Title: Application of a hybrid data mining model to identify the main predictive factors influencing hospital length of stay
Authors: Ahmed Belderrar; Abdeldjebar Hazzab
Addresses: Laboratoire du Commande, Analyse et Optimisation des Systèmes Electro-énergétiques, Université TAHRI Mohamed de Béchar, BP 417 route de kenadsa, Béchar 08000, Algeria ' Laboratoire du Commande, Analyse et Optimisation des Systèmes Electro-énergétiques, Université TAHRI Mohamed de Béchar, BP 417 route de kenadsa, Béchar 08000, Algeria
Abstract: Length of hospital stay is one of the most appropriate measures that can be used for management of hospital resources and assistant of hospital admissions. The main predictive factors associated with the length of stay are critical requirements and should be identified to build a reliable prediction model for hospital stays. A hybrid integration approach consisting of fuzzy radial basis function neural network and hierarchical genetic algorithms was proposed. The proposed approach was applied on a dataset collected from a variety of intensive care units. We achieved an acceptable forecast accuracy level with more than 80.50%. We found 14 common predictive factors. Most notably, we consistently found that the demographic characteristics, hospital features, medical events and comorbidities strongly correlate to the length of stay. The proposed approach can be used as an effective tool for healthcare providers and can be extended to other hospital predictions.
Keywords: data mining; hospital management; hospital stay; hybrid prediction model; predictive factors.
International Journal of Business Intelligence and Data Mining, 2020 Vol.16 No.3, pp.313 - 323
Received: 06 Feb 2017
Accepted: 23 Sep 2017
Published online: 13 Feb 2020 *