{
  "id": 6650564,
  "title": "Explainable AI score predicts heart muscle bleeding risk before artery reopening",
  "url": "https://urgent.news/2026/09/10/explainable-ai-score-predicts-heart-muscle-bleeding-risk-before",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-10T21:40:11.000Z",
  "source": {
    "name": "Medical Xpress",
    "slug": "medical-xpress",
    "url": "https://medicalxpress.com/news/2026-09-ai-score-heart-muscle-artery.html"
  },
  "original_language": "en",
  "account": "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.",
  "summary": "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).",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}