructured":"World Health Organization . Definition, diagnosis and classification of diabetes mellitus and its complications. Part 1: diagnosis and classification of diabetes mellitus. Geneva, 1999. Available: http:\/\/apps.who.int\/iris\/bitstream\/10665\/66040\/1\/WHO_NCD_NCS_99.2.pdf"},{"key":"2026082504101161000_4.3.e004661.6","doi-asserted-by":"publisher","DOI":"10.2337\/dc14-S081"},{"key":"2026082504101161000_4.3.e004661.7","doi-asserted-by":"crossref","first-page":"668","DOI":"10.1016\/S2468-1253(21)00019-4","article-title":"Diabetes following acute pancreatitis","volume":"6","author":"Hart","year":"2021","journal-title":"Lancet Gastroenterol Hepatol"},{"key":"2026082504101161000_4.3.e004661.8","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2019.00637"},{"key":"2026082504101161000_4.3.e004661.9","doi-asserted-by":"publisher","DOI":"10.1136\/gutjnl-2013-305062"},{"key":"2026082504101161000_4.3.e004661.10","doi-asserted-by":"publisher","DOI":"10.2337\/dc17-0542"},{"key":"2026082504101161000_4.3.e004661.11","doi-asserted-by":"publisher","DOI":"10.2337\/dc25-S004"},{"key":"2026082504101161000_4.3.e004661.12","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1016\/S2468-1253(16)30106-6","article-title":"Type 3c (pancreatogenic) diabetes mellitus secondary to chronic pancreatitis and pancreatic cancer","volume":"1","author":"Hart","year":"2016","journal-title":"Lancet Gastroenterol Hepatol"},{"key":"2026082504101161000_4.3.e004661.13","doi-asserted-by":"crossref","DOI":"10.3389\/fphys.2019.00328","article-title":"Aging and comorbidities in acute pancreatitis I: a meta-analysis and systematic review based on 194,702 patients","volume":"10","author":"M\u00e1rta","year":"2019","journal-title":"Front Physiol"},{"key":"2026082504101161000_4.3.e004661.14","doi-asserted-by":"publisher","DOI":"10.1001\/archinternmed.2008.601"},{"key":"2026082504101161000_4.3.e004661.15","doi-asserted-by":"publisher","DOI":"10.2337\/diacare.17.9.961"},{"key":"2026082504101161000_4.3.e004661.16","doi-asserted-by":"publisher","DOI":"10.1016\/j.mcna.2004.04.013"},{"key":"2026082504101161000_4.3.e004661.17","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1016\/j.trsl.2017.02.004","article-title":"Smoking and the risk of type 2 diabetes","volume":"184","author":"Maddatu","year":"2017","journal-title":"Transl Res"},{"key":"2026082504101161000_4.3.e004661.18","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2024.111806"},{"key":"2026082504101161000_4.3.e004661.19","doi-asserted-by":"crossref","DOI":"10.2337\/dc05-0338","article-title":"Metformin-induced pancreatitis: a possible adverse drug effect during acute renal failure","volume":"29","author":"Fimognari","year":"2006","journal-title":"Diabetes Care"},{"key":"2026082504101161000_4.3.e004661.20","doi-asserted-by":"publisher","DOI":"10.1097\/01.mcg.0000173929.60115.b4"},{"key":"2026082504101161000_4.3.e004661.21","doi-asserted-by":"publisher","DOI":"10.2337\/dc18-2195"},{"key":"2026082504101161000_4.3.e004661.22","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2023-077591","article-title":"Statins exposure and acute pancreatitis: a retrospective cohort study using a large national insurance database","volume":"13","author":"Ba","year":"2023","journal-title":"BMJ Open"},{"key":"2026082504101161000_4.3.e004661.23","doi-asserted-by":"crossref","DOI":"10.3389\/fmed.2023.1257222","article-title":"Risk factors for diabetes mellitus after acute pancreatitis: a systematic review and meta-analysis","volume":"10","author":"Zahariev","year":"2023","journal-title":"Front Med (Lausanne)"},{"key":"2026082504101161000_4.3.e004661.24","doi-asserted-by":"crossref","first-page":"900","DOI":"10.1016\/j.pan.2023.10.009","article-title":"Incident diabetes following acute pancreatitis in a multicenter prospective observational cohort","volume":"23","author":"Bejjani","year":"2023","journal-title":"Pancreatology"},{"key":"2026082504101161000_4.3.e004661.25","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1007\/s00535-020-01682-y","article-title":"Trajectories of glycaemia following acute pancreatitis: a prospective longitudinal cohort study with 24 months follow-up","volume":"55","author":"Bharmal","year":"2020","journal-title":"J Gastroenterol"},{"key":"2026082504101161000_4.3.e004661.26","doi-asserted-by":"crossref","first-page":"696","DOI":"10.1097\/MPA.0000000000001818","article-title":"Identification of a risk profile for new-onset diabetes