Incorporating behavioural and psychological factors into cardiovascular disease risk prediction models: protocol for a systematic review.

Abstract

This systematic review aims to: (1) evaluate how behavioural and psychological factors have been incorporated into cardiovascular disease (CVD) risk prediction models; (2) assess their impact on model performance metrics such as area under the curve (AUC) and net reclassification index (NRI); and (3) identify which specific variables are most consistently associated with predictive improvements. This protocol is reported in accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses protocols (PRISMA-P) 2015, and the systematic review will follow the Cochrane Handbook and report findings based on PRISMA 2020. A systematic review protocol developed in accordance with the (PRISMA-P) 2015 guidelines. Systematic searches will be carried out in PubMed, Scopus, Web of Science and Google Scholar, limited to studies published from 2019 to 2024. Peer-reviewed original studies involving adult populations (≥18 years) at risk of CVD, incorporating at least one behavioural or psychological variable into a CVD risk prediction model. Studies must report model performance metrics such as AUC or NRI. Studies focusing solely on biochemical or demographic factors, paediatric populations, or non-CVD outcomes will be excluded. Two independent reviewers will screen eligible studies, extract data and assess study quality using the Newcastle-Ottawa Scale and Quality in Prognostic Studies tool. A narrative synthesis will be performed, with meta-analysis conducted if feasible. Ethical approval is not required for this study. Findings will be disseminated through peer-reviewed publication and conference presentations. CRD420251014218.