Machine learning for healthcare behavioural OR: Addressing waiting time perceptions in emergency care

Abstract

Recent research has discovered links between patient satisfaction and waiting time perceptions. We examine factors associated with waiting time estimation behaviour and how it can be linked to patient flow modelling. Using data from more than 250 patients, we evaluate machine learning (ML) methods to understand waiting time estimation behaviour in two emergency department areas. Our attribute ranking and selection methods reveal that actual waiting time, clinical attributes, and the service environment are among the top ranked and selected attributes. The classification precision for the true outcome of overestimating waiting times reaches almost 70% and 78% in the waiting area and the treatment room, respectively. We linked the ML results with a discrete-event simulation model. Our scenario analysis reveals that changing staffing patterns can lead to a substantial drop-off in overestimation of waiting times. These insights can be employed to control waiting time perceptions and, potentially, increase patient satisfaction.

Keywords:

• Waiting-time perceptions
• machine learning
• attribute selection
• classification
• discrete-event simulation

Acknowledgements

The authors sincerely thank the anonymous referees for their careful review and excellent suggestions for improvement of this article.

Disclosure statement

No potential conflict of interest was reported by the authors.