Adam D. Sturge

Background: Electrocardiograms (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. Methods: We 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 (ECG _AI ). 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 Harrell’s C-index and net benefit. Findings: Incident 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 ECG _AI 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 ECG _AI scores modestly improved model discrimination, ΔC-index 0.03 (95% CI: 0.02–0.04) and ΔC-index 0.03 (95% CI: 0.02–0.03), respectively. ECG _AI 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. Interpretation: In 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. Funding: UK Engineering and Physical Sciences Research Council for the University of Oxford Health Data Science Centre for Doctoral Training [EP/S02428X/1] and Wellcome Trust.

Background Many adults in high-income countries carry a device capable of measuring physical- activity behaviour. Thus, there is public health need to understand whether such data can enhance prediction of future health outcomes. We aimed to investigate whether device-measured daily-step count and walking cadence improve the prediction of mortality beyond traditional risk-factors. Methods Risk models were developed to predict five-year all-cause mortality using data from the UK Biobank accelerometer sub-study, with external validation in the US 2011-2014 National Health and Nutrition Examination Survey (NHANES). Median daily-step count and peak one-minute walking cadence were derived using self-supervised machine learning models from seven-day wrist-worn accelerometer data. Cox models were used to develop a baseline model incorporating traditional risk- factors, and a baseline model plus accelerometer data (i.e. daily-steps and walking cadence). Changes in model performance were assessed using Harrell’s C-index, net reclassification index (NRI; 10% threshold), and the Nam-D’Agostino calibration test. Findings Among 79,717 UK Biobank participants, 1,640 died within 5-years. Adding accelerometer data to the baseline model modestly improved risk discrimination and classification with a change in c- index of 0.008 (95% confidence interval [CI] 0.005-0.011) and 3.3% NRI (95%CI 2.1%-4.5%). Greatest improvements in prediction were observed in participants with prior disease at baseline, showing a change in c-index of 0.028 (95%CI 0.019-0.039) and 5.9% NRI (95%CI 3.1%-8.6%). In the NHANES external validation cohort (n=4,713; deaths=378), similar improvements in prediction were observed (change in c-index: 0.015, 95%CI 0.007-0.025; NRI: 4.0%, 95%CI 0.7%-7.4%). All models were well calibrated (Nam-D’Agostino χ² range: 6.8-13.2). Interpretation Device-measured daily-step count and walking cadence consistently demonstrated modest improvements in predicting mortality risk beyond traditional risk-factors, with the most significant enhancements seen in individuals with prior disease. These findings suggest that incorporating information from wearables does provide important new ways to improve risk stratification for targeted intervention in high-risk individuals.