Exploring potential barriers in equitable access to pediatric diagnostic imaging using machine learning

• DOI: 10.3389/fpubh.2023.968319
• Publication Date: 2023-02-24T06:32:15Z
• Authors: Maryam Taheri-Shi...; Khashayar Namdar; Kelvin Ling; Karima Karmali; Melissa D. McCradden; Wayne Lee; Farzad Khalvati
• Keywords: Univariate analysis; Univariate; Demographics; Odds

In this work, we examine magnetic resonance imaging (MRI) and ultrasound (US) appointments at the Diagnostic Imaging (DI) department of a pediatric hospital to discover possible relationships between selected patient features no-show or long waiting room time endpoints. The chosen include age, sex, income, distance from hospital, percentage non-English speakers in postal code, single caregivers appointment slot (morning, afternoon, evening), day week (Monday Sunday). We trained univariate Logistic Regression (LR) models using training sets identified predictive (significant) that remained significant test sets. also implemented multivariate Random Forest (RF) predict achieved Area Under Receiver Operating Characteristic Curve (AUC) 0.82 0.73 for predicting endpoints, respectively. LR analysis on DI uncovered effect during day/week, patients' demographics such as income number no-shows For no-show, found slot, caregiver be most critical contributors. Age, distance, were important our prediction models. no sex discrimination among scheduled appointments. Nonetheless, inequities based low language barrier did exist.