Prediction of atrial fibrillation and stroke using machine learning models in UK Biobank

Areti Papadopoulou; Daniel Harding; Greg Slabaugh; Eirini Marouli; Panos Deloukas

doi:10.1016/j.heliyon.2024.e28034

Prediction of atrial fibrillation and stroke using machine learning models in UK Biobank

Heliyon. 2024 Mar 17;10(7):e28034. doi: 10.1016/j.heliyon.2024.e28034. eCollection 2024 Apr 15.

Authors

Areti Papadopoulou¹, Daniel Harding¹, Greg Slabaugh^{2

3}, Eirini Marouli^{1

3}, Panos Deloukas^{1

4}

Affiliations

¹ William Harvey Research Institute, Barts and the London School of Medicine and Dentistry, Queen Mary University of London, London, UK.
² School of Electronic Engineering and Computer Science, Queen Mary University of London, London, UK.
³ Digital Environment Research Institute, Queen Mary University of London, London, UK.
⁴ Princess Al-Jawhara Al-Brahim Centre of Excellence in Research of Hereditary Disorders (PACER-HD), King Abdulaziz University, Jeddah, Saudi Arabia.

Abstract

Objective: Atrial fibrillation (AF) is the most common cardiac arrythmia, and it is associated with increased risk for ischemic stroke, which is underestimated, as AF can be asymptomatic. The aim of this study was to develop optimal ML models for prediction of AF in the population, and secondly for ischemic stroke in AF patients.

Methods: To develop ML models for prediction of 1) AF in the general population and 2) ischemic stroke in patients with AF we constructed XGBoost, LightGBM, Random Forest, Deep Neural Network, Support Vector Machine and Lasso penalised logistic regression models using UK-Biobank's extensive real-world clinical data, questionnaires, as well as biochemical and genetic data, and their predictive performances were compared. Ranking and contribution of the different features was assessed by SHapley Additive exPlanations (SHAP) analysis. The clinical tool CHA₂DS₂-VASc for prediction of ischemic stroke among AF patients, was used for comparison to the best performing ML model.

Findings: The best performing model for AF prediction was LightGBM, with an area-under-the-roc-curve (AUROC) of 0.729 (95% confidence intervals (CI): 0.719, 0.738). The best performing model for ischemic stroke prediction in AF patients was XGBoost with AUROC of 0.631 (95% CI: 0.604, 0.657). The improved AUROC in the XGBoost model compared to CHA₂DS₂-VASc was statistically significant based on DeLong's test (p-value = 2.20E-06). In addition, the SHAP analysis showed that several peripheral blood biomarkers (e.g. creatinine, glycated haemoglobin, monocytes) were associated with ischemic stroke, which are not considered by CHA₂DS₂-VASc.

Implications: The best performing ML models presented have the potential for clinical use, but further validation in independent studies is required. Our results endorse the incorporation of some routinely measured blood biomarkers for ischemic stroke prediction in AF patients.