Machine Learning Based Hospital Mortality Prediction Using Synthetic Minority Oversampling Technique

This paper aims to assess the efficiency, adaptiveness, and feasibility of various Machine Learning Algorithms for predicting mortality rates inside the hospital. The predictors and factors associated with in-hospital mortality rates in Intensive Care Units (ICUs) and other emergency sections have been poorly organized and categorized. Various Data Mining Techniques, and Machine Learning algorithms like Random Forest, XG-Boost, and Decision Tree, have been employed over a legitimate public dataset of various patients and their performance is measured and compared within and with existing works.