Development and validation of risk prediction model for recurrent cardiovascular events among Chinese: P-CARDIAC model

This study aimed to develop and validate a cardiovascular diseases (CVD) risk prediction model, Personalized CARdiovascular DIsease risk Assessment for Chinese (P-CARDIAC), for recurrent cardiovascular events using Machine-Learning technique. Three cohorts of Chinese patients with established CVD in Hong Kong were included; Hong Kong Island cohort as the derivation cohort, whilst the Kowloon and New Territories cohorts were validation cohorts. The 10-year CVD outcome was a composite of diagnostic or procedure codes for coronary heart disease, ischaemic or haemorrhagic stroke, peripheral artery disease, and revascularization. We estimated incidence of recurrent CVD events for each cohort with reference to the total person-years of each cohort. Multivariate imputation with chained equations (MICE) and XGBoost were applied for the model development. The comparison with TRS-2°P and SMART2 used the validation cohorts with 1000 bootstrap replicates. A total 48,799, 119,672 and 140,533 patients were included in the derivation and validation cohorts, respectively. A list of 125 risk variables were used to make predictions on CVD risk, of which, eight classes of medications were considered interactive drug use. Model performance in the derivation cohort showed satisfying discrimination and calibration with a C-statistic of 0·69. Internal validation showed good discrimination and calibration performance with C-statistic over 0·6. P-CARDIAC also showed better performance than TRS-2°P and SMART2. Compared to other risk scores, P-CARDIAC enables to identify unique patterns of Chinese patients with established CVD. We anticipate that P-CARDIAC can be applied in various settings to prevent recurrent CVD events, thus reducing the related healthcare burden. Condensed Abstract A CVD risk prediction model named Personalized CARdiovascular DIsease risk Assessment for Chinese (P-CARDIAC), for recurrent cardiovascular events among Chinese adults using Machine-Learning technique was newly developed. It predicted 10-year CVD outcome including a composite of diagnostic or procedure codes for coronary heart disease, ischaemic or haemorrhagic stroke, peripheral artery disease, and revascularization by incidence of recurrent CVD. Model showed satisfying discrimination and calibration with a C-statistic of 0·69. P-CARDIAC also showed better performance than existing risk scores, such as TRS-2°P and SMART2. P-CARDIAC could help predict recurrent CVD risk and reduce the healthcare burden.