JMIR Publications

ABSTRACT

Background:

Steatotic liver disease (SLD) is highly prevalent and noninvasive identification of patients with significant fibrosis remains a clinical challenge.

Objective:

We used explainable artificial intelligence (XAI) to improve SLD risk stratification while maintaining transparency necessary for clinical adoption.

Methods:

We developed and internally validated an XAI‑based machine‑learning framework to predict significant fibrosis in a U.S. population‑based dataset. Forty‑three routinely available clinical, demographic, anthropometric, laboratory, and lifestyle variables were included. After preprocessing and imputation, data were split into training (80%) and testing (20%) sets. Synthetic Minority Oversampling Technique (SMOTE) addressed class imbalance in the training set. Logistic regression, random forest, support‑vector machine, XGBoost, k‑nearest neighbors, naïve Bayes, artificial neural network, and a stacked ensemble were trained and evaluated. Performance metrics included accuracy, precision, recall, F1 score, Cohen’s kappa, and area under the receiver‑operating‑characteristic curve (AUROC). Global and local model interpretability were assessed using feature importance, Shapley Additive exPlanations (SHAP) values, individual conditional expectation (ICE) plots, and individualized explanations.

Results:

Among 7,056 participants, 716 (10.1%) had significant fibrosis. XGBoost achieved the highest discrimination (AUROC, 0.79), followed by random forest (AUROC, 0.78) and logistic regression (AUROC, 0.77). Logistic regression and naïve Bayes demonstrated the highest sensitivity (0.65 and 0.55, respectively). Across models, waist circumference, body‑mass index, cardiovascular comorbidity, sex, HbA1c, and liver enzymes were the most influential predictors.

Conclusions:

In this population‑based cohort, XAI predicted significant fibrosis with moderate discrimination and provided transparent, patient‑level explanations. External validation is needed before clinical implementation. Clinical Trial: Not Applicable