Predicting the factors involved in orthopedic patient hospital stay

Long hospital stays can be stressful for the patient for many reasons. Patient length of stay also concerns the hospital from a business standpoint who would like to minimize the length of a patient’s stay, without compromising care. In this study, we investigated what factors are associated with length of hospital stay among orthopedic surgical cases. We hypothesized that age would be the greatest predictor of hospital stay among patients who underwent orthopedic surgery. We also hypothesized that the length of stay would, on average, range from one to three days. We used a dataset from the New York Statewide Planning and Cooperative System which comprises a group of hospitals in New York City. Using machine learning models to predict a patient’s length of stay, we employed exploratory data analysis, support vector machines, principal component analysis and random forest models. Through our models, we found that severity of illness was indeed the highest factor that contributed to determining patient length of stay. The other two factors that followed were the facility that the patient was staying in and the type of procedure that they underwent.