Actionable absolute risk prediction of atherosclerotic cardiovascular disease based on the UK Biobank.

Cardiovascular diseases (CVDs) are the primary cause of all death globally. Timely and accurate identification of people at risk of developing an atherosclerotic CVD and its sequelae is a central pillar of preventive cardiology. One widely used approach is risk prediction models; however, currently available models consider only a limited set of risk factors and outcomes, yield no actionable advice to individuals based on their holistic medical state and lifestyle, are often not interpretable, were built with small cohort sizes or are based on lifestyle data from the 1960s, e.g. the Framingham model. The risk of developing atherosclerotic CVDs is heavily lifestyle dependent, potentially making many occurrences preventable. Providing actionable and accurate risk prediction tools to the public could assist in atherosclerotic CVD prevention. Accordingly, we developed a benchmarking pipeline to find the best set of data preprocessing and algorithms to predict absolute 10-year atherosclerotic CVD risk. Based on the data of 464,547 UK Biobank participants without atherosclerotic CVD at baseline, we used a comprehensive set of 203 consolidated risk factors associated with atherosclerosis and its sequelae (e.g. heart failure). Our two best performing absolute atherosclerotic risk prediction models provided higher performance, (AUROC: 0.7573, 95% CI: 0.755-0.7595) and (AUROC: 0.7544, 95% CI: 0.7522-0.7567), than Framingham (AUROC: 0.680, 95% CI: 0.6775-0.6824) and QRisk3 (AUROC: 0.725, 95% CI: 0.7226-0.7273). Using a subset of 25 risk factors identified with feature selection, our reduced model achieves similar performance (AUROC 0.7415, 95% CI: 0.7392-0.7438) while being less complex. Further, it is interpretable, actionable and highly generalizable. The model could be incorporated into clinical practice and might allow continuous personalized predictions with automated intervention suggestions.

Déclaration de conflit d'intérêts

This research was funded by Ada Health GmbH and has been conducted using the UK Biobank under application number 34802. All of the authors are or were employees of, contractors for, or hold equity in Ada Health GmbH. AK, AB, OB, HH, MJ, DN, BLS and SG are employees or company directors of Ada Health GmbH and some of the listed authors hold stock options in the company. Ada Health GmbH has received research grant funding from the Bill & Melinda Gates Foundation, Fondation Botnar, the Federal Ministry of Education and Research Germany, the Federal Ministry for Economic Affairs and Energy Germany and the European Union. PW is employed by Wicks Digital Health Ltd, which has received funding from Ada Health, AstraZeneca, Baillie Gifford, Biogen, Bold Health, Camoni, Compass Pathways, Coronna, EIT, Endava, Happify, HealthUnlocked, Inbeeo, Kheiron Medical, Lindus Health, Sano Genetics, Self Care Catalysts, The Learning Corp, The Wellcome Trust, THREAD Research, VeraSci, and Woebot. HH is the topic driver of the AI-based symptom assessment group of the WHO/ITU Focus Group on AI4H (Artificial Intelligence for Health) and SG is a member of the clinical evaluation topic group of the WHO/ITU Focus Group on AI4H. A related patent application is currently pending with the title “System and method for predicting the risk of a patient to develop an atherosclerotic cardiovascular disease” and application number EP21191089.8. This does not alter our adherence to PLOS ONE policies on sharing data and materials.