Machine‐Learning–Based Prediction of Hypertension and Its Risk Factors Among Adults in the Northern Region of Bangladesh

Hypertension (HTN) is a major contributor to cardiovascular morbidity and mortality globally. Its burden is rising in low- and middle-income countries like Bangladesh. Despite its rising prevalence, predictive modeling of HTN using advanced analytical approaches remains limited in rural populations. This study is aimed at predicting HTN and identifying its key risk factors among adults in Dinajpur District, Bangladesh, using machine-learning (ML) techniques. A community-based cross-sectional study was conducted among 1026 adults aged ≥ 30 years between December 2024 and February 2025. Data on sociodemographic, behavioral, and clinical characteristics were collected through a structured questionnaire. Feature selection was performed using recursive feature elimination (RFE), Boruta-based feature selection (BFS), and random forest (RF) methods. Five ML algorithms such as logistic regression, decision tree, RF, extreme gradient boosting, and light gradient boosting machine were trained and evaluated based on accuracy, precision, recall, F1 score, and area under the curve (AUC). SHAP (SHapley Additive exPlanations) analysis was employed to interpret model outputs. The prevalence of HTN among participants was 36.5%. The RF model achieved the highest predictive performance with 72% accuracy, 71% precision, 72% recall, 71% F1 score, and an AUC of 0.80. Thirteen significant predictors were identified, with age, body weight, sweets consumption, vigorous activity, education, family size, height, and family income emerging as the most influential determinants. These findings demonstrate the potential of ML models in predicting HTN and identifying modifiable risk factors. The results provide actionable insights to support early detection, targeted interventions, and effective resource allocation for HTN prevention and control in rural Bangladesh.