{
  "id": 3787887,
  "title": "Registry-based model predicts hip fracture risk better than current screening",
  "url": "https://urgent.news/2026/08/27/registry-based-model-predicts-hip-fracture-risk-better-than-current",
  "topic": "science",
  "section": "Science",
  "published": "2026-08-27T18:00:12.000Z",
  "source": {
    "name": "Medical Xpress",
    "slug": "medical-xpress",
    "url": "https://medicalxpress.com/news/2026-08-registry-based-hip-fracture-current.html"
  },
  "original_language": "en",
  "account": "A sophisticated machine-learning algorithm, FRACTURE-ML, developed using extensive Swedish national health registry data, can predict hip fracture risk with high accuracy, according to a study published in PLOS Medicine. This innovative approach outperforms traditional clinical screening methods that rely on in-person assessments and may struggle to identify at-risk individuals on a large scale. By analyzing over 100,000 variables derived from diagnoses, medications, procedures, and demographic data, FRACTURE-ML demonstrated strong predictive power, accurately identifying individuals at risk of hip fractures up to five years ahead. The model's simplicity, using just 35 variables, retained nearly 90% of its predictive performance, suggesting that valuable insights can be gleaned from more manageable, interpretable models. Despite its reliance on registry data lacking information on lifestyle factors like smoking and alcohol, the study underscores the potential for FRACTURE-ML to facilitate more efficient preventive measures and reduce the burden of hip fractures in the population. Further validation and implementation testing in diverse settings are necessary to fully assess its real-world applicability.",
  "summary": "A machine-learning tool built from Swedish national health registry data can predict hip fracture risk with high accuracy without an in-person assessment and identifies far more at-risk individuals than current clinical screening practices, according to a study published Aug. 27 in the journal PLOS Medicine by Kristian Axelsson and Mattias Lorentzon of the University of Gothenburg, Sweden, and…",
  "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."
}