An interpretability model for syndrome differentiation of HBV-ACLF in traditional Chinese medicine using small-sample imbalanced data

作     者：ZHOU Zhan PENG Qinghua XIAO Xiaoxia ZOU Beiji LIU Bin GUO Shuixia 周展;彭清华;肖晓霞;邹北骥;刘彬;郭水霞

作者机构：School of InformaticsHunan University of Chinese MedicineChangshaHunan 410208China School of Traditional Chinese MedicineHunan University of Chinese MedicineChangshaHunan 410208China School of Mathematics and StatisticsHunan Normal UniversityChangshaHunan 410081China 

基　　金：Key research project of Hunan Provincial Administration of Traditional Chinese Medicine(A2023048) Key Research Foundation of Education Bureau of Hunan Province,China(23A0273) 

出 版 物：《Digital Chinese Medicine》 (数字中医药（英文）)

年 卷 期：2024年第7卷第2期

页      码：137-147页

摘      要：Objective Clinical medical record data associated with hepatitis B-related acute-on-chronic liver failure(HBV-ACLF)generally have small sample sizes and a class ***,most machine learning models are designed based on balanced data and lack *** study aimed to propose a traditional Chinese medicine(TCM)diagnostic model for HBV-ACLF based on the TCM syndrome differentiation and treatment theory,which is clinically interpretable and highly *** We collected medical records from 261 patients diagnosed with HBV-ACLF,including three syndromes:Yang jaundice(214 cases),Yang-Yin jaundice(41 cases),and Yin jaundice(6 cases).To avoid overfitting of the machine learning model,we excluded the cases of Yin *** data standardization and cleaning,we obtained 255 relevant medical records of Yang jaundice and Yang-Yin *** address the class imbalance issue,we employed the oversampling method and five machine learning methods,including logistic regression(LR),support vector machine(SVM),decision tree(DT),random forest(RF),and extreme gradient boosting(XGBoost)to construct the syndrome diagnosis *** study used precision,F1 score,the area under the receiver operating characteristic(ROC)curve(AUC),and accuracy as model evaluation *** model with the best classification performance was selected to extract the diagnostic rule,and its clinical significance was thoroughly ***,we proposed a novel multiple-round stable rule extraction(MRSRE)method to obtain a stable rule set of features that can exhibit the model’s clinical *** The precision of the five machine learning models built using oversampled balanced data exceeded *** these models,the accuracy of RF classification of syndrome types was 0.92,and the mean F1 scores of the two categories of Yang jaundice and Yang-Yin jaundice were 0.93 and 0.94,***,the AUC was *** extraction rules of the RF syn

主 题 词：Traditional Chinese medicine(TCM) Hepatitis B-related acute-on-chronic liver failure(HBV-ACLF) Imbalanced data Random forest(RF) Interpretability 

学科分类：0711[理学-心理学类] 07[理学] 08[工学] 081101[081101] 0811[工学-水利类] 071102[071102] 081103[081103] 

核心收录：

D　O　I：10.1016/j.dcmed.2024.09.005

馆 藏 号：203144076...