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

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.

Barriers to Care Among Glaucoma Patients With a Missed Appointment and Interest in a Navigator Program

“…Research outside of ophthalmology has investigated the burden of these factors on appointment attendance, with one study on breast imaging revealing housing insecurity, difficulty paying utility bills, and low income as predictors of missed clinic appointments. 21 In ophthalmology, a study revealed that neighborhood-level social vulnerability increased appointment nonattendance. 22 These findings highlight the importance of understanding the conditions and communities where patients reside and how these factors contribute to their overall health status.…”

“…Approximately 55% of patients reported facing at least one social risk factor. Research outside of ophthalmology has investigated the burden of these factors on appointment attendance, with one study on breast imaging revealing housing insecurity, difficulty paying utility bills, and low income as predictors of missed clinic appointments 21 . In ophthalmology, a study revealed that neighborhood-level social vulnerability increased appointment nonattendance 22 .…”

Socioeconomic and demographic factors predictive of missed appointments in outpatient radiation oncology: an evaluation of access

“…In one of the most robust studies to date, Sotudian et al used a dataset of 9,970 patients and 36,606 to develop linear and non-linear models to identify predictive variables for missed breast imaging appointments ( 15 ). Among the 57 potentially impactful variables analyzed, the investigators found that those related to social determinants of health including housing insecurity, difficulty paying utility bills, and family caretaking were among the strongest in predicting for “no shows.”…”

ITNR: Inversion Transformer-based Neural Ranking for cancer drug recommendations

“…Conventional Machine Learning (ML) algorithms are generally designed to minimize regression or classification errors [12,13,16,32,42]. Many real-world applications, on the other hand, deemphasize prediction accuracy and prioritize the correct ordering among all the instances [33,34].…”