Machine-learning prediction of impaired outcome in diabetic patients undergoing non-cardiac surgery.

Background: Diabetic patients undergoing non-cardiac surgery are vulnerable to postoperative cardiovascular and cerebrovascular complications, yet risk stratification tools tailored to this population remain limited. This study aimed to develop interpretable machine-learning models for predicting impaired outcome in diabetic patients undergoing non-cardiac surgery. Methods: We conducted a retrospective cohort study using an the INSPiRE analytic dataset is institutionally governed, de-identified, and not publicly available and included 4,293 diabetic patients undergoing non-cardiac surgery. Patients were classified into a control group ( Results: Patients with impaired outcome were older, had lower body weight, higher ASA class, heavier cardiovascular comorbidity burden, and greater intraoperative hypotension exposure. Among the five models, AdaBoost showed the best discrimination with an AUC of 0.82 (95% CI, 0.78-0.86), specificity of 0.76, sensitivity of 0.72, and PPV of 0.69. LightGBM, XGBoost, and CatBoost also outperformed the sparse penalized baseline. Boruta and SHAP consistently highlighted prior ischemic stroke, prior myocardial infarction, preoperative creatinine, albumin, inflammatory markers, age, ASA class, heart-rate and systolic blood-pressure summaries, and BUN as major contributors to risk. Conclusion: Interpretable ensemble learning provided modest internal improvement in perioperative risk stratification in diabetic patients undergoing non-cardiac surgery. Impaired outcome appeared to be driven by the combined burden of established vascular disease, reduced renal and nutritional reserve, inflammatory activation, and intraoperative hemodynamic instability. Further calibration testing, external validation, and fully reproducible pipeline reporting are needed before clinical deployment.