Upstate Medical University cardiologist Ankur Kalra helped lead a team of researchers that has developed and tested a scoring system that can help identify patients at high risk of internal bleeding in damaged heart muscle after a severe heart attack using explainable artificial intelligence (XAI).
Kalra, MD, MSc, FACP, FACC, FSCAI, director of Cardiac Catheterization Laboratories and chief of Cardiology at Upstate, is the co-principal investigator on the National Institutes of Health/National Heart, Lung, and Blood Institute grant. The study, "Predicting Intramyocardial Hemorrhage Before Reperfusion in STEMI Patients With Intrinsically Explainable Artificial Intelligence," was recently published in the Journal of American College of Cardiology (JACC).
"These findings are significant as appropriate identification will lead to incremental therapy with intravenous dexrazoxane," said Kalra, who is a structural heart interventional cardiologist. "Dexrazoxane is an investigational drug; we are presenting our findings from a Phase 2a study in Munich on Aug. 31 at European Society of Cardiology Congress. We anticipate the manuscript will be simultaneously published in one of the highest impact factor journals in cardiology.
Myocardial infarction (MI)—commonly known as a heart attack—is a significant global health concern, with over 800,000 cases reported annually in the United States alone.
Intramyocardial hemorrhage or IMH is a life-threatening complication of a heart attack that can occur after doctors restore blood flow through a blocked artery. IMH, the most serious form of heart muscle injury, affects about 40 percent of patients treated for ST-segment elevation myocardial infarction, or STEMI, a severe type of heart attack and increases the risk of heart failure and death.
The new scoring system is designed for interventional cardiologists to use in cardiac catheterization, or CATH labs before reopening a patient's blocked artery.
The score could eventually help clinicians assess risk in real time during emergency angiography, when providers check for blockage within the heart arteries, or it could help identify patients who need closer monitoring after a blocked artery is reopened. The score may also help doctors decide which patients need a cardiac MRI, and which may qualify to participate in a clinical trial aimed in reducing damage from IMH.
"This is the kind of AI we need for accurate, interpretable and usable data at the point of care," Kalra said. "The SNN method allows interventionalists to see exactly which factors are driving the prediction, rather than being asked to trust a black box."
Kalra adds that at some point, Upstate will have this type of XAI.
"These findings are actionable in an electronic health record-based calculator that can help identify these patients," he said.
Collaborators on the study included the Indiana University School of Medicine; the University of Toledo College of Medicine and Life Sciences; Northern Ontario School of Medicine University; Cleveland Clinic; and Upstate Medical University.
