'Length of Stay' Hospital Decision Support System

'Length of Stay' Hospital Decision Support System: In this PhD we will develop an automated AI system that predicts the expected Length of Stay (LoS) in a hospital bed for patients, starting from the central database of our academic hospital UZ Leuven (1000s or beds, more than 500 000 consultations per year). Can a patient be treated at home, or should (s) be hospitalized? If so, when a patient is kept too long, costs for the hospital and waiting queues for other patients increase, but when a patient leaves prematurely, it might happen that he or she has come back, possibly with health complications, and hence financial impact. So there is an 'optimal' LoS, which we assume to be predictable. This is a challenging problem, where one has to take into account the pathology for which the patient is treated, the required care trajectory and the individual patient profile and the overall demands on the system (capacity, queues, etc.). The end result is a fully automated, user-friendly software module in which we run efficient forecasting algorithms, several hundred or times per day.