An AI model integrating ECG data and blood biomarkers predicts heart transplant rejection with high specificity, reducing the need for invasive biopsies.
Key Details
- 1NYU Langone researchers trained AI on 5,300 ECGs from 2,357 adult heart transplant recipients.
- 2The combined model used ECG data and blood biomarker results to flag rejection risk.
- 3In a test group, the combined model correctly identified 94% of patients without rejection, outperforming models that used only blood tests.
- 4The integrated approach would have spared multiple patients from unnecessary biopsies.
- 5Study spanned data from 2018–2024; results published September 25, 2026, in the Journal of Heart and Lung Transplantation.
- 6Researchers plan to test the model across more transplant centers.
Why It Matters

Source
EurekAlert
Related News

Deep Learning and MRI Identify Cognitive Impairment in CKD Patients
Researchers used multimodal MRI and a novel deep learning model to identify cognitive impairment in chronic kidney disease patients with strong validation.

Advances in 3D-Printed Devices for Structured-Light Imaging
Researchers review femtosecond laser 3D microfabrication for integrated structured-light optical devices.

Deep Learning Tool Predicts DBS Outcomes in Dystonia via MRI
Researchers developed a deep learning algorithm (DystoniaDBSNet) that uses MRI scans to predict which dystonia patients will benefit from deep brain stimulation (DBS) surgery.