Artificial intelligence prediction of age from echocardiography as a marker for cardiovascular disease

Q: What are the key findings of this study?

An artificial intelligence model predicting age from echocardiogram videos achieved a mean absolute error of 6.76 years, and a 10-year increase in predicted age was associated with a higher risk of all-cause mortality (HR 1.42) compared to chronological age.

Q: What is the clinical evidence from this study?

Study design: Observational. Population: Cardiovascular disease and biological aging (n=185494). Intervention: AI-predicted age from echocardiography vs. Chronological age. Primary outcome: All-cause mortality (per 10-year increase in predicted age) (HR 1.42, 95% CI 1.37-1.48, p=<0.005).

Q: What does this research mean for the field?

Deep learning prediction of biological age from echocardiograms achieves a mean absolute error of 6.76 years and is more strongly associated with all-cause mortality and cardiovascular disease risk than chronological age. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

Meenal Rawlani; Hirotaka Ieki; Christina Binder; Victoria Yuan; I-Min Chiu; Ankeet Bhatt; Joseph E. Ebinger; Yuki Sahashi; Andrew P. Ambrosy; Hiroki Usuku; Kenichi Tsujita; Paul Cheng; Alan C. Kwan; David Ouyang

doi:10.1038/s41746-025-02050-x

November 18, 2025npj Digital MedicineOpen Access

Artificial intelligence prediction of age from echocardiography as a marker for cardiovascular disease

View Full Paper

Ask AI

Bookmark

Share

Key result

AI-predicted age from echocardiography linked to ~42% higher mortality risk per 10-year increase.

HR 1.42
95% CI 1.37-1.48
P<0.005
n=185,494

Figures

Why the study?

While chronological age is a universal risk predictor, distinguishing biologically older from younger individuals may identify accelerated or delayed cardiovascular aging.

Does an AI model predicting age from echocardiography videos accurately estimate biological age and improve cardiovascular risk stratification compared to chronological age?

Study Design

Type

Observational (n=185,494)

Multicenter

Yes

Structured PICO

Does an AI model predicting age from echocardiography videos accurately estimate biological age and improve cardiovascular risk stratification compared to chronological age?

P

Population

185,494 patients undergoing clinically indicated echocardiography across multiple international centers, followed for up to 5 years to assess the association between AI-predicted cardiac age and cardiovascular outcomes.

E

Exposure

Deep learning ensemble model (ResNet architecture) predicting biological age from multi-view echocardiogram videos (PLAX, A2C, A4C, SC views).

C

Comparator

Chronological age (used as the baseline standard for age and for comparing prognostic value in risk stratification).

O

Outcome

Mean absolute error (MAE) and coefficient of determination (R2) of the predicted age compared to chronological age.surrogate

Main Result

Hazard Ratio: 1.42 (95% CI 1.37–1.48)

p-value: p=<0.005

Limitations

Dataset is derived from patients undergoing clinically indicated imaging and may be enriched for individuals with underlying health concerns.
May not fully reflect the distribution of cardiac aging in an asymptomatic or community-based population.
The KU cohort from Japan had a smaller sample size and represented a demographically distinct population, which may have contributed to lower performance.
Potential for misuse of biological age predictions by institutions, such as insurance companies, to discriminate.
Smaller sample size and distinct demographics in the Kumamoto University cohort may have contributed to lower performance in that group.
Missing clinical parameters limited ASCVD score calculation for some studies.

Ask about this paper

Answers are grounded in this paper and cite their sources.

Implication

AI-predicted age from echocardiograms serves as a marker of biological cardiac aging and provides stronger prognostic value for cardiovascular outcomes than chronological age.

Abstract

While chronological age is a universal risk predictor across most populations and diseases, distinguishing between biologically older from younger individuals may identify individuals with accelerated or delayed cardiovascular aging. This study presents a deep learning model to predict age from echocardiogram videos, leveraging 2,610,266 videos from 166,508 studies from 90,738 patients. Leveraging multi-view echocardiography, our model achieved a mean absolute error (MAE) of 6.76 (6.65–6.87) years and a coefficient of determination (R 2 ) of 0.732 (0.72–0.74) on Cedars-Sinai Medical Center test set. Consistent performance was observed across four external validation cohorts. Predictions were associated with increased risk of coronary artery disease, heart failure, and stroke, and captured discontinuities before and after a heart transplant. Guided back propagation highlighted the model’s focus on the mitral valve, mitral apparatus, and basal inferior wall, underscoring the potential of computer vision-based assessment of echocardiography in enhancing cardiovascular risk assessment and aging.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Rawlani et al. (2025) conducted an observational in Cardiovascular disease and biological aging (n=185,494). AI-predicted age from echocardiography vs. Chronological age was evaluated on All-cause mortality (per 10-year increase in predicted age) (HR 1.42, 95% CI 1.37-1.48, p=<0.005). An artificial intelligence model predicting age from echocardiogram videos achieved a mean absolute error of 6.76 years, and a 10-year increase in predicted age was associated with a higher risk of all-cause mortality (HR 1.42) compared to chronological age.

synapsesocial.com/papers/6a8db3b11c0389f4063151d9 https://doi.org/10.1038/s41746-025-02050-x

View Full Paper

Ask AI

Bookmark

Share

Artificial intelligence prediction of age from echocardiography as a marker for cardiovascular disease

Figures

Study Design

Structured PICO

Main Result

Limitations

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

Artificial intelligence prediction of age from echocardiography as a marker for cardiovascular disease

Figures

Study Design

Structured PICO

Main Result

Limitations

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading