Development and Internal Validation of Machine Learning Algorithms for Determining Sodium Valproate Concentrations below the Standard Level Using a Risk Prediction Model of Children with Epilepsy

Figure 4

ROC for different machine learning algorithms and establishment of the nomogram. (a) ROC curves indicating the accuracy of the random forest (RF), support vector machine (SVM), gradient boosting machine (GBM), generalized linear model (GLM), and neural network (NNET) in the development group. (b) ROC curves indicating the accuracy of the RF, SVM, GBM, GLM, and NNET in the validation group. (c) Prediction of sodium valproate concentrations below the standard level by nomogram in the development group.

(a)

(b)

(c)