Simple heart test shows promise for spotting hidden artery disease
Researchers combined conventional ECG readings with advanced signal analysis to create a predictive score for coronary artery disease, achieving 72% accuracy in an external validation study. The finding could help clinicians screen patients more efficiently before ordering expensive imaging tests, potentially reducing unnecessary scans and healthcare costs.
Originaltitel: Explainable advanced electrocardiography predicts coronary artery disease on coronary computed tomography angiography
ABSTRACT BACKGROUND Conventional electrocardiography (ECG) has limited diagnostic accuracy for detecting coronary artery disease (CAD) in patients with stable chest pain. Advanced electrocardiography (A-ECG) may improve diagnostic performance. The study aimed to derive, externally validate, and prognostically validate an explainable A-ECG score for detecting CAD on coronary computed tomography angiography (CCTA). METHODS Participants attending an outpatient rapid access chest pain clinic (RACC) underwent a standard 12-lead ECG and CCTA. Any CAD was defined as any calcified or non-calcified plaque. Elastic net with nested resampling was used to derive an A-ECG score using measures from the conventional ECG, derived vectorcardiography, and measures of waveform complexity. RESULTS In the derivation cohort (n=171, age 59±13 years, 60% male), n=99 (58%) had any CAD on CCTA. A seven parameter A-ECG score to detect any CAD was derived. In an external validation cohort (n=773, age 57±12 years, 49% male, n=433 (56%) with any CAD), the score had an area under the receiver operating characteristic curve [95% confidence interval] of 0.66 [0.63–0.70] for detecting any CAD, and 0.72 [0.68–0.76] for detecting any coronary artery calcification. In the UK Biobank (n=27,239, 966 events, follow-up 1.9 [0.7–4.4] years, age 66±8 years, 50% female), higher A-ECG scores were associated with cardiovascular events even after adjusting for age, sex and cardiovascular risk factors (p<0.001). CONCLUSIONS An explainable A-ECG model, incorporating demographic and electrocardiographic features, demonstrated modest but externally reproducible discrimination for CCTA-defined coronary atherosclerosis and independent prognostic association in a large population cohort. This scalable, low-cost approach may aid triage and risk stratification in chest pain pathways.