{
  "id": 639532,
  "title": "AI heart disease prediction tools show promise but are not ready for clinical use: review",
  "url": "https://urgent.news/2026/08/12/ai-heart-disease-prediction-tools-show-promise-but-are-not-ready-for-639532",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-12T06:21:47.000Z",
  "source": {
    "name": "The Hindu",
    "slug": "the-hindu",
    "url": "https://www.thehindu.com/news/national/karnataka/ai-heart-disease-prediction-tools-show-promise-but-are-not-ready-for-clinical-use-review/article71332372.ece"
  },
  "original_language": "en",
  "account": "A recent review highlights that while artificial intelligence (AI) holds promise in aiding India to identify individuals at risk of cardiovascular disease (CVD) earlier, the technology is not yet prepared for routine clinical use. Conducted by researchers from the Indian Institute of Science, M.S. Ramaiah University of Applied Sciences, and the London School of Hygiene and Tropical Medicine, the systematic review examined 30 studies published since 2017 on AI-based models designed to predict future cardiovascular disease in adults without existing heart disease. Most models were developed using datasets sourced from the U.S., U.K., and South Korea, and relied on machine learning algorithms like Random Forests, Support Vector Machines, and neural networks. According to Denny John, a faculty member at M.S. Ramaiah University of Applied Sciences and an author of the review, AI could enhance cardiovascular risk assessment precision and personalization, but the current evidence lacks sufficient rigor for widespread adoption. Indian institutions have already developed AI models incorporating locally relevant factors, but these tools require rigorous validation before clinical integration. While AI models performed comparably to conventional risk calculators in distinguishing high-risk from low-risk individuals over a 5-10 year period, the review emphasized that better statistical performance does not guarantee improved patient care. Key concerns include the lack of evidence demonstrating whether predicted risk aligns with real-world outcomes, as well as the need for external validation, calibration, and assessment of clinical usefulness before AI tools guide long-term treatment decisions. Dr. John stressed the importance of prospective validation of AI-based cardiovascular risk models across diverse populations, including India, before their integration into routine healthcare, and called for adherence to international reporting and assessment frameworks like TRIPOD+AI and PROBAST+AI to enhance transparency and reduce bias.",
  "summary": "The findings are particularly relevant for India, where cardiovascular disease accounts for nearly one-third of all deaths and often affects people at younger ages than in many other countries",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 2,
    "also_reported_by": [
      {
        "outlet": "The Hindu Health",
        "title": "AI heart disease prediction tools show promise but are not ready for clinical use: review",
        "url": "https://urgent.news/2026/08/12/ai-heart-disease-prediction-tools-show-promise-but-are-not-ready-for",
        "published": "2026-08-12T06:21:47.000Z"
      }
    ]
  },
  "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."
}