{
  "id": 9780115,
  "title": "AI model predicts pancreatic cancer risk 3 years before diagnosis",
  "url": "https://urgent.news/2026/09/25/ai-model-predicts-pancreatic-cancer-risk-3-years-before-diagnosis",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-25T15:00:49.000Z",
  "source": {
    "name": "Medical Xpress",
    "slug": "medical-xpress",
    "url": "https://medicalxpress.com/news/2026-09-ai-pancreatic-cancer-years-diagnosis.html"
  },
  "original_language": "en",
  "account": "Researchers at Mayo Clinic have developed an AI model to predict an individual's risk of developing pancreatic cancer up to three years before diagnosis. Pancreatic cancer is rare but deadly, with 67,000 new diagnoses and 52,000 deaths in 2026, accounting for 3% of all new cancers but 8% of cancer-related deaths. Early detection is crucial, as only 1 in 5 patients are diagnosed in time, leading to survival measured in months rather than years. While universal screening for pancreatic cancer is not feasible, the Mayo Clinic team aimed to create an AI model that could identify high-risk patients. The model utilized longitudinal health histories from patients' electronic health records, combined with data from routine laboratory tests over a decade or more. Tested on a dataset of 6,066 individuals with pancreatic cancer and 33,396 controls, the model achieved an AUROC of 0.853, indicating strong discrimination between at-risk and low-risk individuals. The area under the precision-recall curve (AUPRC) was 0.712, demonstrating the model's ability to identify patients truly at risk while minimizing false positives. The researchers are currently deploying the model prospectively in clinical settings and working on further validation.",
  "summary": "Researchers at Mayo Clinic have designed an artificial intelligence model that could predict an individual's risk of developing pancreatic cancer years before diagnosis. The research was presented at the American College of Surgeons (ACS) Clinical Congress 2026 in Washington, Sept. 26–29.",
  "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."
}