Key result
XGBoost predicts hypertension risk with ~78% accuracy using age, BMI, waist circumference, and male sex.
Why the study?
Hypertension frequently remains undetected until complications arise, and evidence in Indonesia integrating multiyear surveillance data with machine learning to predict population-level risk is limited.
Can machine learning models accurately predict population-level risk of abnormal blood pressure in Indonesian adults?
Observational (n=196,951)
Can machine learning models accurately predict population-level risk of abnormal blood pressure in Indonesian adults?
Effect estimate: AUC 0.736
Machine learning models, particularly XGBoost, can effectively predict population-level hypertension risk using community health surveillance data.
Should not yet change community BP screening; leaves open ML utility for population hypertension risk prediction pending validation.
BACKGROUND: Hypertension remains a major global health burden, often undetected until complications occur. In Indonesia, evidence integrating multiyear surveillance data with machine learning (ML) to predict population-level risk remains limited. The objective of the study was to examine temporal trends in hypertension risk and develop predictive models at the population level. MATERIALS AND METHODS: This observational study utilized community health surveillance data on 196,951 adults (2019–2021). Blood pressure was classified using World Health Organization/Joint National Committee 7 criteria, with prehypertension and hypertension combined as abnormal ( y = 1). Predictors included sociodemographic characteristics, anthropometric measurements, various health behaviors, and comorbidities. Missing values were imputed using K-Nearest Neighbors. Logistic Regression, Random Forest, Gradient Boosting, eXtreme Gradient Boosting (XGBoost), and Support Vector Machine models were developed using an 80:20 split, 10-fold cross-validation, and hyperparameter tuning. Model interpretability was assessed using SHapley Additive exPlanations (SHAP). RESULTS: Abnormal blood pressure prevalence increased from 74.4% (2019) to 79.7% (2020) and 80.2% (2021). XGBoost demonstrated superior performance, achieving 78.3% accuracy and an area under the curve of 0.736, outperforming other models. SHAP analysis identified age, waist circumference, body mass index, and male sex as the strongest predictors of the risk of hypertension. CONCLUSION: Hypertension risk in Indonesia rose from 2019 to 2021. Interpretable ML models, particularly XGBoost, show potential for population-level risk stratification and early detection in community and primary healthcare settings.
No takes yet. Share an insight, caveat, or question.
Ginting et al. (2026) conducted an observational in Hypertension (n=196,951). Machine learning predictive models (XGBoost) vs. Other machine learning models (Logistic Regression, Random Forest, Gradient Boosting, SVM) was evaluated on Model accuracy and area under the curve (AUC) for predicting abnormal blood pressure (AUC 0.736). An XGBoost machine learning model predicted hypertension risk with 78.3% accuracy and an AUC of 0.736, identifying age, waist circumference, BMI, and male sex as the strongest predictors.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: