{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T21:20:50Z","timestamp":1790284850569,"version":"4.1.0"},"reference-count":47,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Endocrinol."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Type 2 diabetes mellitus (T2DM) is a highly prevalent non-communicable chronic disease that substantially reduces life expectancy. Accurate estimation of all-cause mortality risk in T2DM patients is crucial for personalizing and optimizing treatment strategies.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>This study analyzed a cohort of 554 patients (aged 40\u201387 years) with diagnosed T2DM over a maximum follow-up period of 16.8 years, during which 202 patients (36%) died. Key survival-associated features were identified, and multiple machine learning (ML) models were trained and validated to predict all-cause mortality risk. To improve model interpretability, Shapley additive explanations (SHAP) was applied to the best-performing model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The extra survival trees (EST) model, incorporating ten key features, demonstrated the best predictive performance. The model achieved a C-statistic of 0.776, with the area under the receiver operating characteristic curve (AUC) values of 0.86, 0.80, 0.841, and 0.826 for 5-, 10-, 15-, and 16.8-year all-cause mortality predictions, respectively. The SHAP approach was employed to interpret the model\u2019s individual decision-making processes.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The developed model exhibited strong predictive performance for mortality risk assessment. Its clinically interpretable outputs enable potential bedside application, improving the identification of high-risk patients and supporting timely treatment optimization.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fendo.2025.1689312","type":"journal-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T04:14:20Z","timestamp":1760674460000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Explainable artificial intelligence model predicting the risk of all-cause mortality in patients with type 2 diabetes mellitus"],"prefix":"10.3389","volume":"16","author":[{"given":"Olga","family":"Vershinina","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacopo","family":"Sabbatinelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna Rita","family":"Bonfigli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dalila","family":"Colombaretti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angelica","family":"Giuliani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mikhail","family":"Krivonosov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arseniy","family":"Trukhanov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudio","family":"Franceschi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mikhail","family":"Ivanchenko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabiola","family":"Olivieri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2021.109119","article-title":"IDF Diabetes Atlas: Global, regional and country-level diabetes prevalence estimates for 2021 and projections for 2045","volume":"183","author":"Sun","year":"2022","journal-title":"Diabetes Res Clin Pract"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.2337\/dc10-S062","article-title":"Diagnosis and classification of diabetes mellitus","volume":"33","year":"2010","journal-title":"Diabetes Care"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1056\/NEJM199306103282306","article-title":"Long-term complications of diabetes mellitus","volume":"328","author":"Nathan","year":"1993","journal-title":"N Engl J Med"},{"key":"B4","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1177\/1474651413495703","article-title":"Mortality in type 2 diabetes mellitus: magnitude of the evidence from a systematic review and meta-analysis","volume":"13","author":"Nwaneri","year":"2013","journal-title":"Diabetes Vasc Dis"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.2337\/dc12-1513","article-title":"All-cause and cardiovascular mortality in middle-aged people with type 2 diabetes compared with people without diabetes in a large U.K. Primary care database","volume":"36","author":"Taylor","year":"2013","journal-title":"Diabetes Care"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2019.2696","article-title":"Association of diabetes with all-cause and cause-specific mortality in asia: A pooled analysis of more than 1 million participants","volume":"2","author":"Yang","year":"2019","journal-title":"JAMA Netw Open"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa0706245","article-title":"Effect of a multifactorial intervention on mortality in type 2 diabetes","volume":"358","author":"G\u00e6de","year":"2008","journal-title":"N Engl J Med"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.2337\/dc21-1512","article-title":"Association of a healthy lifestyle with all-cause and cause-specific mortality among individuals with type 2 diabetes: A prospective study in UK biobank","volume":"45","author":"Han","year":"2022","journal-title":"Diabetes Care"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1001\/archinte.168.5.451","article-title":"Development and validation of an all-cause mortality risk score in type 2 diabetesThe hong kong diabetes registry","volume":"168","author":"Yang","year":"2008","journal-title":"Arch Intern Med"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.2337\/dc08-1047","article-title":"Predicting 6-year mortality risk in patients with type 2 