A Machine Learning Model to Aid Detection of Familial Hypercholesterolemia
Authors' conclusion
Detecting individuals with FH can be improved by considering additional predictors.
Study context
- Population
- Unrelated UK Biobank participants; Familial hypercholesterolemia (FH) variant carriers identified by whole-exome sequencing488 FH variant carriers
- Participants
- 139,779 participants
- Comparison
- Multivariable ML models vs low-density lipoprotein cholesterol (LDL-C) adjusted for statin use
- Outcome
- Identification of monogenic FH variant carriers (AUC)
Methodological detailsLASSO logistic regression, independent training and testing data
- LASSO logistic regression
- Independent training and testing data
Performance
As reported in the abstract
FH detection
| Test or model | AUC |
|---|---|
| 14-variable model | 0.77 (95% CI: 0.71-0.83) |
| 9-variable model | 0.76 (95% CI: 0.71-0.82) |
AUC
14-variable model0.77 (95% CI: 0.71-0.83)
9-variable model0.76 (95% CI: 0.71-0.82)
Original publication
A Machine Learning Model to Aid Detection of Familial Hypercholesterolemia. JACC Adv. Published 24 May 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →