Explainable artificial intelligence model predicting the risk of all-cause mortality in patients with type 2 diabetes mellitus

Olga Vershinina^1*Jacopo Sabbatinelli^2,3*Anna Rita Bonfigli³Dalila Colombaretti⁴Angelica Giuliani⁴Mikhail Krivonosov¹Arseniy Trukhanov⁵Claudio Franceschi¹Mikhail Ivanchenko¹Fabiola Olivieri^3,4

• ¹Nacional'nyj issledovatel'skij Nizegorodskij gosudarstvennyj universitet imeni N I Lobacevskogo, Nizhny Novgorod, Russia
• ²Department of Clinical and Molecular Sciences, Università Politecnica delle Marche, Ancona, Italy
• ³INRCA-IRCCS, Ancona, Italy
• ⁴Universita Politecnica delle Marche Dipartimento di Scienze Cliniche e Molecolari, Ancona, Italy
• ⁵Mriya Life Institute, National Academy of Active Longevity, Moscow, Russia

Background: 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. Methods: This study analyzed a cohort of 554 patients (aged 40-87 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. Results: 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's individual decision-making processes. Conclusion: The developed model exhibited strong predictive performance for mortality risk This is a provisional file, not the final typeset article assessment. Its clinically interpretable outputs enable potential bedside application, improving the identification of high-risk patients and supporting timely treatment optimization.