Full Program »
Using machine learning models to predict the Length of Stay in a hospital setting.
Proper prediction of Length Of Stay (LOS) has become in- increasingly important these years. The LOS prediction provides better services, managing hospital resources and controls their costs. In this paper, we implemented and compared two Machine Learning (ML) methods, the Random Forest (RF) and the Gradient Boosting model (GB), using an open-source available dataset. This data are been firstly preprocessed by combining data transformation, data standardization, and data codication. Then, the RF and the GB were carried out, with a phase of hyperparameters tuning until setting optimal coefficients. Finally, the Mean Square Error (MAE), the R-squared (R2) and the Adjusted R-squared (Adjusted R2) metrics are selected to evaluate the model with parameters.