Health · Medical Research · 6 hrs ago
AI-estimated older heart age linked to higher long-term mortality
Researchers used AI to estimate heart age from heart ultrasound images for 568 adults aged 50 or older in a community-based study.
They compared each person's estimated heart age with their actual age, using scans taken between 2002 and 2004.
Over the following 20 years, the team tracked deaths related to cardiovascular disease and dementia.
Each five-year increase in the heart-age gap was linked to 46% higher mortality after accounting for age, sex, body mass index and heart pumping function.
This is an association, and the study does not show that an older estimated heart age causes these deaths.
The findings suggest AI-estimated heart age may help identify long-term health vulnerability, including in people outside groups already known to have heart disease.
Researchers say larger studies in independent groups are needed, and further work could test whether lifestyle or medical treatments can reduce the heart-age gap.
An older artificial intelligence-estimated heart age relative to a person’s actual age was associated with higher long-term cardiovascular- and dementia-related mortality.
The analysis included 568 adults aged 50 or older who had echocardiograms between 2002 and 2004.
Over 20 years, each five-year increase in the gap between estimated and actual heart age was associated with a 46% higher risk of these deaths after adjustment for age, sex, body mass index and left ventricular ejection fraction.
The findings were presented at the ESC Digital & AI Summit 2026.
The researchers said larger, independent prospective studies are warranted.
- Who
- Researchers led by study presenter Doctor Jeffrey G. Malins of Mayo Clinic, Rochester, analyzed data from 568 adults.
- What
- An older AI-estimated heart age was associated with higher long-term cardiovascular- and dementia-related mortality.
- When
- The echocardiograms were performed between 2002 and 2004, with mortality data collected over 20 years. Results were presented at the ESC Digital & AI Summit 2026.
- Where
- The cohort was community-based; the study presenter was from Mayo Clinic in Rochester, USA.
- Why
- The researchers assessed whether the relationship between AI-estimated heart age and outcomes also exists in the general population.
This story does not have two clearly opposing sides.
The 568 adults in the community-based cohort underwent echocardiography.
Researchers collected data on cardiovascular- and dementia-related mortality.
The study results were presented at the ESC Digital & AI Summit 2026.
- Participants
- 568 adults aged 50 years or older
- Echocardiograms
- Performed between 2002 and 2004
- Follow-up
- 20 years
- Adjusted association
- Each five-year increase in heart-age gap was associated with a 46% increase in cardiovascular- and dementia-related mortality
- Study presenter
- Doctor Jeffrey G. Malins, Mayo Clinic, Rochester, USA
What people are saying
Wider prospective evaluations of AI-derived cardiac aging signatures in larger, independent cohorts are now warranted.
Previously, it has been shown that a discrepancy between AI-estimated heart age and actual age is linked with worse outcomes in patients with cardiovascular disease, but there is a gap in the evidence regarding whether this relationship exists for the general population.