Predicting No-show Medical Appointments Using Machine Learning

Abstract

Health care centers face many issues due to the limited availability of resources, such as funds, equipment, beds, physicians, and nurses. Appointment absences lead to a waste of hospital resources as well as endangering patient health. This fact makes unattended medical appointments both socially expensive and economically costly. This research aimed to build a predictive model to identify whether an appointment would be a no-show or not in order to reduce its consequences. This paper proposes a multi-stage framework to build an accurate predictor that also tackles the imbalanced property that the data exhibits. The first stage includes dimensionality reduction to compress the data into its most important components. The second stage deals with the imbalanced nature of the data. Different machine learning algorithms were used to build the classifiers in the third stage. Various evaluation metrics are also discussed and an evaluation scheme that fits the problem at hand is described. The work presented in this paper will help decision makers at health care centers to implement effective strategies to reduce the number of no-shows.