Lipids & metabolic liver disease
Machine Learning Reveals the Contribution of Lipoproteins to Liver Triglyceride Content and Inflammation
Authors' conclusion
Isolated hypertriglyceridemia is the second strongest, after obesity, independent predictor of MASLD/MASH. Individuals with hypertriglyceridemia, but not with hypercholesterolemia, should be screened for liver disease.
Study context
- Population
- Europeans from the UK Biobank without chronic viral hepatitis or other causes of liver disease; 14,937 with liver MRI data14,937 with liver MRI
- Participants
- 218,732 participants
- Exposure
- Isolated hypertriglyceridemia and isolated hypercholesterolemia vs controls
- Outcome
- Prevalence of MASLD and MASH; independent contribution of lipoproteins to liver triglyceride content
Methodological detailsUK Biobank, machine learning
- UK Biobank
- Machine learning
Main finding
As reported in the abstract
- Isolated hypertriglyceridemia vs Control: P = 1.23 × 10-41
- Isolated hypertriglyceridemia vs Control: P = 1.29 × 10-10
- Isolated hypercholesterolemia vs Control: P = 0.019
- Isolated hypercholesterolemia vs Control: P = 0.97
Observational data: associations, not effects.
Further findings
Predictors of liver proton density fat fraction (machine learning)
- Feed-forward neural network had the best cross-validation mean squared error (MSE) on the validation set
- Circulating triglycerides were the second strongest independent predictor after BMI (largest absolute mean Shapley additive explanation value)
Original publication
Machine Learning Reveals the Contribution of Lipoproteins to Liver Triglyceride Content and Inflammation. J Clin Endocrinol Metab. Published 4 June 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →