About the Study: Transthyretin amyloid cardiomyopathy results from abnormal protein deposits in the heart and can lead to progressive heart failure. As effective therapies become available, clinicians need better ways to identify which patients face the greatest risk of death or heart failure hospitalization.
In this multicenter cohort study of 850 patients with transthyretin amyloid cardiomyopathy, a machine learning–based time-to-event model showed better risk discrimination for all-cause mortality and heart failure hospitalization than the National Amyloidosis Centre and Mayo Clinic staging systems. The model performed well across multiple patient groups and treatment settings, suggesting potential value for more individualized prognosis in contemporary clinical care.
Meeting Information: ESC 2026
This paper will be presented during European Society of Cardiology Congress in Munich, Germany.
Local Embargo Time: 13:45 (1:45 P.M.) CEST.
ESC Presentation: The paper will be featured during the Symposium “How imaging-based digital twins, artificial intelligence, and robotics will guide interventions” on the Digital Health Stage.
Related Content: This paper has an accompanying editorial . Explore JAMA+ AI for editor-curated research, commentary, and multimedia from across JAMA Network.
Corresponding Author: Christoph Gräni, MD, PhD, Department of Cardiology, Inselspital, Bern University Hospital, University of Bern, Freiburgstrasse 20, CH-3010 Bern, Switzerland ( christoph.graeni@insel.ch ).
10.1001/jamacardio.2026.3496
To access the embargoed study: Visit our JAMA Network Media Center at this link https://media.jamanetwork.com/
Link to the article in your story
We encourage you to link out to this article in your story using the link below. It includes an access token that will give free access to the article for your readers up to one year after publication. (The link will be live after the article publishes and embargo is lifted.)
Editor's Note: Please see the article for additional information, including full author list, author contributions and affiliations, conflict of interest and financial disclosures, and funding and support.
JAMA Cardiology
Machine Learning–Driven Risk Prediction Model in Transthyretin Amyloid Cardiomyopathy