Welcome to the InfoSci Platform
Last Minute Medical Appointments No-Show Management

Last Minute Medical Appointments No-Show Management

Daniel M. Sousa, André Vasconcelos
Copyright: © 2020 |Volume: 15 |Issue: 4 |Pages: 20
ISSN: 1555-3396|EISSN: 1555-340X|EISBN13: 9781522597988|DOI: 10.4018/IJHISI.2020100102
Cite Article Cite Article

MLA

Sousa, Daniel M., and André Vasconcelos. "Last Minute Medical Appointments No-Show Management." IJHISI vol.15, no.4 2020: pp.18-37. http://doi.org/10.4018/IJHISI.2020100102

APA

Sousa, D. M. & Vasconcelos, A. (2020). Last Minute Medical Appointments No-Show Management. International Journal of Healthcare Information Systems and Informatics (IJHISI), 15(4), 18-37. http://doi.org/10.4018/IJHISI.2020100102

Chicago

Sousa, Daniel M., and André Vasconcelos. "Last Minute Medical Appointments No-Show Management," International Journal of Healthcare Information Systems and Informatics (IJHISI) 15, no.4: 18-37. http://doi.org/10.4018/IJHISI.2020100102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

A no-show occurs when a client has an appointment of some sort with another entity, and voluntarily or not, the client does not show up to that appointment. A patient missing an appointment will mean that the clinic's and health professional's time slot will be wasted. The goal of this research is to find a solution that minimizes no-shows, detecting when a patient is not going to come to the appointment and finding an appropriate replacement. The authors propose a hybrid solution which combines two different behavior prediction techniques: population-based behavior and individual-based behavior. The algorithm starts by computing a no-show probability based on the population's behavior using a logistic regression model. After that, using Bayesian inference, that probability is personalized for each patient. After computing the no-show probabilities for every candidate patient, the algorithm checks if any of them are interested on taking the appointment. The proposed algorithm was assessed using lab data and healthcare provider data.