Artificial intelligence-derived cardiac ageing is associated with cardiac events post-heart transplantation

Ilke Ozcan1, Takumi Toya1,2, Michal Cohen-Shelly1

  • 1Department of Cardiovascular Medicine, Mayo Clinic, 200 First Street SW, Rochester, MN 55902, USA.

Insights

Artificial intelligence-determined physiological age from electrocardiograms (ECGs) can predict cardiac mortality risk in heart transplant recipients. An increase in ECG age post-transplant is linked to a higher risk of major adverse cardiovascular events.

Area of Science:

  • Cardiology
  • Artificial Intelligence
  • Transplantation Medicine

Background:

  • An artificial intelligence (AI) algorithm estimating physiological age from 12-lead electrocardiograms (ECGs) has shown associations with cardiac mortality in the general population.
  • Investigating this AI-derived 'physiological age' in heart transplant (HTx) recipients is crucial for understanding post-transplant outcomes.

Purpose of the Study:

  • To evaluate the utility of an AI-based ECG algorithm for assessing physiological age in heart transplant recipients.
  • To determine if physiological age, as estimated by ECG, is associated with major adverse cardiovascular events (MACE) after HTx.

Main Methods:

  • A cohort of 540 heart transplant recipients was studied, analyzing ECGs taken within one year before and after transplantation.
  • Physiological age was derived using an AI algorithm from 12-lead ECGs.
  • Major adverse cardiovascular events (MACE), including revascularization, heart failure hospitalization, re-transplantation, and mortality, were tracked over a median follow-up of 8.8 years.

Main Results:

  • Pre-transplant ECG age correlated significantly with recipient chronological age (mean 63 vs 49 years).
  • Post-transplant ECG age correlated with both donor (mean 54 vs 32 years) and recipient ages.
  • An increase in ECG age after transplantation was significantly associated with an increased risk of MACE (HR: 1.58, P=0.0002), even after adjusting for confounders.

Conclusions:

  • ECG-derived physiological age and its changes after heart transplantation are associated with an increased risk of MACE.
  • AI-assessed cardiac aging post-heart transplantation may serve as a significant predictor of adverse cardiovascular events.
Abstract