Improving the Detection of Potential Cases of Familial Hypercholesterolemia: Could Machine Learning Be Part of the Solution?

Journal: Journal of the American Heart Association
PMID: 38879446

Abstract

BACKGROUND: Familial hypercholesterolemia (FH), while highly prevalent, is a significantly underdiagnosed monogenic disorder. Improved detection could reduce the large number of cardiovascular events attributable to poor case finding. We aimed to assess whether machine learning algorithms outperform clinical diagnostic criteria (signs, history, and biomarkers) and the recommended screening criteria in the United Kingdom in identifying individuals with FH-causing variants, presenting a scalable screening criteria for general populations.

Authors

  • Christophe A T Stevens
    Department of Primary Care and Public Health School of Public Health, Imperial College London London United Kingdom.
  • Antonio J Vallejo-Vaz
    Department of Primary Care and Public Health School of Public Health, Imperial College London London United Kingdom.
  • Joana R Chora
    Nacional Institute of Health Dr. Ricardo Jorge Lisbon Portugal.
  • Fotis Barkas
    Department of Primary Care and Public Health School of Public Health, Imperial College London London United Kingdom.
  • Julia Brandts
    Department of Primary Care and Public Health School of Public Health, Imperial College London London United Kingdom.
  • Alireza Mahani
    Quantitative Research Davidson Kempner Capital Management New York NY.
  • Leila Abar
    National Institute of Cancer National Institute of Health Rockville MD.
  • Mansour T A Sharabiani
    Department of Primary Care and Public Health School of Public Health, Imperial College London London United Kingdom.
  • Kausik K Ray
    Department of Primary Care and Public Health School of Public Health, Imperial College London London United Kingdom.

Keywords

External Resources

Popular Topics
Recent Journals