Implications of Diagnosis Through a Machine Learning Algorithm on Management of People With Familial Hypercholesterolemia
Authors' conclusion
These findings suggest that implementation of a MLA approach such as FIND FH may be feasible for identifying undiagnosed individuals living with FH, as well as addressing treatment disparities in this population at increased cardiovascular risk.
Study context
- Population
- Patients flagged by the Flag, Identify, Network, and Deliver (FIND) familial hypercholesterolemia (FH) machine learning algorithm (MLA) as high probability for FH in the EMR of one large academic medical centeridentified over 5.5 years
- Participants
- 471 patients
- Exposure
- Established FH diagnosis vs undiagnosed likely FH
- Established FHn = 32
- Likely FHn = 121reference
- Suspected FHn = 318
- Outcome
- FH diagnostic coding status of MLA-identified patients
Methodological detailsretrospective, single academic medical centre, machine learning algorithm screening
- Retrospective
- Single academic medical centre
- Machine learning algorithm screening
Main finding
As reported in the abstract
Likely FH
26%
121
Observational data: associations, not effects.
Further findings
Prior MACE
- No significant differences between established FH and likely FH
Original publication
Implications of Diagnosis Through a Machine Learning Algorithm on Management of People With Familial Hypercholesterolemia. JACC Adv. Published 21 August 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →