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

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

  • By

  • 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

  • Susan Cheng

  • David Ouyang

  • November 18, 2025

  • 0 min

Share

  • 1

    A deep learning model was developed to predict age from echocardiogram videos, achieving a mean absolute error of 6.76 years.

  • 2

    The model utilized 2,610,266 videos from 166,508 studies, demonstrating consistent performance across multiple validation cohorts.

  • 3

    Predicted age was associated with increased risks of coronary artery disease, heart failure, and stroke, highlighting its clinical relevance.

  • 4

    The model focused on key cardiac structures, indicating the potential of AI in enhancing cardiovascular risk assessment.

  • 5

    Survival analysis showed that patients predicted to be older had significantly worse outcomes, emphasizing the importance of biological age.

Original Source(s)

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

  • by 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, Susan Cheng, David Ouyang

  • November 18, 2025

Related Content

Control Tower in the hospital: a structure–process–outcome systemic review of telemedicine systems for interprofessional collaboration

Impact of Residential Radon Exposure on the Risks of Myocardial Infarction and Stroke in the All of Us Research Program

Determinants of Stroke Incidence in Hypertensive Patients in Eastern Ethiopia: A Case-Control Analysis