Item refines Peer-reviewed Added 20 September 2026

Three Holter ECG measures with age predicted five-year mortality in Israeli adults

A random forest combining atrial fibrillation burden, premature ventricular contraction burden, T-wave alternans and age reached an AUROC of 0.79 for five-year mortality in 54,395 Israeli primary care patients.

Three measures were taken from 81,362 Holter recordings of 54,395 people at 20 Israeli primary care centres. Combined with age in a random forest, five-year discrimination was 0.79 for death from any cause and 0.69 for ischaemic stroke. In those under 75, the three measures predicted up to 10% better than age on its own.

Why it is interesting: Tests whether ECG measures already recorded in primary care add prognostic information beyond age.

Source: Physiological Measurement, 18 September 2026
Paper: Single-lead ECG biomarkers for cardiovascular and mortality risk prediction
Authors: Attali L, Solewicz Y, Brimer Biton S, Hamami H, Zvuloni E, Green I et al.
DOI: 10.1088/1361-6579/aea9ec
Type: Peer-reviewed article
Design: Retrospective cohort: 81,362 Holter recordings from 54,395 people at 20 Israeli primary care centres; random forest predicting 5-year outcomes
Verdict: Refines prior evidence
Driver: AI in medicine
Free full text: Free to read at the publisher

Abstract — the authors' own words, CC BY

Objective. Cardiovascular disease remains one of the leading causes of morbidity and mortality worldwide, highlighting the need for accurate risk prediction. Atrial fibrillation burden (AFB), premature ventricular contraction burden (PVCB), and T-wave alternans (TWA) have been individually associated with adverse outcomes. We hypothesized that these three digital ECG biomarkers provide complementary prognostic information for major cardiovascular endpoints and all-cause mortality (ACM), and developed a machine learning approach combining these biomarkers for risk prediction. Approach. We analyzed 81 362 Holter recordings from 54 395 individuals across 20 primary care centers in Israel. A random forest model using AFB, PVCB, TWA, and age was trained to predict 5 year risk of heart failure (HF), ischemic stroke (IS), and ACM. Main results. On the test set, best AUROCs were for HF 0.75 [95% CI: 0.74-0.77] (), for IS 0.69 [0.66-0.71] (), and for ACM 0.79 [0.77-0.80] (). Combining the three ECG-derived biomarkers showed complementary predictive value and improved discrimination by up to 10% over age alone in individuals agedyears. Significance. AFB, PVCB, and TWA contribute complementary prognostic information for risk stratification. When combined with age, these biomarkers improve predictive performance compared with age alone.