Interpretable machine learning model for predicting covert hepatic encephalopathy in patients with cirrhosis: a...

Area of Science:

• Hepatology
• Neuroscience
• Artificial Intelligence

Background:

• Covert hepatic encephalopathy (CHE) affects up to 50% of cirrhosis patients, often remaining undiagnosed due to subclinical symptoms and diagnostic tool limitations.
• Existing diagnostic methods for CHE are subjective, have variable sensitivity, and lack accessibility, hindering timely intervention.

Purpose of the Study:

• To develop and validate interpretable machine learning (ML) models for predicting CHE in cirrhosis patients.
• To utilize multidimensional clinical and lifestyle data for accurate CHE prediction.

Main Methods:

• A retrospective study of 503 cirrhosis patients from 16 Chinese medical centers.
• CHE diagnosis via psychometric hepatic encephalopathy score and EncephalApp Stroop tests.
• Recursive feature elimination, Pearson's correlation, and eight ML models (including LightGBM, RF, XGBoost) were used for prediction and interpretation via SHAP values.

Main Results:

• The LightGBM model achieved an AUC of 0.810 (training) and 0.710 (validation), outperforming RF and XGBoost in diagnostic performance.
• Key predictors identified by SHAP analysis include lower MMSE scores, older age, hypoalbuminemia, lack of computer usage, and elevated blood urea nitrogen.
• Decision curve analysis confirmed LightGBM's superior diagnostic utility.

Conclusions:

• A novel ML-based approach, particularly LightGBM, offers a promising, interpretable method for predicting CHE in cirrhotic patients.
• Identified clinical and demographic predictors can aid in early CHE detection and personalized patient management.
• This approach has the potential to improve outcomes for patients at high risk of CHE.