diabetes","volume":"31","author":"Wells","year":"2008","journal-title":"Diabetes Care"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.2337\/dc11-2281","article-title":"Predictors of mortality over 8 years in type 2 diabetic patients","volume":"35","author":"McEwen","year":"2012","journal-title":"Diabetes Care"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.2337\/dc12-1906","article-title":"Development and validation of a predicting model of all-cause mortality in patients with type 2 diabetes","volume":"36","author":"De Cosmo","year":"2013","journal-title":"Diabetes Care"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2015.02.015","article-title":"Development and validation of a predictive risk model for all-cause mortality in type 2 diabetes","volume":"108","author":"Robinson","year":"2015","journal-title":"Diabetes Res Clin Pract"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdiacomp.2017.01.017","article-title":"Prediction of five-year all-cause mortality in Chinese patients with type 2 diabetes mellitus \u2013 A population-based retrospective cohort study","volume":"31","author":"Wan","year":"2017","journal-title":"J Diabetes its Complications"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1111\/dom.14240","article-title":"Building clinical risk score systems for predicting the all-cause and expanded cardiovascular-specific mortality of patients with type 2 diabetes","volume":"23","author":"Liu","year":"2021","journal-title":"Diabetes Obes Metab"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.3390\/jcm10204779","article-title":"Developing a prediction model for 7-year and 10-year all-cause mortality risk in type 2 diabetes using a hospital-based prospective cohort study","volume":"10","author":"Chiu","year":"2021","journal-title":"JCM"},{"key":"B17","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1186\/s12933-022-01616-3","article-title":"Prognostic value of soluble ST2, high-sensitivity cardiac troponin, and NT-proBNP in type 2 diabetes: a 15-year retrospective study","volume":"21","author":"Sabbatinelli","year":"2022","journal-title":"Cardiovasc Diabetol"},{"key":"B18","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1111\/1753-0407.13343","article-title":"Developing a prediction model for all-cause mortality risk among patients with type 2 diabetes mellitus in Shanghai, China","volume":"15","author":"Qi","year":"2023","journal-title":"J Diabetes"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1136\/bmjdrc-2020-001950","article-title":"Development of a predictive risk model for all-cause mortality in patients with diabetes in Hong Kong","volume":"9","author":"Lee","year":"2021","journal-title":"BMJ Open Diabetes Res Care"},{"key":"B20","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1186\/s12902-021-00751-4","article-title":"Glycemic and lipid variability for predicting complications and mortality in diabetes mellitus using machine learning","volume":"21","author":"Lee","year":"2021","journal-title":"BMC Endocr Disord"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsx.2024.103135","article-title":"Machine learning and statistical models to predict all-cause mortality in type 2 diabetes: Results from the UK Biobank study","volume":"18","author":"Zhang","year":"2024","journal-title":"Diabetes Metab Syndrome: Clin Res Rev"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2870052","article-title":"Peeking inside the black-box: A survey on explainable artificial intelligence (XAI)","volume":"6","author":"Adadi","year":"2018","journal-title":"IEEE Access"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.107161","article-title":"Application of explainable artificial intelligence for healthcare: A systematic review of the last decade (2011\u20132022)","volume":"226","author":"Loh","year":"2022","journal-title":"Comput Methods Programs Biomedicine"},{"key":"B24","doi-asserted-by":"publisher","first-page":"8412","DOI":"10.1038\/s41598-023-35551-4","article-title":"Predicting 1-year mortality of patients with diabetes mellitus in Kazakhstan based on administrative health data using machine learning","volume":"13","author":"Alimbayev","year":"2023","journal-title":"Sci Rep"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.3390\/diabetology6010005","article-title":"All-cause mortality prediction in subjects with diabetes mellitus using a machine learning model and shapley values","volume":"6","author":"Mirea","year":"2025","journal-title":"Diabetology"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.18632\/oncotarget.10615","article-title":"Leukocyte telomere length and mortality risk in patients with type 2 diabetes","volume":"7","author":"Bonfigli","year":"2016","journal-title":"Oncotarget"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0119983","article-title":"N-glycomic changes in serum proteins in type 2 diabetes mellitus correlate with complications and with metabolic syndrome parameters","volume":"10","author":"Testa","year":"2015","journal-title":"PloS One"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1080\/08839514.2019.1637138","article-title":"Comparison of performance of data imputation methods for numeric dataset","volume":"33","author":"Jadhav","year":"2019","journal-title":"Appl Artif Intell"},{"key":"B29","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1186\/s12874-024-02173-x","article-title":"Comparison of the effects of imputation methods for missing data in predictive modelling of cohort study datasets","volume":"24","author":"Li","year":"2024","journal-title":"BMC Med Res