Social determinants of health and the prediction of missed breast imaging appointments

Shahabeddin Sotudian; Aaron Afran; Christina A LeBedis; Anna F Rives; Ioannis Ch Paschalidis; Michael D C Fishman

doi:10.1186/s12913-022-08784-8

Social determinants of health and the prediction of missed breast imaging appointments

BMC Health Serv Res. 2022 Nov 30;22(1):1454. doi: 10.1186/s12913-022-08784-8.

Authors

Shahabeddin Sotudian¹, Aaron Afran², Christina A LeBedis^{2

3}, Anna F Rives^{2

3}, Ioannis Ch Paschalidis^{4

5

6}, Michael D C Fishman^{2

3}

Affiliations

¹ Department of Electrical and Computer Engineering, Division of Systems Engineering, Boston University, Boston, MA, USA.
² Department of Radiology, Boston University School of Medicine, Boston, MA, USA.
³ Department of Radiology, Boston Medical Center, Boston University School of Medicine, Boston, MA, USA.
⁴ Department of Electrical and Computer Engineering, Division of Systems Engineering, Boston University, Boston, MA, USA. yannisp@bu.edu.
⁵ Department of Biomedical Engineering, and Faculty of Computing & Data Sciences, Boston University, Boston, MA, USA. yannisp@bu.edu.
⁶ Rafik B. Hariri Institute for Computing and Computational Science & Engineering, Boston, MA, USA. yannisp@bu.edu.

Abstract

Background: Predictive models utilizing social determinants of health (SDH), demographic data, and local weather data were trained to predict missed imaging appointments (MIA) among breast imaging patients at the Boston Medical Center (BMC). Patients were characterized by many different variables, including social needs, demographics, imaging utilization, appointment features, and weather conditions on the date of the appointment.

Methods: This HIPAA compliant retrospective cohort study was IRB approved. Informed consent was waived. After data preprocessing steps, the dataset contained 9,970 patients and 36,606 appointments from 1/1/2015 to 12/31/2019. We identified 57 potentially impactful variables used in the initial prediction model and assessed each patient for MIA. We then developed a parsimonious model via recursive feature elimination, which identified the 25 most predictive variables. We utilized linear and non-linear models including support vector machines (SVM), logistic regression (LR), and random forest (RF) to predict MIA and compared their performance.

Results: The highest-performing full model is the nonlinear RF, achieving the highest Area Under the ROC Curve (AUC) of 76% and average F1 score of 85%. Models limited to the most predictive variables were able to attain AUC and F1 scores comparable to models with all variables included. The variables most predictive of missed appointments included timing, prior appointment history, referral department of origin, and socioeconomic factors such as household income and access to caregiving services.

Conclusions: Prediction of MIA with the data available is inherently limited by the complex, multifactorial nature of MIA. However, the algorithms presented achieved acceptable performance and demonstrated that socioeconomic factors were useful predictors of MIA. In contrast with non-modifiable demographic factors, we can address SDH to decrease the incidence of MIA.

Keywords: Breast imaging; Missed appointment; Predictive model; Radiology; Social determinants of health.

MeSH terms

Diagnostic Imaging
Humans
Retrospective Studies
Social Determinants of Health*
Social Factors*
Socioeconomic Factors