P1575 - Uncovering Hidden Phenotypes and Referral Bias in MASLD Screening: A Combined Latent Class and Explainable Machine Learning Approach

Safia Mohamed, MD¹, Dimitri Melki, MD², Pranav Ramamurthy, MBBS, MD³, Victoria Caruso, DO¹, Mithil Gowda Suresh, MD⁴, Yesenia Greeff, MD⁵
1University of Massachusetts Chan Medical School - Baystate Health, Springfield, MA; 2University of Massachusetts Chan Medical School - Baystate Health, Windsor, CT; 3University of Massachusetts Chan Medical School-Baystate Medical Center, Springfield, MA; 4St. Vincent's Hospital, Chicopee, MA; 5University of Massachusetts Chan Medical School - Baystate Health, Northampton, MA

Introduction: MASLD risk stratification in patients with Type 2 Diabetes Mellitus (T2DM) is often guided by fibrosis indices such as FIB-4. However, substantial heterogeneity in clinical profiles and referral patterns may obscure high-risk patients. We hypothesized that latent phenotypes exist within the T2DM population and that nonclinical factors influence specialist referral decisions.

Methods: We retrospectively analyzed 1,149 adult patients with T2DM from a multi-provider outpatient network in 2021. In Phase 1, we used Latent Class Analysis (LCA) on clinical and demographic data (e.g., age, sex, BMI, A1c, FIB-4, AST, ALT, platelets, provider type, race) to identify hidden patient phenotypes. In Phase 2, we trained an XGBoost classifier to predict referral to GI/Hepatology, and used SHapley Additive exPlanations (SHAP) to interpret feature contributions across LCA-defined classes.

Results: LCA identified four distinct patient phenotypes with varying MASLD risk and demographic profiles. One class, characterized by older males with elevated FIB-4 and A1c, showed high referral rates. In contrast, a phenotype dominated by younger females with moderate FIB-4 was under-referred despite risk factors.

The XGBoost model achieved strong performance (AUC = 0.81), and SHAP analysis revealed that provider type and race were among the top five predictors of referral, alongside FIB-4, age, and A1c. When stratified by LCA class, disparities emerged: race and provider type had outsized influence in lower-referral phenotypes, suggesting systemic bias.

Discussion: Combining LCA and explainable ML highlights important gaps in MASLD referral practices. Clinical risk alone does not determine referral, and subgroup analyses reveal inequities by race and provider type. These findings underscore the need for targeted interventions that align referral decisions with evidence-based risk rather than provider or demographic heuristics.

Disclosures:
Safia Mohamed indicated no relevant financial relationships.
Dimitri Melki indicated no relevant financial relationships.
Pranav Ramamurthy indicated no relevant financial relationships.
Victoria Caruso indicated no relevant financial relationships.
Mithil Gowda Suresh indicated no relevant financial relationships.
Yesenia Greeff indicated no relevant financial relationships.

Safia Mohamed, MD¹, Dimitri Melki, MD², Pranav Ramamurthy, MBBS, MD³, Victoria Caruso, DO¹, Mithil Gowda Suresh, MD⁴, Yesenia Greeff, MD⁵. P1575 - Uncovering Hidden Phenotypes and Referral Bias in MASLD Screening: A Combined Latent Class and Explainable Machine Learning Approach, ACG 2025 Annual Scientific Meeting Abstracts. Phoenix, AZ: American College of Gastroenterology.