BACKGROUND : Diabetes mellitus (DM) remains a major global health challenge, and its burden is intensified by comorbidities, such as obesity, hyperglycemia, and kidney dysfunction. Diverse geography and population, such as Indonesia, create unique provincial variations in DM risk factors, necessitating detailed sub-nationwide analyses to guide policymaking. This study aimed to evaluate regional disparities in diabetes-related mortality and associated risk factors across Indonesian provinces and to examine whether population density influences the distribution of these risk factors. METHODS : We analyzed age-standardized DM mortality and summary exposure values for 9 comorbidities across 34 provinces (GBD 2021), using Pearson's/Spearman's correlations nationally and provincially. Coefficient power was classified as weak (0.01–0.29), moderate (0.30–0.69), or strong (0.70–1.00). RESULTS : At the national scale, DM mortality was moderately associated with high BMI, high FPG, and kidney dysfunction (all R = 0.60; p<0.001). Associations were stronger in high-density provinces and negligible in low-density provinces. Across provinces, BMI and FPG were the most consistent correlates of DM mortality while diet-related factors (e.g., sugar intake) showed the largest gradient by density. CONCLUSIONS These findings support the development of tailored strategies based on population density to effectively reduce diabetes-related mortality. These results indicate that interventions in urban provinces should prioritize curbing sugar intake and reducing obesity prevalence. In intermediate-density regions, the focus should shift to the intensification of management for kidney disease and the optimization of blood pressure control. For low-density provinces, a critical approach involves expanding systematic screening programs and enhancing patient access to healthcare services.
comorbidity ; diabetes ; mortality ; Indonesia ; policy ; regional health planning

Objectives: The number of deaths from cardiovascular disease is projected to reach 23.3 million by 2030. As a contribution to preventing this phenomenon, this paper proposed a machine learning (ML) model to predict patients with arteriosclerotic heart disease (AHD). We also interpreted the prediction model results based on the ML approach and deployed modelagnostic ML methods to identify informative features and their interpretations. Methods: We used a hematology Electronic Health Record (EHR) with information on erythrocytes, hematocrit, hemoglobin, mean corpuscular hemoglobin, mean corpuscular hemoglobin concentration, leukocytes, thrombocytes, age, and sex. To detect and predict AHD, we explored random forest (RF), XGBoost, and AdaBoost models. We examined the prediction model results based on the confusion matrix and accuracy measures. We used the Shapley Additive exPlanations (SHAP) framework to interpret the ML model and quantify the contribution of features to predictions. Results: Our study included data from 6,837 patients, with 4,702 records from patients diagnosed with AHD and 2,135 records from patients without an AHD diagnosis. AdaBoost outperformed RF and XGBoost, achieving an accuracy of 0.78, precision of 0.82, F1-score of 0.85, and recall of 0.88. According to the SHAP summary bar plot method, hemoglobin was the most important attribute for detecting and predicting AHD patients. The SHAP local interpretability bar plot revealed that hemoglobin and mean corpuscular hemoglobin concentration had positive impacts on AHD prediction based on a single observation. Conclusions ML models based on real clinical data can be used to predict AHD.