Researchers have developed an AI tool that accurately diagnoses advanced heart failure using cardiac ultrasound and patient health records.
Key Details
- 1AI approach predicts peak VO2, a key advanced heart failure measure, from cardiac ultrasound images and EHR data.
- 2Model trained on 1,000 heart failure patient datasets from NewYork-Presbyterian/Columbia University Irving Medical Center.
- 3Tested on 127 new patients across three separate NewYork-Presbyterian campuses.
- 4Achieved approximately 85% accuracy in identifying high-risk patients, outperforming prior AI models.
- 5Study published March 3, 2026, in npj Digital Medicine by a consortium of Cornell, Columbia, and NewYork-Presbyterian researchers.
- 6Clinical trials and FDA approval are anticipated as next steps.
Why It Matters
This AI tool could simplify and broaden access to advanced heart failure diagnosis, which traditionally requires specialized, less accessible testing. For radiology and cardiology AI professionals, it highlights a practical, collaborative model for deploying imaging AI in clinical care.
Source
EurekAlert
Related News
•EurekAlert
Dynamic AI Models Provide Early Disease Warnings from Health Data
AI-driven dynamic models may predict disease tipping points earlier by analyzing changes in health data, including imaging.
•EurekAlert
Mount Sinai Develops AI Model to Personalize CPAP's Cardiovascular Impact
Mount Sinai has developed a machine learning model forecasting the cardiovascular risk impact of CPAP in obstructive sleep apnea patients.
•EurekAlert
AI Model Accurately Predicts Recurrence After Barrett’s Esophagus Therapy
Researchers created an AI tool that predicts recurrence of Barrett’s esophagus following endoscopic eradication therapies with greater than 90% accuracy.