Multiple Regression Model to Predict Length of Hospital Stay for Patients Undergoing Femur Fracture Surgery at “San Giovanni di Dio e Ruggi d’Aragona” University Hospital

The economic cuts suffered by public health have in many cases led to the reduction of beds. In order to optimize the available resources, the length of stay (LOS) can be used as an efficiency parameter. The objective of this study is to predict the value of LOS using the clinical information that is generally supplied by a patient who is hospitalized following a fracture of the neck of the femur and to make a comparison with results obtained after the implementation of the new diagnostic-therapeutic-assistance pathway (DTAP). The analysis was conducted on data extrapolated from the information system of the University Hospital “San Giovanni di Dio and Ruggi d’Aragona” of Salerno (Italy). The results show promising outcome in the use of the proposed prediction models as a tool for determining an estimate of the LOS and support the decision making process and the management of hospital resources in advance. In addition, the comparison of between the two models can be used as an indicator to assess the efficiency of the implemented DTAP.