Interpretable Machine Learning Model for Predicting Covert Hepatic Encephalopathy in Patients with Cirrhosis: A Multicenter Study

Yilong Liu¹Kai Ding¹Yifan Qiu²Peiqin Wang¹Ruoyao Wang²Xin Zeng^3*Chuan Yin^1*

• ¹Shanghai Changzheng Hospital, Huangpu, China
• ²Naval Medical University, Shanghai, China
• ³Department of Gastroenterology, Shanghai East Hospital, Tongji University School of Medicine, shanghai, China

Background and Aim: Covert hepatic encephalopathy (CHE) is a neurocognitive complication affecting 40.9–50.4% of patients with cirrhosis, often remaining undiagnosed due to its subclinical nature and limitations of diagnostic tools. Existing tools are constrained by subjectivity, variable sensitivity, and limited accessibility. This study aims to develop and validate interpretable machine learning (ML) models for predicting CHE in cirrhotic patients using multidimensional clinical and lifestyle data. Methods: This retrospective study included 503 patients with liver cirrhosis from 16 medical centers in China. CHE was diagnosed using the psychometric hepatic encephalopathy score and EncephalApp Stroop tests. Recursive Feature Elimination and Pearson correlation analysis were used for feature selection. Eight ML models were implemented to predict CHE. Performance was assessed via AUC, sensitivity, specificity, and decision curve analysis. The SHapley Additive exPlanations (SHAP) values interpreted the optimal model. Results: The LightGBM model achieved the highest AUC of 0.810 in the training set and 0.710 in the validation set. Decision curve analysis showed that LightGBM had better diagnostic performance than RF and XGBoost. The SHAP analysis identified key predictors of CHE, including lower MMSE scores, older age, hypoalbuminemia, lack of prior computer usage, and higher blood urea nitrogen levels. Conclusions: This study presents a novel ML-based approach for predicting CHE in cirrhotic patients, with LightGBM offering the best balance of performance and interpretability. The identified clinical and demographic predictors could facilitate early CHE detection and personalized management, ultimately improving outcomes for this high-risk population.