Endometrial cancer (EC) is a type of cancer that has in recent years become one of the most common and deadly types of cancers among women worldwide. A rapid diagnosis has been shown to be crucial in the survival of patients with EC. In recent years, the use of machine learning (ML), for the diagnosis of EC has increased, allowing for earlier diagnosis than without ML. Data from 94 patients had been used to train three MLs, to discover which of them produce the best results and whether they could be further used for the diagnosis EC. The MLs tested were logistic regression, random forest and XGBoost. The performance of each of the MLs was measured using balanced accuracy and by generating a Receiver Operating Characteristic (ROC) curve. Of the three MLs, XGBoost performed the best, with a median balanced accuracy of 0.63 and median ROCvalue of 0.64. As XGBoost had not previously been used in the diagnosis of EC, these findings show the possibility of further testing XGBoost as a diagnostic tool for EC. The highest performing XGBoost model then generated a set of the micro RNAs (miRNA) with the highest importance values. These miRNAs were then inputted into miRNet, tofind the most significant pathways connected to the miRNAs. Based on a biological interpretation of the enrichment analysis, the pathways with the lowest false discovery rate (FDR), and the most significance, were Pathways in cancer, with RNA transport and Prostate cancer. The pathway to EC was still present and had an FDR lower than 0.05, making it a significant connection.