Interpretable machine learning model for predicting covert hepatic encephalopathy in patients with cirrhosis: a
Yilong Liu1, Kai Ding1, Yifan Qiu2
1Department of Gastroenterology, Changzheng Hospital, Naval Medical University, Shanghai, China.
Insights
Machine learning models can predict covert hepatic encephalopathy (CHE) in cirrhosis patients. The LightGBM model showed strong performance, identifying key predictors like MMSE scores and age for early detection.
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.
Background And Aim:
Covert hepatic encephalopathy (CHE) is a neurocognitive complication affecting 40.9-50.4% of patients with cirrhosis. It often remains undiagnosed owing to its subclinical nature and the limitations of existing diagnostic tools, which 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 patients with cirrhosis 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's 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 are interpreted by the optimal model.
Results:
The light gradient boosting machine (LightGBM) model achieved the highest area under the receiver operating characteristic (ROC) curve (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 random forest (RF) and eXtreme gradient boosting (XGBoost). The SHAP analysis identified key predictors of CHE, including lower Mini-Mental State Examination (MMSE) scores, older age, hypoalbuminemia, lack of prior computer usage, and higher blood urea nitrogen levels.
Conclusion:
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.
