Risk prediction for delayed clearance of high-dose methotrexate in pediatric hematological malignancies by machine learning

This study aimed to establish a predictive model to identify children with hematologic malignancy at high risk for delayed clearance of high-dose methotrexate (HD-MTX) based on machine learning. A total of 205 patients were recruited. Five variables (hematocrit, risk classification, dose, SLC19A1 rs2838958, sex) and three variables (SLC19A1 rs2838958, sex, dose) were statistically significant in univariable analysis and, separately, multivariate logistic regression. The data was randomly split into a training cohort and a validation cohort. A nomogram for prediction of delayed HD-MTX clearance was constructed using the three variables in the training dataset and validated in the validation dataset. Five machine learning algorithms (cart classification and regression trees, naive Bayes, support vector machine, random forest, C5.0 decision tree) combined with different resampling methods were used for model building with five or three variables. When developed machine learning models were evaluated in the validation dataset, the C5.0 decision tree combined with the synthetic minority oversampling technique (SMOTE) using five variables had the highest area under the receiver operating characteristic curve (AUC 0.807 [95% CI 0.724-0.889]), a better performance than the nomogram (AUC 0.69 [95% CI 0.594-0.787]). The results support potential clinical application of machine learning for patient risk classification.

Automated summary

This study aimed to establish a predictive model using machine learning to identify children with hematologic malignancy at high risk for delayed clearance of high-dose methotrexate (HD-MTX). Five and three variables were found to be statistically significant in univariable and multivariate analysis. The C5.0 decision tree combined with SMOTE using five variables showed the highest AUC value (0.807).