after acute pancreatitis","volume":"50","author":"Firkins","year":"2021","journal-title":"Pancreas"},{"key":"2026082504101161000_4.3.e004661.27","doi-asserted-by":"crossref","DOI":"10.3389\/fcdhc.2023.1326239","article-title":"Association of pancreatitis with risk of diabetes: analysis of real-world data","volume":"4","author":"Ba","year":"2023","journal-title":"Front Clin Diabetes Healthc"},{"key":"2026082504101161000_4.3.e004661.28","doi-asserted-by":"crossref","DOI":"10.3390\/nu13041112","article-title":"Dietary fibre intake in type 2 and new-onset prediabetes\/diabetes after acute pancreatitis: a nested cross-sectional study","volume":"13","author":"Li","year":"2021","journal-title":"Nutrients"},{"key":"2026082504101161000_4.3.e004661.29","doi-asserted-by":"crossref","DOI":"10.3389\/fendo.2025.1704688","article-title":"Association between severe acute pancreatitis and new-onset diabetes: a propensity score-matched real-world study","volume":"16","author":"Ba","year":"2025","journal-title":"Front Endocrinol (Lausanne)"},{"key":"2026082504101161000_4.3.e004661.30","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":"Collins","year":"2024","journal-title":"BMJ"},{"key":"2026082504101161000_4.3.e004661.31","doi-asserted-by":"crossref","DOI":"10.1093\/jamiaopen\/ooad035","article-title":"A global federated real-world data and analytics platform for research","volume":"6","author":"Palchuk","year":"2023","journal-title":"JAMIA Open"},{"key":"2026082504101161000_4.3.e004661.32","doi-asserted-by":"crossref","first-page":"598","DOI":"10.1097\/MPA.0000000000002072","article-title":"Recruitment and retention strategies for the Diabetes RElated to Acute Pancreatitis and Its Mechanisms study: from the Type 1 Diabetes in Acute Pancreatitis Consortium","volume":"51","author":"Yazici","year":"2022","journal-title":"Pancreas"},{"key":"2026082504101161000_4.3.e004661.33","doi-asserted-by":"publisher","DOI":"10.15585\/mmwr.mm7102e2"},{"key":"2026082504101161000_4.3.e004661.34","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1016\/S2213-8587(22)00044-4","article-title":"Risks and burdens of incident diabetes in long COVID: a cohort study","volume":"10","author":"Xie","year":"2022","journal-title":"Lancet Diabetes Endocrinol"},{"key":"2026082504101161000_4.3.e004661.35","doi-asserted-by":"crossref","first-page":"782","DOI":"10.2337\/dc21-1686","article-title":"The incidence of diabetes among 2,808,106 veterans with and without recent SARS-CoV-2 infection","volume":"45","author":"Wander","year":"2022","journal-title":"Diabetes Care"},{"key":"2026082504101161000_4.3.e004661.36","doi-asserted-by":"publisher","DOI":"10.2337\/dc20-0063"},{"key":"2026082504101161000_4.3.e004661.37","doi-asserted-by":"crossref","first-page":"172","DOI":"10.4093\/dmj.2024.0826","article-title":"Prevalence, incidence, and metabolic characteristics of young adults with type 2 diabetes mellitus in South Korea (2010\u20132020)","volume":"49","author":"Kim","year":"2025","journal-title":"Diabetes Metab J"},{"key":"2026082504101161000_4.3.e004661.38","doi-asserted-by":"crossref","first-page":"105726","DOI":"10.1016\/j.ebiom.2025.105726","article-title":"Prediction of acute and chronic kidney diseases during the post-covid-19 pandemic with machine learning models: utilizing national electronic health records in the US","volume":"115","author":"Zhang","year":"2025","journal-title":"EBioMedicine"},{"key":"2026082504101161000_4.3.e004661.39","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-025-02276-5","article-title":"Flexible imputation toolkit for electronic health records","volume":"15","author":"Vafaei Sadr","year":"2025","journal-title":"Sci Rep"},{"key":"2026082504101161000_4.3.e004661.40","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-08328-6"},{"key":"2026082504101161000_4.3.e004661.41","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph18147526"},{"key":"2026082504101161000_4.3.e004661.42","doi-asserted-by":"crossref","first-page":"22","DOI":"10.3390\/ijerph192215027","article-title":"Machine learning models for data-driven prediction of diabetes by lifestyle type","volume":"19","author":"Qin","year":"2022","journal-title":"Int J Environ Res Public Health"},{"key":"2026082504101161000_4.3.e004661.43","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1049\/htl2.12039","article-title":"Diabetes prediction using machine learning and explainable AI