Abstract: Determining the optimal time for patient discharge is a challenging and complex task that involves multiple opposing decision perspectives. On the one hand, patient safety and the quality of healthcare service delivery and on the other hand, economic factors and resource availability need to be considered by hospital personnel. By using state-of-the-art machine learning methods, this paper presents a novel approach to determine the optimal time of patient discharge from different viewpoints, including a cost-centered, an outcome-centered, and a balanced perspective. The proposed approach has been developed and tested as part of a case study in an Australian private hospital group. For this purpose, unplanned readmissions and associated costs for episodes of admitted patient care are analyzed with regards to the respective time of discharge. The results of the analyses show that increasing the length of stay for certain procedure groups can lead to reduced costs. The developed approach can aid physicians and hospital management to make more evidence-based decisions to ensure both sufficient healthcare quality and cost-effective resource allocation in hospitals.
Authors: Isabella Eigner (FAU Erlangen Nuremberg, Germany); Freimut Bodendorf (University of Erlangen-Nuremberg, Germany)
Email: firstname.lastname@example.org, email@example.com