Background: Metabolic dysfunction–associated steatotic liver disease (MASLD) affects up to 70% of individuals with type 2 diabetes (T2D) and is a major predictor of liver-related and cardiovascular complications. Advanced fibrosis (≥F3) is the strongest prognostic marker, yet current non-invasive tools underperform in diabetes care. Explainable artificial intelligence (AI) offers an opportunity to improve diagnostic accuracy and clinician trust. Objective: To evaluate the feasibility, usability, and preliminary effectiveness of FibroX, an explainable AI tool designed to detect MASLD-associated advanced fibrosis in adults with T2D during simulated clinical encounters. Methods: This 12-month provider-level, randomized crossover pilot trial will enroll ≥36 primary care clinicians managing adults with T2D. Each clinician will complete two simulation periods (FibroX-enabled care vs usual care) separated by a one-week washout. Outcomes include feasibility (recruitment ≥70%, completion ≥85%), usability (System Usability Scale ≥70), diagnostic accuracy (sensitivity, specificity, AUROC), and implementation metrics using the RE-AIM framework. Data will be analyzed using McNemar’s test and mixed-effects logistic regression. Results: Feasibility and usability data will be available by month 3, diagnostic accuracy analyses by month 6, and implementation outcomes by month 9. Final synthesis and interpretation are expected by month 12 to inform a future multi-center trial. Conclusions: This pilot will generate critical evidence on integrating explainable AI into diabetes care workflows for MASLD screening. If successful, FibroX could enable guideline-concordant triage, reduce missed diagnoses, and improve long-term outcomes for patients with T2D. Clinical Trial: ClinicalTrials.gov NCT07305324
Njei et al. (Sun,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: