Objectives: The objective of this study was to develop machine learning models to predict health insurance claim costs among older adults in Indonesia. Methods: This study utilized secondary data from the Indonesian National Health Insurance program (Jaminan Kesehatan Nasional [JKN]) spanning 2017 to 2023. Three modeling techniques—linear regression, random forest, and XGBoost—were employed to predict individual claim costs. Model performance was assessed using the root mean square error (RMSE), coefficient of determination (R2), and mean absolute error (MAE). Additionally, variable importance analysis was conducted to identify key predictors. Results: XGBoost with 500 boosting rounds yielded the best performance, with an RMSE of 11 360 283, an R2 of 0.81, and an MAE of 4 485 917, outperforming both linear regression (RMSE, 13 710 035; R2=0.72) and random forest (RMSE, 12 434 238; R2=0.78). Notably, outpatient care was identified as the most consistent predictor across all models. Other significant predictors included length of stay (LOS), diagnosis type (International Classification of Diseases, 10th revision chapter), facility type, facility classification, and severity of illness, particularly for moderate cases. Although LOS and diagnosis type were important predictors, these findings should be interpreted in the context of Indonesia’s fixed Indonesian Case-Based Groups payment system. Conclusions XGBoost provides reliable predictions of claim costs among older adults, capturing clinical, utilization, and structural drivers. These findings can inform targeted interventions, improve chronic disease management, optimize the referral system, and support integration of predictive tools into JKN to enhance responsiveness and promote sustainable, equitable financing.

Background: Mental health disorders among older adults are an increasing global concern, with depression affecting up to 30% globally and even higher in developing countries. In Indonesia, despite high prevalence, little is known about how mental health services are utilized by older adults under the National Health Insurance (JKN) program. This study aims to examine patterns of mental health service utilization among older adults (aged ≥60 years) enrolled in the JKN program. Methods: We conducted a retrospective cohort study using the 2024 BPJS Kesehatan Mental Health Contextual Sample, which was based on stratified random sampling. The sample included 5,966 older adults who were alive by December 31, 2023, and had at least one mental health diagnosis (International Classification of Diseases 10th revision [ICD-10] F00–F99). JKN membership categories include formal workers (PPU), informal workers (PBPU), government-subsidized groups (PBI), and non-workers. Data analysis included descriptive statistics and generalized linear modeling to assess factors associated with service utilization. Results: Anxiety and neurotic disorders were the most common diagnoses (36.0%), followed by psychotic disorders (28.3%) and mood disorders (19.0%). The mean number of visits per person per year was 4.94±5.18. The PPU group had higher utilization than other participant groups, while those never married and those in higher ward classes had significantly lower utilization. Age was inversely associated with service use. No significant differences were observed by gender or divorce status. Conclusion These findings highlight the value of administrative claims data to monitor mental health service use in later life. Efforts to address disparities across sociodemographic groups could enhance equitable access to mental healthcare for older adults.

Objectives: This study investigated the determinants of undiagnosed hypertension among Indonesian adults. Methods: This study involved an analysis of secondary data from the 2014 Indonesia Family Life Survey (IFLS) on 5914 Indonesian adults (≥40 years). The determinant variables examined in this cross-sectional study were education level, monthly per capita expenditures (PCE), whether the participant experienced headaches in the morning, and other general health variables. The outcome variable was undiagnosed hypertension, which was defined as participants with hypertension who had not received a hypertension diagnosis from a health professional and had never been prescribed medication for treating hypertension. The data were analyzed using logistic regression. Results: A total of 3322 participants (56.2%) were found to have undiagnosed hypertension. The odds ratios (ORs) and 95% confidence intervals (CIs) of undiagnosed hypertension were significantly higher among those who completed primary school or lower (OR, 1.60; 95% CI, 1.29 to 1.98), had low monthly PCE (OR, 1.28; 95% CI, 1.13 to 1.43), did not report experiencing headaches in the morning (OR, 1.97; 95% CI, 1.76 to 2.21), and reported a general health status of healthy (OR, 2.05; 95% CI, 1.82 to 2.30) than those who had a higher education level, had high monthly PCE, experienced headaches in the morning, and were unhealthy. Conclusions Education level, monthly PCE, the experience of headaches in the morning, and general health status were associated with undiagnosed hypertension. The monitoring system for detecting undiagnosed hypertension cases must be strengthened. Health promotion is also necessary to reduce the prevalence of undiagnosed hypertension.