"Predicting delayed methotrexate elimination in pediatric acute lymphoblastic leukemia patients: an innovative web-based machine learning tool developed through a multicenter, retrospective analysis"

作者全名："Jian, Chang; Chen, Siqi; Wang, Zhuangcheng; Zhou, Yang; Zhang, Yang; Li, Ziyu; Jian, Jie; Wang, Tingting; Xiang, Tianyu; Wang, Xiao; Jia, Yuntao; Wang, Huilai; Gong, Jun"

作者地址："[Jian, Chang; Zhang, Yang; Li, Ziyu; Jian, Jie; Wang, Tingting; Wang, Xiao] Chongqing Med Univ, Coll Med Informat, Chongqing, Peoples R China; [Chen, Siqi] Chongqing Med Univ, Coll Pharm, Chongqing, Peoples R China; [Wang, Zhuangcheng] Chongqing Med Univ, Big Data Engn Ctr, Childrens Hosp, Chongqing, Peoples R China; [Zhou, Yang] Nantong Univ, Dept Med, Affiliated Hosp, Nantong, Jiangsu, Peoples R China; [Xiang, Tianyu; Jia, Yuntao] Chongqing Med Univ, Dept Pharm, Childrens Hosp, Chongqing, Peoples R China; [Wang, Huilai; Gong, Jun] Chongqing Med Univ, Univ Town Hosp, Dept Informat Ctr, Chongqing, Peoples R China"

通信作者："Wang, HL; Gong, J (通讯作者)，Chongqing Med Univ, Univ Town Hosp, Dept Informat Ctr, Chongqing, Peoples R China."

来源：BMC MEDICAL INFORMATICS AND DECISION MAKING

ESI学科分类：CLINICAL MEDICINE

WOS号：WOS:001040191600002

JCR分区：Q2

影响因子：3.3

年份：2023

卷号：23

期号：1

开始页：　

结束页：　

文献类型：Article

关键词：Methotrexate; Delayed metabolism; Acute lymphoblastic leukemia; Machine learning

摘要："BackgroundHigh-dose methotrexate (HD-MTX) is a potent chemotherapeutic agent used to treat pediatric acute lymphoblastic leukemia (ALL). HD-MTX is known for cause delayed elimination and drug-related adverse events. Therefore, close monitoring of delayed MTX elimination in ALL patients is essential.ObjectiveThis study aimed to identify the risk factors associated with delayed MTX elimination and to develop a predictive tool for its occurrence.MethodsPatients who received MTX chemotherapy during hospitalization were selected for inclusion in our study. Univariate and least absolute shrinkage and selection operator (LASSO) methods were used to screen for relevant features. Then four machine learning (ML) algorithms were used to construct prediction model in different sampling method. Furthermore, the performance of the model was evaluated using several indicators. Finally, the optimal model was deployed on a web page to create a visual prediction tool.ResultsThe study included 329 patients with delayed MTX elimination and 1400 patients without delayed MTX elimination who met the inclusion criteria. Univariate and LASSO regression analysis identified eleven predictors, including age, weight, creatinine, uric acid, total bilirubin, albumin, white blood cell count, hemoglobin, prothrombin time, immunological classification, and co-medication with omeprazole. The XGBoost algorithm with SMOTE exhibited AUROC of 0.897, AUPR of 0.729, sensitivity of 0.808, specificity of 0.847, outperforming the other models. And had AUROC of 0.788 in external validation.ConclusionThe XGBoost algorithm provides superior performance in predicting the delayed elimination of MTX. We have created a prediction tool to assist medical professionals in predicting MTX metabolic delay."

基金机构：　

基金资助正文：