Development and validation of machine learning models for nonalcoholic fatty liver disease.

BACKGROUND: Nonalcoholic fatty liver disease (NAFLD) had become the most prevalent liver disease worldwide. Early diagnosis could effectively reduce NAFLD-related morbidity and mortality. This study aimed to combine the risk factors to develop and validate a novel model for predicting NAFLD. METHODS: We enrolled 578 participants completing abdominal ultrasound into the training set. The least absolute shrinkage and selection operator (LASSO) regression combined with random forest (RF) was conducted to screen significant predictors for NAFLD risk. Five machine learning models including logistic regression (LR), RF, extreme gradient boosting (XGBoost), gradient boosting machine (GBM), and support vector machine (SVM) were developed. To further improve model performance, we conducted hyperparameter tuning with train function in Python package 'sklearn'. We included 131 participants completing magnetic resonance imaging into the testing set for external validation. RESULTS: There were 329 participants with NAFLD and 249 without in the training set, while 96 with NAFLD and 35 without were in the testing set. Visceral adiposity index, abdominal circumference, body mass index, alanine aminotransferase (ALT), ALT/AST (aspartate aminotransferase), age, high-density lipoprotein cholesterol (HDL-C) and elevated triglyceride (TG) were important predictors for NAFLD risk. The area under curve (AUC) of LR, RF, XGBoost, GBM, SVM were 0.915 [95% confidence interval (CI): 0.886-0.937], 0.907 (95% CI: 0.856-0.938), 0.928 (95% CI: 0.873-0.944), 0.924 (95% CI: 0.875-0.939), and 0.900 (95% CI: 0.883-0.913), respectively. XGBoost model presented the best predictive performance, and its AUC was enhanced to 0.938 (95% CI: 0.870-0.950) with further parameter tuning. CONCLUSIONS: This study developed and validated five novel machine learning models for NAFLD prediction, among which XGBoost presented the best performance and was considered a reliable reference for early identification of high-risk patients with NAFLD in clinical practice.

Noninvasive Diagnostic Technique for Nonalcoholic Fatty Liver Disease Based on Features of Tongue Images.

OBJECTIVE: To investigate a new noninvasive diagnostic model for nonalcoholic fatty liver disease (NAFLD) based on features of tongue images. METHODS: Healthy controls and volunteers confirmed to have NAFLD by liver ultrasound were recruited from China-Japan Friendship Hospital between September 2018 and May 2019, then the anthropometric indexes and sampled tongue images were measured. The tongue images were labeled by features, based on a brief protocol, without knowing any other clinical data, after a series of corrections and data cleaning. The algorithm was trained on images using labels and several anthropometric indexes for inputs, utilizing machine learning technology. Finally, a logistic regression algorithm and a decision tree model were constructed as 2 diagnostic models for NAFLD. RESULTS: A total of 720 subjects were enrolled in this study, including 432 patients with NAFLD and 288 healthy volunteers. Of them, 482 were randomly allocated into the training set and 238 into the validation set. The diagnostic model based on logistic regression exhibited excellent performance: in validation set, it achieved an accuracy of 86.98%, sensitivity of 91.43%, and specificity of 80.61%; with an area under the curve (AUC) of 0.93 [95% confidence interval (CI) 0.68-0.98]. The decision tree model achieved an accuracy of 81.09%, sensitivity of 91.43%, and specificity of 66.33%; with an AUC of 0.89 (95% CI 0.66-0.92) in validation set. CONCLUSIONS: The features of tongue images were associated with NAFLD. Both the 2 diagnostic models, which would be convenient, noninvasive, lightweight, rapid, and inexpensive technical references for early screening, can accurately distinguish NAFLD and are worth further study.

Atherogenic index of plasma combined with waist circumference and body mass index to predict metabolic-associated fatty liver disease.

BACKGROUND: Early identification of metabolic-associated fatty liver disease (MAFLD) is urgent. Atherogenic index of plasma (AIP) is a reference predictor of obesity-related diseases, but its predictive value for MAFLD remains unclear. No studies have reported whether its combination with waist circumference (WC) and body mass index (BMI) can improve the predictive performance for MAFLD. AIM: To systematically explore the relationship between AIP and MAFLD and evaluate its predictive value for MAFLD and to pioneer a novel noninvasive predictive model combining AIP, WC, and BMI while validating its predictive performance for MAFLD. METHODS: This cross-sectional study consecutively enrolled 864 participants. Multivariate logistic regression analysis and receiver operating characteristic curve were used to evaluate the relationship between AIP and MAFLD and its predictive power for MAFLD. The novel prediction model A-W-B combining AIP, WC, and BMI to predict MAFLD was established, and internal verification was completed by magnetic resonance imaging diagnosis. RESULTS: Subjects with higher AIP exhibited a significantly increased risk of MAFLD, with an odds ratio of 12.420 (6.008-25.675) for AIP after adjusting for various confounding factors. The area under receiver operating characteristic curve of the A-W-B model was 0.833 (0.807-0.858), which was significantly higher than that of AIP, WC, and BMI (all P < 0.05). Subgroup analysis illustrated that the A-W-B model had significantly higher area under receiver operating characteristic curves in female, young and nonobese subgroups (all P < 0.05). The best cutoff values for the A-W-B model to predict MAFLD in males and females were 0.5932 and 0.4105, respectively. Additionally, in the validation set, the area under receiver operating characteristic curve of the A-W-B model to predict MAFLD was 0.862 (0.791-0.916). The A-W-B level was strongly and positively associated with the liver proton density fat fraction (r = 0.630, P < 0.001) and significantly increased with the severity of MAFLD (P < 0.05). CONCLUSION: AIP was strongly and positively associated with the risk of MAFLD and can be a reference predictor for MAFLD. The novel prediction model A-W-B combining AIP, WC, and BMI can significantly improve the predictive ability of MAFLD and provide better services for clinical prediction and screening of MAFLD.