Lipids & metabolic liver disease
Computed tomography-based body composition indicative of diabetes after hypertriglyceridemic acute pancreatitis
Authors' conclusion
The association between body composition and PPDM-A provides insight into the potential pathogenesis of PPDM-A. Our model is feasible for reliably predicting PPDM-A in the early stages of AP and enables early intervention in patients with potential PPDM-A.
Study context
- Population
- Patients with hypertriglyceridemic acute pancreatitis (HTGP); 65 with PPDM-A, 100 without
- Participants
- 165 patients
- Exposure
- Support vector machine (SVM) vs linear discriminant analysis (LDA) vs logistic regression (LR) prediction models for PPDM-A
- Outcome
- Prediction of post-acute pancreatitis prediabetes/DM (PPDM-A)
Methodological detailsmachine learning prediction model
- Machine learning prediction model
Main finding
As reported in the abstract
AUC for predicting PPDM-A
| Group | AUC |
|---|---|
| SVM | 0.796 |
| LDA | 0.783 |
| LR | 0.745 |
AUC
SVM0.796
LDA0.783
LR0.745
Observational data: associations, not effects.
Further findings
Body composition parameters discriminating PPDM-A vs non-PPDM-A
- Significant body composition-related parameters, of 84
- 15
Original publication
Computed tomography-based body composition indicative of diabetes after hypertriglyceridemic acute pancreatitis. Diabetes Res Clin Pract. Published 18 September 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →