An Interpretable Machine Learning Framework Integrating Multi-Window Environmental Exposure for Hypertension Risk Assessment.
- 1Department of Chemistry and Chemical Engineering, Jinzhong University, Jinzhong 030619, China.
- 2School of Physical Education, Shanxi University, Taiyuan 030006, China.
Abstract
Machine learning (ML) models for hypertension risk prediction have predominantly relied on traditional demographic and clinical risk factors, often overlooking the temporal heterogeneity of environmental exposures. This study developed and validated an interpretable ML framework that systematically integrates multi-window cumulative PM2.5 exposure features for hypertension risk assessment. We designed a modular analytical pipeline comprising five ML algorithms-Generalized Linear Model (GLM), Lasso regression, Decision Tree, Random Forest (RF), and XGBoost-coupled with a three-layer interpretability module (variable importance, SHAP values, and partial dependence plots). The framework ingests traditional risk factors alongside cumulative PM2.5 exposure across five temporal windows (0-day, 7-day, 15-day, 30-day, and 60-day). As a validation case, the framework was applied to 2523 participant-visits from the Beijing subsample of the China Health and Nutrition Survey. Analyses were performed at the participant level, systolic and diastolic blood pressure were excluded from the predictors of the hypertension classifiers, and models were validated with person-level and year-based splits. After these corrections the five models showed realistic discrimination, with test AUCs of 0.69-0.77 and Brier scores of 0.17-0.23. Age, body mass index (BMI) and waist circumference were consistently among the most important predictors, and the 60-day PM2.5 window was the most important exposure feature. Adding the five PM2.5 window features improved test AUC by ≈0.02-0.03 in the ensemble models (p = 0.03-0.05). Window-specific adjusted analyses showed inverse associations of PM2.5 with hypertension that were stronger for longer windows. The proposed framework provides a reusable interpretable approach for incorporating multi-window environmental exposure data into cardiovascular risk prediction. Its modular design enables adaptation to other environmental exposures, health outcomes, and population cohorts, supporting both risk screening and personalized intervention strategies.
Related
- Identifying a Cardio‐Hepatic Phenotype by Integrating the Albumin‐Bilirubin Score Into Risk Assessment in Pulmonary Arterial Hypertension
- Integrating climate change adaptation into hypertension care: an evidence based framework for climate resilient primary healthcare and public health planning in Limpopo Province, South Africa
- X-Admix: An Interpretable Multimodal Cross-Attention Framework for Integrating Genotype, Local Ancestry, and Social Drivers of Health in Admixed African American Populations
- Construction of a Standardized Time-Lapse Imaging Database and a Gradient Boosting Ensemble Framework for Integrating Zygote Morphokinetic Parameters with Conventional Embryo Assessment
- Interpretable Machine Learning for Predicting Early Onset Hypertension in the US.
BibTeX
@article{zhao2026interpretable,
title = {{An Interpretable Machine Learning Framework Integrating Multi-Window Environmental Exposure for Hypertension Risk Assessment.}},
author = {Ying Zhao and Kexin Yuan},
journal = {Toxics},
year = {2026},
month = sep,
doi = {10.3390/toxics14100871},
url = {https://europepmc.org/article/MED/42931658},
note = {CC BY},
}
RIS
TY - JOUR
TI - An Interpretable Machine Learning Framework Integrating Multi-Window Environmental Exposure for Hypertension Risk Assessment.
AU - Ying Zhao
AU - Kexin Yuan
PY - 2026
DA - 2026/09/30
JO - Toxics
DO - 10.3390/toxics14100871
UR - https://europepmc.org/article/MED/42931658
AB - Machine learning (ML) models for hypertension risk prediction have predominantly relied on traditional demographic and clinical risk factors, often overlooking the temporal heterogeneity of environmental exposures. This study developed and validated an interpretable ML framework that systematically integrates multi-window cumulative PM2.5 exposure features for hypertension risk assessment. We designed a modular analytical pipeline comprising five ML algorithms-Generalized Linear Model (GLM), Lasso regression, Decision Tree, Random Forest (RF), and XGBoost-coupled with a three-layer interpretability module (variable importance, SHAP values, and partial dependence plots). The framework ingests traditional risk factors alongside cumulative PM2.5 exposure across five temporal windows (0-day, 7-day, 15-day, 30-day, and 60-day). As a validation case, the framework was applied to 2523 participant-visits from the Beijing subsample of the China Health and Nutrition Survey. Analyses were performed at the participant level, systolic and diastolic blood pressure were excluded from the predictors of the hypertension classifiers, and models were validated with person-level and year-based splits. After these corrections the five models showed realistic discrimination, with test AUCs of 0.69-0.77 and Brier scores of 0.17-0.23. Age, body mass index (BMI) and waist circumference were consistently among the most important predictors, and the 60-day PM2.5 window was the most important exposure feature. Adding the five PM2.5 window features improved test AUC by ≈0.02-0.03 in the ensemble models (p = 0.03-0.05). Window-specific adjusted analyses showed inverse associations of PM2.5 with hypertension that were stronger for longer windows. The proposed framework provides a reusable interpretable approach for incorporating multi-window environmental exposure data into cardiovascular risk prediction. Its modular design enables adaptation to other environmental exposures, health outcomes, and population cohorts, supporting both risk screening and personalized intervention strategies.
SN - 2305-6304
ER -