AgingResearch.NewsJoin free

Within-patient variability of AI-ECG age prediction

There is 1 paper on within-patient variability of AI-ECG age prediction in aging research: 1 observational study in people. The newest story, Nov 9, 2026: “AI heart-test predictions varied within hospitalized patients”.

Biomarker

1 paper studies it1 finding

1 new paper in 30 daysSee all 1 papers on within-patient variability of AI-ECG age prediction

“After full adjustment, within-patient variability of predicted age and sex was independently associated with 5-year mortality across all three cohorts”
Reproducibility of AI-ECG Predictions: Within-Patient Reliability of AI-ECG Across Nine Prediction Tasks and Three Multi-Centre CohortsAHA Scientific Sessions 2026 abstract2026doi:10.1161/circ.154.suppl_1.9994
  • Humans1

Associations

1

5-year all-cause mortality

upin humans1

1 study

  1. Within-patient variability of AI-ECG age prediction is associated with 5-year all-cause mortality in humans (Q4 versus Q1 HR: BIDMC 1.38 (95% CI 1.23–1.53); MGH 1.21 (1.17–1.25); EUH 1.62 (1.46–1.81)).

    “After full adjustment, within-patient variability of predicted age and sex was independently associated with 5-year mortality across all three cohorts”

    HumansHighest versus lowest quartile of within-patient prediction variability; adjusted for age, sex, comorbidity burden and cluster mean prediction5 years

    AI heart-test predictions varied within hospitalized patients

    AHA Scientific Sessions 2026 abstract

Latest

Dec 2025: 0Jan 2026: 0Feb 2026: 0Mar 2026: 0Apr 2026: 0May 2026: 0Jun 2026: 0Jul 2026: 0Aug 2026: 0Sep 2026: 0Oct 2026: 0Nov 2026: 11 paper in 12 months
AHA Scientific Sessions 2026 Abstract

AI heart-test predictions varied within hospitalized patients

Disagreement rates across repeated heart recordings ranged from 14.3% to 24.5% for disease prediction tasks.Disagreement rates across repeated heart recordings ranged from 14.3% to 24.5% for disease prediction tasks.

Cohort studyBiomarkers
Paper

Related