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
UVA's $4M NIH Grant Backs AI to Optimize Cardiac MRI Therapies
UVA secures $4 million NIH funding to develop GenStrain, an AI model using MRI data to personalize cardiac pacing therapies.
•EurekAlert
Machine Learning Models Predict Cancer Risk with Routine Health Data
Researchers developed machine learning models using routinely collected health data to predict individual risk for 20 common cancers, outperforming traditional methods for several cancer types.
•EurekAlert
AI Deep Learning Model Enhances Echocardiogram RV Assessment and Prognosis
Researchers developed DROID-RV, a deep learning tool that automates right ventricular assessment from echocardiograms, showing strong prognostic links with cardiovascular outcomes.