Supplementary files and source codes

  #All attached source codes and result files were packed in “” for reference.
  #This file contains raw clinical dataset.
  #This folder contains all modeling codes based on Python and R language. After running codes, the results will be saved in the “/result” folder including AUC values, importance, prediction values and true values. The three “.py” files named with “_model” are used to build online predictive tools for HTML display.
  #“*threshold” files contain threshold of sampling in each model.
  #“*data” files contain predicted output, true value, AUC and importance of each feature. In sheet “data”, the column stand for features while rows stand for predicted values during sampling. In sheet “y_testdata”, the column stands for true values in one sampling. In sheet “y_prodata”, the column stands for predicted values in the corresponding “y_testdata” sheet.
  #“allmodel_auc1030.csv” file contains the auc values generated by the nine models used in the 20 data resampling process, the column stands for the prediction results corresponding to the header model, and the rows stands for the results of one data resampling.
  #“heatmap.xlsx” contains predicted values of nine models and true values.

Your E-mail:

  I acknowledge and agree to the terms above and in the Ckd Prediction System Privacy Policy.