{
  "id": 7579989,
  "title": "Study demonstrates how machine learning model enables targeted Lp(a) screening",
  "url": "https://urgent.news/2026/09/15/study-demonstrates-how-machine-learning-model-enables-targeted-lp-a",
  "topic": "health",
  "section": "Health & Medicine",
  "published": "2026-09-15T15:20:05.000Z",
  "source": {
    "name": "Medical Xpress",
    "slug": "medical-xpress",
    "url": "https://medicalxpress.com/news/2026-09-machine-enables-lpa-screening.html"
  },
  "original_language": "en",
  "account": "A new study published in JACC: Advances by The Family Heart Foundation demonstrates how their FIND Lp(a) Machine Learning Model can identify individuals with atherosclerotic cardiovascular disease (ASCVD) who are at higher risk for elevated lipoprotein(a) (Lp(a)). The model has already been implemented at five major U.S. healthcare systems as part of the FIND Lp(a) Program, which aims to promote Lp(a) screening. The study, \"FIND Lp(a) MLM: Targeted Screening Enrichment of Elevated Lipoprotein(a) in Atherosclerotic Cardiovascular Disease,\" outlines the development and preliminary validation of the model using the Family Heart Database. The model proved to be highly accurate, with patients identified being over 2.2 times more likely to have high Lp(a) (≥125 nmol/L) compared to the general ASCVD population. This targeted approach could expedite the implementation of guideline-recommended universal Lp(a) screening, despite the slow progress thus far. Diane MacDougall, from the Family Heart Foundation, notes that the model helps prioritize Lp(a) screening for patients most at risk, thereby accelerating the adoption of universal screening and facilitating better management of cardiovascular risk for those with elevated Lp(a). Lp(a) is a genetic risk factor for cardiovascular disease, yet awareness among healthcare professionals is lacking. Currently, 99% of U.S. adults have never had their Lp(a) levels checked. The FIND Lp(a) model is a key element of the Family Heart Foundation's quality improvement program, which utilizes machine learning and electronic health record data to identify individuals likely to have high Lp(a). Through its Collaborative Learning Network, the foundation and five healthcare system partners are validating the model's real-world performance while sharing best practices and establishing sustainable strategies for Lp(a) screening and care. Despite the challenges faced by many machine learning initiatives, the FIND Lp(a) MLM project marks a significant advancement in applying machine learning and predictive analytics to clinical practice.",
  "summary": "The Family Heart Foundation has published a new study in JACC: Advances demonstrating how its FIND Lp(a) Machine Learning Model can identify people with atherosclerotic cardiovascular disease (ASCVD) who are more likely to have high lipoprotein(a)—or Lp(a).",
  "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."
}