Predictive Model of Oxaliplatin-induced Liver Injury Based on Artificial Neural Network and Logistic Regression  

作　　者：Rui Huang Yuanxuan Cai Yisheng He Zaoqin Yu Li Zhao Tao Wang Xiaofang Shangguan Yuhang Zhao Zherui Chen Yunzhou Chen Chengliang Zhang 

机构地区：[1]School of Pharmacy,Tongji Medical College,Huazhong University of Science and Technology,Wuhan,Hubei,China [2]Ciechanover Institute of Precision and Regenerative Medicine,School of Medicine,The Chinese University of Hong Kong-Shenzhen,Shenzhen,Guangdong,China [3]Tongji Hospital,Tongji Medical College,Huazhong University of Science and Technology,Wuhan,Hubei,China [4]Hubei Center for Adverse Drug Reaction/Adverse Drug Event Monitoring,Wuhan,Hubei,China [5]National Center for Adverse Drug Reaction Monitoring,Beijing,China [6]School of Statistics and Mathematics,Zhongnan University of Economics and Law,Wuhan,Hubei,China

出　　处：《Journal of Clinical and Translational Hepatology》2023年第7期1455-1464,共10页临床与转化肝病杂志（英文版）

基　　金：the Medical Ethics Committee of Tongji Hospital,Tongji Medical College,Huazhong University of Science and Technology(No.TJIRB20160504).

摘　　要：Background and Aims:Identifying potential high-risk groups of oxaliplatin-induced liver injury(OILI)is valuable,but tools are lacking.So artificial neural network(ANN)and logistic regression(LR)models will be developed to predict the risk of OILI.Methods:The medical information of patients treated with oxaliplatin between May and November 2016 at 10 hospitals was collected prospectively.We used the updated Roussel Uclaf causality assessment method(RUCAM)to identify cases of OILI and summarized the patient and medication characteristics.Furthermore,the ANN and LR models for predicting the risk of OILI were developed and evaluated.Results:The incidence of OILI was 3.65%.The median RUCAM score with interquartile range was 6(4,9).The ANN model performed similarly to the LR model in sensitivity,specificity,and accuracy.In discrimination,the area under the curve of the ANN model was larger(0.920>0.833,p=0.019).In calibration,the ANN model was slightly improved.The important predictors of both models overlapped partially,including age,chemotherapy regimens and cycles,single and total dose of OXA,glucocorticoid drugs,and antihistamine drugs.Conclusions:When the discriminative and calibration ability was given priority,the ANN model outperformed the LR model in predicting the risk of OILI.Other chemotherapy drugs in oxaliplatin-based chemotherapy regimens could have different degrees of impact on OILI.We suspected that OILI may be idiosyncratic,and chemotherapy dose factors may be weakly correlated.Decision making on prophylactic medications needs to be carefully considered,and the actual preventive effect needed to be supported by more evidence.

关 键 词：OXALIPLATIN Liver injury Adverse drug reaction RUCAM PHARMACOVIGILANCE 

分 类 号：R575[医药卫生—消化系统] TP183[医药卫生—内科学]