techniques","volume":"10","author":"Tasin","year":"2023","journal-title":"Healthc Technol Lett"},{"key":"2026082504101161000_4.3.e004661.44","doi-asserted-by":"crossref","first-page":"6155","DOI":"10.3390\/s22166155","article-title":"Feasibility study of constructing a screening tool for adolescent diabetes detection applying machine learning methods","volume":"22","author":"Hu","year":"2022","journal-title":"Sensors"},{"key":"2026082504101161000_4.3.e004661.45","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2021.e07419","article-title":"Machine learning for prediction of diabetes risk in middle-aged Swedish people","volume":"7","author":"Lama","year":"2021","journal-title":"Heliyon"},{"key":"2026082504101161000_4.3.e004661.46","doi-asserted-by":"crossref","DOI":"10.5888\/pcd16.190109","article-title":"Building risk prediction models for type 2 diabetes using machine learning techniques","volume":"16","author":"Xie","year":"2019","journal-title":"Prev Chronic Dis"},{"key":"2026082504101161000_4.3.e004661.47","doi-asserted-by":"crossref","first-page":"4406","DOI":"10.1038\/s41598-020-61123-x","article-title":"Machine learning for characterizing risk of type 2 diabetes mellitus in a rural Chinese population: the Henan Rural Cohort Study","volume":"10","author":"Zhang","year":"2020","journal-title":"Sci Rep"},{"key":"2026082504101161000_4.3.e004661.48","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2016.09.014"},{"key":"2026082504101161000_4.3.e004661.49","article-title":"Classification performance of neural networks versus logistic regression models: evidence from healthcare practice","volume":"14","author":"Issitt","year":"2022","journal-title":"Cureus"},{"key":"2026082504101161000_4.3.e004661.50","doi-asserted-by":"crossref","first-page":"1286","DOI":"10.3390\/jcm10061286","article-title":"Prediction of long-term stroke recurrence using machine learning models","volume":"10","author":"Abedi","year":"2021","journal-title":"JCM"},{"key":"2026082504101161000_4.3.e004661.51","doi-asserted-by":"crossref","first-page":"568","DOI":"10.1097\/MPA.0000000000002079","article-title":"Rationale and design for the Diabetes RElated to Acute Pancreatitis and Its Mechanisms Study: a prospective cohort study from the Type 1 Diabetes in Acute Pancreatitis Consortium","volume":"51","author":"Hart","year":"2022","journal-title":"Pancreas"},{"key":"2026082504101161000_4.3.e004661.52","doi-asserted-by":"crossref","first-page":"586","DOI":"10.1097\/MPA.0000000000002080","article-title":"Design and rationale for the use of magnetic resonance imaging biomarkers to predict diabetes after acute pancreatitis in the Diabetes RElated to Acute Pancreatitis and Its Mechanisms Study","volume":"51","author":"Tirkes","year":"2022","journal-title":"Pancreas"},{"key":"2026082504101161000_4.3.e004661.53","doi-asserted-by":"crossref","DOI":"10.1186\/s12884-024-07049-y","article-title":"Predicting preterm birth using electronic medical records from multiple prenatal visits","volume":"24","author":"Huang","year":"2024","journal-title":"BMC Pregnancy Childbirth"},{"key":"2026082504101161000_4.3.e004661.54","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1016\/j.ajog.2023.06.017","article-title":"Identifying risk of stillbirth using machine learning","volume":"229","author":"Cersonsky","year":"2023","journal-title":"Am J Obstet Gynecol"},{"key":"2026082504101161000_4.3.e004661.55","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.108968","article-title":"Missing value estimation using clustering and deep learning within multiple imputation framework","volume":"249","author":"Samad","year":"2022","journal-title":"Knowl Based Syst"},{"key":"2026082504101161000_4.3.e004661.56","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2019.02.016"}],"container-title":["BMJ Public Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjph-2025-004661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T11:10:24Z","timestamp":1787656224000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjpublichealth.bmj.com\/lookup\/doi\/10.1136\/bmjph-2025-004661"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":56,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,8,25]]},"published-print":{"date-parts":[[2026,7]]}},"alternative-id":["10.1136\/bmjph-2025-004661"],"URL":"https:\/\/doi.org\/10.1136\/bmjph-2025-004661","relation":{},"ISSN":["2753-4294"],"issn-type":[{"value":"2753-4294","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}