Subjects with bipolar disorder show accelerated biological aging compared to controls, as determined by AI-based electrocardiographic assessment, which appears to be independent of cardiovascular risk factors.
Key Findings
Results
Delta-Age (ECG-Age minus chronological age) was 2.5 years higher in subjects with bipolar disorder than in controls.
Mean Delta-Age in BD subjects was 3.23 ± 7.88 years versus 0.70 ± 7.62 years in controls (p < 0.001).
The study included 278 subjects with BD and 29,341 controls.
BD subjects had a mean chronological age of 49.23 ± 10.56 years and a mean ECG-Age of 52.47 ± 10.99 years.
Controls had a mean chronological age of 54.01 ± 12.33 years and a mean ECG-Age of 54.70 ± 11.35 years.
Results
Subjects with bipolar disorder were significantly more likely to have accelerated aging (Delta-Age ≥ 1SD above the mean) compared to controls.
Logistic regression revealed an odds ratio of 1.34 (95% CI = 1.01–1.76, p = 0.03) for BD subjects having Delta-Age ≥ 1SD.
This association was independent of chronological age, sex, and established cardiovascular risk factors.
Accelerated aging was defined as Delta-Age ≥ 1 standard deviation above the mean.
Methods
The study used a previously validated AI-ECG algorithm to assess physiological age from 12-lead ECG signals.
Patients were aged ≥ 30 years and sought primary care between 1998 and 2000 in Olmsted County, Minnesota.
Participants were followed up using the Rochester Epidemiology Project.
The BD cohort was 56.8% female; the control cohort was 53.7% female.
ECG-Age derived from the AI algorithm was used as a proxy measure of biological/physiological aging.
Background
Individuals with bipolar disorder are at increased risk for major adverse cardiovascular events, and AI-based ECG age assessment may independently predict all-cause and cardiovascular mortality.
Prior evidence indicates that the difference between chronological and physiological age as determined by AI-based ECG assessment may reflect biological aging.
AI-ECG-based age has been shown to independently predict all-cause and cardiovascular mortality in unselected populations.
The study was motivated by the known elevated cardiovascular risk in BD populations.
Conclusions
The authors identified pharmacological treatment and comorbidity patterns as potential mitigating or accelerating factors for biological aging in bipolar disorder that require future investigation.
The study calls for future research to explore mechanisms of accelerated aging in BD.
The authors note the need to assess generalizability to other major mental illnesses beyond BD.
Pharmacological treatments and comorbidity patterns were highlighted as variables that could either mitigate or further accelerate biological aging.
What This Means
This research suggests that people with bipolar disorder (BD) age biologically faster than people without the condition. The researchers used an artificial intelligence (AI) tool that analyzes standard heart recordings (electrocardiograms, or ECGs) to estimate a person's physiological—or biological—age, which can differ from their actual calendar age. By comparing nearly 280 people with bipolar disorder to over 29,000 people without it, they found that the biological age of people with BD was, on average, about 2.5 years older than expected based on their actual age, compared to people without BD.
Importantly, this accelerated aging was not simply explained by known heart disease risk factors like high blood pressure, diabetes, or smoking. Even after accounting for these factors, as well as age and sex, people with BD were about 34% more likely to show signs of significantly accelerated biological aging on their ECG. This finding adds to a growing body of evidence that BD may take a toll on the body that goes beyond what traditional risk factors alone can explain.
This research suggests that monitoring biological aging in people with bipolar disorder—potentially using AI-based ECG tools—could be a useful way to identify those at heightened cardiovascular risk. The findings also raise questions about what drives this accelerated aging: whether medications used to treat BD, patterns of other health conditions, or the disorder itself play a role. Future studies are needed to explore these questions and whether similar patterns exist in other serious mental illnesses.
Miola A, Medina-Inojosa B, Cuellar-Barboza A, Prieto M, Morgan R, Coombes B, et al.. (2026). Accelerated biological aging in bipolar disorder as determined by artificial intelligence-based electrocardiographic assessment.. Journal of affective disorders. https://doi.org/10.1016/j.jad.2026.121968