Development and validation of an ECG-based 10-year risk prediction model for Major Adverse Cardiac and Cerebrovascular Events in UK Biobank

BackgroundElectrocardiograms (ECG) are commonly used to diagnose heart conditions, but whether they add to traditional risk factors in predicting cardiovascular disease (CVD) is currently unclear. We investigated whether ECG measurements, taken at rest, exercise, and recovery, improve the prediction of major cardiovascular and cerebrovascular events (MACCE) both independently and when added to a clinical risk model derived from QRISK3 risk factors currently used in UK primary care. MethodsWe obtained ECG recordings from 41,076 UK Biobank participants without a history of MACCE who underwent a submaximal cycle ergometry test. We developed two ECG risk scores: one derived from conventional ECG parameters, measured at rest, peak exercise and recovery (C-ECG), and a neural-network risk model based on raw ECG recordings (ECGAI). We estimated the association between ECG scores and incident MACCE, using Cox proportional hazards models adjusted for traditional risk factors. Incremental predictive value was assessed relative to a newly derived Cox clinical risk score, constructed by refitting Cox models using the QRISK3 risk factors. All models were internally validated using five-fold cross-validation and 1,000 bootstrap iterations. Predictive performance was evaluated using Harrells C-index and net benefit. FindingsIncident MACCE was reported in 4,082 (9.9%) individuals, 3,463 (9.7%) of whom had valid ECG parameters and a median follow-up of 12.5 years. C-ECG and ECGAI scores were independently associated with MACCE, with hazard ratios of 1.76 (95% CI: 1.63-1.91) and 1.18 (95% CI: 1.15-1.21) per SD increase, respectively. When added to the Cox clinical risk score, both C-ECG and ECGAI scores modestly improved model discrimination, {Delta}C-index 0.03 (95% CI: 0.02-0.04) and {Delta}C-index 0.03 (95% CI: 0.02-0.03), respectively. ECGAI risk scores were observed to significantly improve the categorical NRI among women (NRI = 0.09, 95% CI: 0.06-0.11) at a risk threshold of 10%, suggesting enhanced risk stratification in this subgroup. InterpretationIn individuals without a history of prior MACCE, ECG-derived risk scores independently predict the 10-year risk of MACCE. However, when combined with QRISK3 risk factors, ECG risk scores only marginally improve risk prediction. FundingUK Engineering and Physical Sciences Research Council for the University of Oxford Health Data Science Centre for Doctoral Training [EP/S02428X/1] and Wellcome Trust.