Multi-horizon machine learning for population-level hypertension risk stratification in the UK Biobank

Naik, A, Olier, I ORCID: 0000-0002-5679-7501, Dawson, EA ORCID: 0000-0002-5958-267X, McDowell, G ORCID: 0000-0002-2880-5236, Lane, DA, Lip, GYH and Ortega-Martorell, S ORCID: 0000-0001-9927-3209 Multi-horizon machine learning for population-level hypertension risk stratification in the UK Biobank. European Heart Journal: Digital Health. ISSN 2634-3916 (Accepted)

Text Multi-horizon Hypertension Prediction.pdf - Accepted Version Access Restricted Available under License Creative Commons Attribution. Download (2MB)

Abstract

Hypertension is a major contributor to cardiovascular morbidity and mortality, yet identifying individuals at risk before clinical diagnosis remains challenging. Here, we present a multi-horizon machine learning framework designed to model incident hypertension risk across multiple clinically meaningful time windows using data from 246,286 participants in the UK Biobank. The framework systematically compares predictive performance across five horizons under severe class imbalance, enabling analysis of how discrimination, precision, and risk drivers evolve as outcome prevalence changes over time.
Seven classification algorithms were evaluated, including logistic regression, random forest, naïve Bayes, and four boosting-based ensemble methods. Ensemble boosting models consistently achieved the strongest performance, with average precision increasing from 0.04 for the ≤2-year horizon to 0.22 for the ≤10-year horizon, while ROC-AUC remained relatively stable (~0.75-0.79). To enhance interpretability, we integrate SHapley Additive exPlanations (SHAP) with generative topographic mapping (GTM), combining feature-level attribution with population-level visualisation of model predictions.
Together, this framework reveals consistent predictors of hypertension risk (including baseline blood pressure, age, body mass index, medication burden, and cardiometabolic multimorbidity) and illustrates how combinations of risk factors organise hypertension risk across time horizons. More broadly, our results demonstrate how multi-horizon modelling and complementary explainability approaches can provide deeper insight into evolving disease risk patterns in large biomedical cohorts, supporting more interpretable and scalable strategies for population-level cardiovascular prevention. Such approaches may enable earlier identification of high-risk individuals and inform targeted screening and preventive interventions in routine care settings.

Item Type:	Article
Uncontrolled Keywords:	Artificial Intelligence and Digital Technologies Research Institute (AIDT)
Subjects:	Q Science > QA Mathematics > QA76 Computer software R Medicine > RC Internal medicine > RC1200 Sports Medicine
Divisions:	Computer Science and Mathematics Pharmacy and Biomolecular Sciences Sport and Exercise Sciences
Publisher:	Oxford University Press
Date of acceptance:	15 July 2026
Date Deposited:	21 Jul 2026 14:13
Last Modified:	21 Jul 2026 14:13
URI:	https://researchonline.ljmu.ac.uk/id/eprint/29020

View Item