A DATA MINING-BASED APPROACH TO PREDICT STRAIN SITUATIONS IN HOSPITAL EMERGENCY DEPARTMENT SYSTEMS

Sofia Benbelkacem (1) , Farid Kadri (2, 3) , Sondès Chaabane (2, 3) , Baghdad Atmani (1)

1 LIO - Laboratoire d'Informatique d'Oran
2 TEMPO - Laboratoire de Thermique, Ecoulements Mécaniques matériaux mise en forme PrOduction
3 LAMIH - Laboratoire d'Automatique, de Mécanique et d'Informatique industrielles et Humaines - UMR 8201

Nowadays, emergency departments are confronted to exceptional events such as epidemics problems or health crises. These situations increase the patient flow. The consequence of this influx of patients has resulted in problems of ED overcrowding which often increases the length of stay of patients (LOS) in EDs and leads to strain situations. To cope with such situations, ED managers must predict the LOS. In this paper, we propose a model for predicting the patient length of stay (LOS) in ED using data mining techniques. The used data was collected from the pediatric emergency department (PED) in Lille regional hospital centre, France. Our target is to illustrate with a real world case study, how data mining can be benefit to predict LOS and which its limitations.

Mots clés: data mining; emergency department; classification; prediction; length of stay

Domaines: Modélisation et simulation

Sofia Benbelkacem, Farid Kadri, Sondès Chaabane, Baghdad Atmani. A DATA MINING-BASED APPROACH TO PREDICT STRAIN SITUATIONS IN HOSPITAL EMERGENCY DEPARTMENT SYSTEMS. 10ème Conférence Francophone de Modélisation, Optimisation et Simulation- MOSIM’14, Nov 2014, Nancy, France. ⟨hal-01081556⟩