Exploratory Clustering for Emergency Department Patients

• Main Authors: Batiani, P. (Author), Chatzikyriakou, R. (Author), Dalainas, I. (Author), Feretzakis, G. (Author), Kaldis, V. (Author), Kalles, D. (Author), Kolokytha, S. (Author), Loupelis, E. (Author), Panteris, V. (Author), Petropoulou, S. (Author), Rakopoulou, Z. (Author), Sakagianni, A. (Author), Tika, A. (Author), Trakas, N. (Author), Tzelves, L. (Author)
• Format: Article
• Language: English
• Published: NLM (Medline) 2022
• Subjects: adult; article; clustering; controlled study; crowding (area); emergency department; emergency ward; hospital admission; human; k means clustering; k-means; machine learning; Machine learning; patient triage; unsupervised learning; unsupervised machine learning
• Online Access: View Fulltext in Publisher

 Emergency department (ED) overcrowding is an increasing global problem raising safety concerns for the patients. Elaborating an effective triage system that properly separates patients requiring hospital admission remains difficult. The objective of this study was to compare a clustering-related technique assignment of emergency department patients with the admission output using the k-means algorithm. Incorporating such a model into triage practice could theoretically shorten waiting times and reduce ED overcrowding.