ABSTRACT
The main objective of this chapter is to develop an artificial intelligence (AI) or machine learning (ML) technique-based disease prediction model, i.e., classification and regression tree (CART), for predicting the number of lymph node dissection among endometrial cancer (EC) patients. Also, this chapter aims to compare the CART model with the conventional regression models. Data for this study were collected from a local hospital on 170 EC patients with their covariates. We found that CART model is able to predict the number of lymph node dissection for the EC patients with an accuracy of 95.9% based on the selected covariates and validated by receiver operating characteristics (ROC) curve. It is also found that the CART model (R2 = 0.745) gives better performance than the multiple regression model (R2 = 0.334) by explaining the variations in the number of lymph node dissection with the existing information from its covariates. The covariates such as tumour size and early detected status from lymph node sampling were found as two significant predictors to decide the number of lymph node need to dissect in order to avoid the critical conditions and to take appropriate remedies or treatment at an early stage to optimize their loss, in terms of time, money and life.
