Accepted for/Published in: JMIR Research Protocols
Date Submitted: Dec 28, 2025
Date Accepted: Apr 13, 2026
Date Submitted to PubMed: Apr 13, 2026
An Explainable Artificial Intelligence Tool (FibroX) for Detecting Advanced Liver Fibrosis in Type 2 Diabetes: Protocol for a Pilot Crossover Trial
ABSTRACT
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
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.