Methodol"},{"key":"B30","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1038\/s41746-025-01958-8","article-title":"Comparison of SHAP and clinician friendly explanations reveals effects on clinical decision behaviour","volume":"8","author":"Hur","year":"2025","journal-title":"NPJ Digit Med"},{"key":"B31","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1001\/jamainternmed.2013.12956","article-title":"Rates of complications and mortality in older patients with diabetes mellitus: the diabetes and aging study","volume":"174","author":"Huang","year":"2014","journal-title":"JAMA Intern Med"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2019.107804","article-title":"The association between polypharmacy and adverse health consequences in elderly type 2 diabetes mellitus patients; a systematic review and meta-analysis","volume":"155","author":"AL-Musawe","year":"2019","journal-title":"Diabetes Res Clin Pract"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1016\/j.jamda.2016.07.013","article-title":"Frailty as a major factor in the increased risk of death and disability in older people with diabetes","volume":"17","author":"Castro-Rodr\u00edguez","year":"2016","journal-title":"J Am Med Directors Assoc"},{"key":"B34","first-page":"15","article-title":"Diabetes complications severity index and risk of mortality, hospitalization, and healthcare utilization","volume":"14","author":"Young","year":"2008","journal-title":"Am J Manag Care"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1046\/j.1365-2362.2002.01090.x","article-title":"Impact of diabetes duration and cardiovascular risk factors on mortality in type 2 diabetes: the Hoorn Study","volume":"32","author":"Spijkerman","year":"2002","journal-title":"Eur J Clin Invest"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.2337\/diacare.27.3.704","article-title":"The significant effect of diabetes duration on coronary heart disease mortality","volume":"27","author":"Fox","year":"2004","journal-title":"Diabetes Care"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1111\/dom.14081","article-title":"Prevalence of residual inflammatory risk and associated clinical variables in patients with type 2 diabetes","volume":"22","author":"Prattichizzo","year":"2020","journal-title":"Diabetes Obes Metab"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1016\/j.arr.2024.102253","article-title":"Organ-specific biological clocks: Ageotyping for personalized anti-aging medicine","volume":"96","author":"Prattichizzo","year":"2024","journal-title":"Ageing Res Rev"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.2337\/diacare.29.02.06.dc05-1700","article-title":"High-sensitivity C-reactive protein and coronary heart disease mortality in patients with type 2 diabetes","volume":"29","author":"Soinio","year":"2006","journal-title":"Diabetes Care"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1800256","article-title":"Risk factors, mortality, and cardiovascular outcomes in patients with type 2 diabetes","volume":"379","author":"Rawshani","year":"2018","journal-title":"N Engl J Med"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.18632\/aging.206136","article-title":"Integrating cardiovascular risk biomarkers in the context of inflammaging","volume":"16","author":"Sabbatinelli","year":"2024","journal-title":"Aging"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejim.2024.07.034","article-title":"Prevalence and clinical determinants of rapid eGFR decline among patients with newly diagnosed type 2 diabetes","volume":"130","author":"Russo","year":"2024","journal-title":"Eur J Internal Med"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1161\/CIR.0000000000000664","article-title":"Cardiorenal syndrome: classification, pathophysiology, diagnosis, and treatment strategies: A scientific statement from the american heart association","volume":"139","author":"Rangaswami","year":"2019","journal-title":"Circulation"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2023.1126718","article-title":"Red blood cell distribution width and all-cause mortality in congestive heart failure patients: a retrospective cohort study based on the Mimic-III database","volume":"10","author":"Ji","year":"2023","journal-title":"Front Cardiovasc Med"},{"key":"B45","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1186\/s12933-025-02671-2","article-title":"Triglyceride glucose index predicts long-term mortality and major adverse cardiovascular events in patients with type 2 diabetes","volume":"24","author":"Sbriscia","year":"2025","journal-title":"Cardiovasc Diabetol"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacl.2017.01.009","article-title":"Low levels of ApoA1 improve risk prediction of type 2 diabetes mellitus","volume":"11","author":"Wu","year":"2017","journal-title":"J Clin Lipidology"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1003853","article-title":"Long-term risk of a major cardiovascular event by apoB, apoA-1, and the apoB\/apoA-1 ratio\u2014Experience from the Swedish AMORIS cohort: A cohort study","volume":"18","author":"Walldius","year":"2021","journal-title":"PloS Med"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1689312\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T04:14:22Z","timestamp":1760674462000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1689312\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":47,"alternative-id":["10.3389\/fendo.2025.1689312"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2025.1689312","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,17]]},"article-number":"1689312"}}