Deep learning-based predictions added to clinical parameters for B-mode ultrasound identification of at-risk MASLD yielded modest incremental diagnostic value (AUROC 0.73 vs 0.72 without DLPs).
Observational (n=205)
Do deep learning-based predictions from B-mode ultrasound improve the identification of increased fibrosis risk in patients with MASLD when added to clinical parameters?
Deep learning predictions from B-mode ultrasound add only modest incremental value to clinical parameters like FIB-4 for identifying increased fibrosis risk in MASLD.
OBJECTIVE: The prevalence of metabolic dysfunction-associated steatotic liver disease (MASLD) continues to rise, underscoring the need for tools to stratify individual risk of disease progression. We evaluated whether logistic regression models augmented by deep learning-based predictions (DLPs) can improve the B-mode ultrasound-based identification of at-risk MASLD, defined as patients with increased fibrosis risk. METHODS: We retrospectively analyzed 205 patients with a total of 636 ultrasound images. We developed a model that reproduces the LSM-based dichotomous fibrosis risk classification using clinical parameters and ultrasound image-derived deep learning pipelines. Patients were classified by same-day liver stiffness measurement (LSM) (<8 kPa: low fibrosis risk; ≥8 kPa: increased fibrosis risk). We assessed the incremental value of DLPs when added to the parameters sex, age, BMI, diabetes mellitus type 2 status and the fibrosis-4 score (FIB-4) based on accuracy, AUROC, and related statistics. RESULTS: The logistic regression model combining the clinical parameters and the DLPs achieved acceptable performance with an AUROC of 0.73 and a test accuracy of 68%. The same model without DLPs showed an AUROC of 0.72 and a test accuracy of 61%. Including FIB-4 improved performance further (AUROC 0.92, accuracy 88%). Models based solely on image data demonstrated limited diagnostic performance. CONCLUSION: B-mode ultrasound provides a weak fibrosis-related signal, yielding limited diagnostic performance. Meaningful discrimination required the incorporation of clinical parameters, with FIB-4 offering the greatest improvement among the parameters assessed. Deep learning predictions added only modest incremental value. Prospective validation is needed to clarify clinical utility.
Stansch et al. (Mon,) conducted a observational in Metabolic Dysfunction-Associated Steatotic Liver Disease (MASLD) (n=205). Logistic regression models augmented by deep learning-based predictions (DLPs) on B-mode ultrasound vs. Logistic regression models without DLPs (clinical parameters only) was evaluated on Identification of at-risk MASLD (increased fibrosis risk defined as liver stiffness measurement ≥8 kPa). Deep learning-based predictions added to clinical parameters for B-mode ultrasound identification of at-risk MASLD yielded modest incremental diagnostic value (AUROC 0.73 vs 0.72 without DLPs).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: