[Retracted] A Prediction Model for Cognitive Impairment Risk in Colorectal Cancer after Chemotherapy Treatment

Figure 2

Predictive model selection and predictor screening. (a) The random forest model. The graph on the left shows the importance of each factor in the random forest model, and the ROC curve demonstrates the accuracy of the random forest model (). (b, c) LASSO analysis conducted 1000 times. The factors were included in the logistic regression model to obtain a pattern diagram of the AUC for the number of occurrences. The model with 14 predictors had good predictive power (). (d) A prediction model developed using the SVM method with the highest prediction accuracy when 13 predictive factors are included ().

(a)

(b)

(c)

(d)