Within-patient prediction variability

There is 1 paper on within-patient prediction variability in aging research: 1 observational study in people. The newest story, Nov 9, 2026: “Repeated heart recordings improved AI risk prediction in patients”.

Biomarker

1 paper studies it2 findings

1 new paper in 30 daysSee all 1 papers on within-patient prediction variability

“those who died showed 4.8x higher between-ECG variability than controls in BIDMC (p<0.001)”
Longitudinal AI-Enhanced ECG for Dynamic and Competing Risk Prediction: Multicentre Development and Validation Across Fifteen Endpoints with Comparison to Single-ECG Modelling and PREVENT for Primary Cardiovascular PreventionAHA Scientific Sessions 2026 abstract2026doi:10.1161/circ.154.suppl_1.9962
  • Humans1

Upstream

1

LAIRE

downin humans1−48% lower

1 study
  1. LAIRE is linked with lower within-patient prediction variability in humans (Compared with AIRE+) (48% lower).

    “Prediction variability was 48% lower with LAIRE than AIRE+”

    HumansCompared with AIRE+

    Repeated heart recordings improved AI risk prediction in patients

    AHA Scientific Sessions 2026 abstract

More on LAIRE

Associations

1

Mortality

upin humans1

1 study
  1. Within-patient prediction variability is associated with mortality in humans (BIDMC; variability in those who died compared with controls) (4.8x higher between-ECG variability in those who died).

    “those who died showed 4.8x higher between-ECG variability than controls in BIDMC (p<0.001)”

    HumansBIDMC; variability in those who died compared with controls

    Repeated heart recordings improved AI risk prediction in 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

Repeated heart recordings improved AI risk prediction in patients

Across three hospital cohorts, models using repeated heart recordings outperformed a single-recording model for 11 of 13 outcomes.Across three hospital cohorts, models using repeated heart recordings outperformed a single-recording model for 11 of 13 outcomes.

Cohort studyBiomarkers