Prediction of appointment no-shows using electronic health records

Qiaohui Lin; Brenda Betancourt; Benjamin A Goldstein; Rebecca C Steorts

doi:10.1080/02664763.2019.1672631

Prediction of appointment no-shows using electronic health records

J Appl Stat. 2019 Sep 30;47(7):1220-1234. doi: 10.1080/02664763.2019.1672631. eCollection 2020.

Authors

Qiaohui Lin¹, Brenda Betancourt¹, Benjamin A Goldstein², Rebecca C Steorts¹

Affiliations

¹ Department of Statistical Science, Duke University, Durham, NC, USA.
² Department of Biostatistics and Bioinformatics, Duke University, Durham, NC, USA.

Abstract

Appointment no-shows have a negative impact on patient health and have caused substantial loss in resources and revenue for health care systems. Intervention strategies to reduce no-show rates can be more effective if targeted to the subpopulations of patients with higher risk of not showing to their appointments. We use electronic health records (EHR) from a large medical center to predict no-show patients based on demographic and health care features. We apply sparse Bayesian modeling approaches based on Lasso and automatic relevance determination to predict and identify the most relevant risk factors of no-show patients at a provider level.

Keywords: Appointment no-shows; Bayessian Lasso; automatic relevance determination; electronic health data; sparse Bayesian modeling.

Grants and funding

Lin, Betancourt, Goldstein, and Steorts were supported by a seed grant from the Duke Center for Integrative Health at Duke University, Durham, North Carolina