Incorporating ECG signal features into the Framingham risk score improved CVD risk prediction in women, increasing Harrell's C-index from 0.84 to 0.85 (NRI 55.7%, IDI 2.8%), with no improvement in men.
Cohort (n=4,637)
Does integrating ECG signal features with the Framingham risk score improve the prediction of incident CVD in adults without prior CVD?
Incorporating ECG signal features into conventional risk models significantly enhances CVD prediction performance and reclassification in women, offering potential for improved individualized preventive strategies.
Effect estimate: C-index 0.85
Non-communicable diseases (NCDs), particularly cardiovascular diseases (CVDs), have becomethe leading cause of mortality worldwide, with Iran exhibiting higher-than-average incidence andmortality rates. Early detection of high-risk individuals is critical, as CVD often progresses silently.Electrocardiogram (ECG) signals may enhance risk prediction beyond Framingham risk score (FRS).This study aimed to evaluate the predictive performance of ECG signal features for incident CVD usingsignal processing in a large population-based cohort from the Tehran Lipid and Glucose Study (TLGS). Atotal of 4,637 adults aged 40 years devoid of past CVD at baseline (2006–2008) were followed up until2018. Baseline characteristics, laboratory measurements, and ECG signal features were collected. CVDevents were defined as coronary heart disease (CHD) or stroke. A recalibrated FRS (baseline) modelassessed the association between ECG features and incident CVD, with model performance evaluatedusing Harrell’s C-index, Net Reclassification Index (NRI), and Integrated Discrimination Improvement(IDI). Over a 10-year follow-up, 483 participants (10.4%) developed CVD. The introduction of ECGsignal features improved risk prediction in women, increasing the Harrell’s C-index from 0.84 to 0.85and demonstrating significant reclassification improvement (NRI: 55.7%, IDI: 2.8%). However, nomeaningful improvement was observed in men. ECG-based modeling outperformed FRS, particularlyfor intermediate-risk categories among women. Incorporating ECG signal features into risk modelssignificantly enhanced CVD prediction performance in women, suggesting potential utility forimproving individualized preventive strategies. Further research is warranted to refine ECG-based riskstratification tools for broader clinical application.
Mahdavi et al. (Wed,) conducted a cohort in Cardiovascular disease (n=4,637). ECG signal features vs. Framingham risk score (FRS) alone was evaluated on Incident CVD (coronary heart disease or stroke) (C-index 0.85). Incorporating ECG signal features into the Framingham risk score improved CVD risk prediction in women, increasing Harrell's C-index from 0.84 to 0.85 (NRI 55.7%, IDI 2.8%), with no improvement in men.