Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
March 26, 2025Open Access

AI-predicted biological age from echocardiograms linked to ~42% higher all-cause mortality per 10-year increase.

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Distinguishing biological from chronological age may help identify individuals with accelerated versus delayed cardiovascular aging and increased risk for adverse outcomes.

Does an AI-predicted biological age from echocardiography improve risk stratification for cardiovascular outcomes compared to chronological age?

Population

90,738 unique patients with 166,508 echocardiogram studies and 2,610,266 videos

Comparison

AI-predicted age from echocardiogram videos vs chronological age

Design

Deep learning model development and validation study

Key result

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

Authors

MRMeenal RawlaniHIHirotaka IekiCBChristina Binder

Discussion

Loading...

Member takes

Overview

May aid mortality risk stratification via AI echo age; hypothesis-generating and requires prospective validation.

Study Design

Type

Observational (n=90,738)

Multicenter

Yes

Structured PICO

Does an AI-predicted biological age from echocardiography improve risk stratification for cardiovascular outcomes compared to chronological age?

P
Population
90,738 unique patients with 166,508 echocardiography studies (2,610,266 videos) from Cedars-Sinai Medical Center and Stanford Healthcare. Patients with prior histories of coronary artery bypass grafting (CABG), cardiac valve replacement, or heart transplant were excluded from the training and validation splits.
I
Intervention
Deep learning artificial intelligence (AI) model (video ResNet architecture and Histogram Gradient Boosting ensemble) predicting biological age from multi-view echocardiogram videos (PLAX, A2C, A4C, SC).
C
Comparator
Chronological age (used as the reference standard for survival and risk prediction comparisons).
O
Outcome
Accuracy of age prediction measured by mean absolute error (MAE) and coefficient of determination (R2).surrogate

Main Result

Effect estimate: HR 1.42 (95% CI 1.37-1.48)

p-value: p=<0.005

AI-derived biological age from echocardiograms outperforms chronological age in predicting long-term cardiovascular outcomes and mortality.

Limitations

  • The dataset originated from a single institution, which may limit generalizability.
  • More sophisticated explainability techniques could further elucidate the specific features driving predictions.
  • Echocardiographic videos analyzed are likely from patients presenting with health concerns, potentially introducing a bias that may not represent normal aging.

Cite This Study

Rawlani et al. (2025) conducted an observational in Cardiovascular Disease (n=90,738). Deep learning artificial intelligence age prediction from echocardiogram videos 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 predicted biological age from echocardiogram videos with a mean absolute error of 6.76 years, and a 10-year increase in predicted age was associated with higher all-cause mortality (HR 1.42).

synapsesocial.com/papers/6a15972d5347fbb173a0022fhttps://doi.org/10.1101/2025.03.25.25324627
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Artificial intelligence prediction of age from echocardiography as a marker for cardiovascular disease2025
  2. 2Artificial intelligence prediction of age from echocardiography as a marker for cardiovascular disease2025 · 1 citations
  3. 3A scoping review on aging and cardiovascular diseases - Molecular mediators and artificial intelligence-based advanced diagnostic methods2026
  4. 4Comparison of Artificial Intelligence–Derived Heart Age with Chronological Age Using Normal Sinus Electrocardiograms in Patients with No Evidence of Cardiac Disease2025 · 2 citations
  5. 5AI-ECG-derived biological age as a predictor of mortality in cardiovascular and acute care patients2025