Lipids & metabolic liver disease
Machine Learning Identifies Metabolic Dysfunction–Associated Steatotic Liver Disease in Patients With Diabetes Mellitus
Authors' conclusion
A ML approach demonstrated high performance in identifying MASLD in patients with DM. This approach may facilitate better risk stratification and cardiovascular risk prevention strategies for high-risk patients with DM at risk of MASLD.
Study context
- Population
- Patients with diabetes mellitus (DM) (mean age 58.85 ± 17.37 years; 48% women)
- Participants
- 2,000 patients
- Outcome
- Classification of DM patients with vs without MASLD (sensitivity, specificity, correctly classified, AUC)
Methodological detailsmachine learning, multiple logistic regression model, decision curve analysis
- Machine learning
- Multiple logistic regression model
- Decision curve analysis
Performance
As reported in the abstract
Identification of MASLD in patients with DM
- Patients with MASLD correctly identified (1735 patients)
- 744/991 (75.08%)
- Patients without MASLD correctly identified (1735 patients)
- 586/744 (78.76%)
- Sensitivity/specificity (1735 patients)
- 0.75/0.79
- AUC (95% CI) (1735 patients)
- 0.84 (0.82-0.86)
- Decision curve analysis (DCA): higher clinical utility of the model, threshold probability
- 30% to 84%
- Sensitivity/specificity (265 test patients)
- 0.80/0.74
- AUC (95% CI) (265 test patients)
- 0.81 (0.76-0.87)
Further findings
Decision curve analysis
- Higher clinical utility of the model, threshold probability range
- 30% to 84%
Unsupervised clustering
- Unsupervised clustering identified high-risk patients
Original publication
Machine Learning Identifies Metabolic Dysfunction–Associated Steatotic Liver Disease in Patients With Diabetes Mellitus. J Clin Endocrinol Metab. Published 8 February 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →