The invention relates to a
curative effect prediction system for MTX treatment of JIA before administration and an establishment method thereof. According to the establishing method, the characteristic variable subset of the detection items of the JIA patient is screened out, the
machine learning
algorithm is used for establishing the
curative effect prediction system for the characteristic variable subset, the AUC reaches 97%, the corresponding prediction sensitivity, specificity and accuracy are all 90% or above, and the prediction performance is remarkably improved compared with a
system established through a traditional method. According to the
curative effect prediction system, expensive
genotype detection is not needed during curative effect prediction, prediction of the curative effect model can be completed only through conventional necessary examination items of a patient, extra
payment detection is not needed, the patient does not need to wait for a long time, and the curative effect can be predicted only after conventional detection is completed on the same day of treatment. After a doctor sees a prediction result in time, a
drug administration decision can be made to apatient immediately. The curative effect prediction
system for MTX treatment of JIA before administration established by the establishment method is an effective tool which is simple, convenient, easyto use, efficient and capable of accurately predicting the MTX curative effect of a patient at an early stage.