Disability-related depression inequities are driven by accessibility deficits: Evidence from crowdsourced sidewalk data and machine learning

Abstract

Research on the built environment and health rarely considers how street-level infrastructure shapes population health outcomes, particularly for persons with disabilities who experience disproportionate exposure to accessibility barriers. This study integrates large-scale, crowdsourced sidewalk data with spatial machine learning algorithms to examine how infrastructure conditions are associated with mental and physical health. We integrated over 1.5 million crowdsourced, geolocated sidewalk labels with ACS indicators, CDC PLACES estimates, and the Environmental Protection Agency (EPA) Walkability Index for Cook County, Illinois. A composite accessibility index (ACCI; 0–1) was constructed to capture sidewalk accessibility based on deficiencies in sidewalk infrastructure and the presence of barriers. Spatially constrained Self-Organizing Maps (SOMs) were used to organize neighborhoods based on similarities across the ACCI, socioeconomic, and health variables, and k-means clustering of the SOM output identified discrete neighborhood typologies. Spatial lag regression models were then estimated. Five neighborhood typologies revealed structured gradients in accessibility, socioeconomic conditions, and disability prevalence. High-access (ACCI = 0.80) neighborhoods had lower poverty (8%) and disability prevalence (20%), whereas low-access (ACCI = 0.46) neighborhoods had higher poverty (34%) and disability prevalence (34%). Depression prevalence was significantly higher in disadvantaged, low-access clusters. Disability significantly moderated the association between sidewalk severity and depression (p = 0.011), corresponding to a 7.7 percentage-point increase in depression in high-disability, low-access areas. Street-level accessibility deficits function as structural determinants of health inequities among persons with disabilities. These findings underscore the need for disability-centered urban design and public health planning.

Dr. Gia Elise Barboza-Salerno

Director

I am an interdisciplinary scholar whose research integrates law, public health, social work, and advanced statistics to study childhood adversity, violence-related harm, and neighborhood-level inequities. I lead the ISSUES Lab at Ohio State, translating spatial and legal analysis into policy and practice.

Dr. Karla Shockley McCarthy

Co-Director

Dr. Karla Shockley, PhD, LMSW, TRCC, FSW, is a Principal Investigator and Senior Research Consultant at the Ohio Colleges of Medicine Government Resource Center, where she leads applied health services and population health research. She uses a collaborative team approach to design and execute mixed methods studies, develops survey instrumentation, oversees qualitative and quantitative analyses, and employs various dissemination methods. Her work centers on translating complex data into actionable insights that inform public health.

Malcolm McCarthy

Undergraduate Geospatial Analyst

Malcolm is a third-year psychology major with minors in GIS and ASL studies interested in pursuing a clinical psychology PhD.

Dr. Amy Watson-Grace

PhD Candidate, Methodologist

Dr. Amy Watson-Grace is a PhD candidate and occupational therapist with advanced pediatric board certification and extensive clinical and leadership experience.