Sepsis is a life-threatening medical condition that, if not treated promptly, can result in tissue damage, organ failure, and death. According to the Centers for Disease Control, about 270,000 individuals die of sepsis in the United States each year. Further, sepsis expenditures accounted for 13% of total US hospital costs in 2013, totaling more than $24 billion.
Our project objectives were to determine if Machine Learning algorithms could reliably predict hospital stay duration for patients with sepsis. We then applied the following analysis methods: Linear Regression, Random Forest, K-Nearest Neighbors, Neural Networks, XGBoost, and lightGBM during our study. This presentation will describe the data, methods, and results of the study, as well as the limitations and path forward.