Studying variables affecting the length of stay in patients with lower limb fractures by means of Machine Learning.

The hospital length of stay (LOS) is an important indicator of the efficiency of hospital management. Reduction in the number of inpatient days results in the reduction of the burden of medical fees and the improvement of the beds management, thus increasing the profit margin of hospitals and lowering the overall costs. Due to the prolonged LOS experienced by the orthopedic trauma inpatients, predicting this parameter has become increasingly important for both resource planning and effective admission scheduling. The purpose of this study is to predict the value of LOS starting from the clinical information of the inpatients with lower limb fractures by implementing different Machine Learning algorithms. The analysis was performed on data extracted from the information system of the University Hospital “San Giovanni di Dio and Ruggi d'Aragona” of Salerno (Italy). The proposed ML algorithms show promising outcomes in estimating the LOS and therefore they can be a helpful tool for supporting the clinicians decision-making process and for the management of hospital resources.