EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Trend and predictive modeling of hypertension risk using multiyear community health surveillance data: Evidence from 2019 to 2021

Johannes B Ginting, Tri Suci, Chrismis N Ginting, Kristiawan Indriyanto

Journal of Family and Community Medicine · 2026-04 · 33 (2) · 137-144

DOI: 10.4103/jfcm.jfcm_26_26 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Family and Community Medicine, online erschienen am 25.04.2026. Verfasst von Johannes B Ginting und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department Master of Public Health, Faculty of Medicine, Dentistry and Health Sciences, Prima University, North Sumatra, Indonesia. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

Stichwörter der Autor:innen

Community health surveillancehypertension predictionmachine learningpopulation healthrisk stratification

Autor:innen und Institutionen

  • Department Master of Public Health, Faculty of Medicine, Dentistry and Health Sciences, Prima University, North Sumatra, Indonesia.
  • Department Master of Indonesia Language Education, Faculty of Teacher Teaching and Education, Prima University, North Sumatra, Indonesia.

Zitieren

APA

Ginting, J. B., Suci, T., Ginting, C. N., & Indriyanto, K. (2026). Trend and predictive modeling of hypertension risk using multiyear community health surveillance data: Evidence from 2019 to 2021. Journal of Family and Community Medicine, 33(2), 137-144. https://doi.org/10.4103/jfcm.jfcm_26_26

Vancouver

Ginting JB, Suci T, Ginting CN, Indriyanto K. Trend and predictive modeling of hypertension risk using multiyear community health surveillance data: Evidence from 2019 to 2021. Journal of Family and Community Medicine. 2026;33(2):137-144. doi:10.4103/jfcm.jfcm_26_26

BibTeX
@article{Ginting2026,
  author = {Ginting, Johannes B and Suci, Tri and Ginting, Chrismis N and Indriyanto, Kristiawan},
  title = {Trend and predictive modeling of hypertension risk using multiyear community health surveillance data: Evidence from 2019 to 2021},
  journal = {Journal of Family and Community Medicine},
  year = {2026},
  volume = {33},
  number = {2},
  pages = {137--144},
  doi = {10.4103/jfcm.jfcm_26_26}
}
Kostenlos starten →