Explainable AI score predicts heart muscle bleeding risk before artery reopening
Upstate Medical University cardiologist Ankur Kalra helped lead a team of researchers that developed and tested a scoring system to help identify patients at high risk of bleeding into damaged heart muscle after a severe heart attack using explainable artificial intelligence (XAI).
Researchers at Upstate Medical University have developed a scoring system using explainable artificial intelligence (XAI) to predict the risk of bleeding into damaged heart muscle after a severe heart attack. The study, led by cardiologist Ankur Kalra, was published in JACC: Advances and aims to identify patients at high risk of intramyocardial hemorrhage (IMH) before reopening a blocked artery.
IMH, a life-threatening complication of a heart attack, affects about 40% of STEMI patients and increases the risk of heart failure and death. The scoring system, which utilizes structural heart interventional cardiologists, could help clinicians assess risk in real-time during emergency angiography or identify patients who need closer monitoring after a blocked artery is reopened.
The tool may also help determine which patients require a cardiac MRI or may qualify for a clinical trial aimed at reducing IMH damage. The XAI method allows interventionalists to understand the driving factors behind the prediction, rather than relying on a "black box" approach. Upstate Medical University plans to integrate this XAI into an electronic health record-based calculator to support decision-making for these high-risk patients.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
