Events

This Bayesian spatiotemporal study in Cook County integrates remote sensing data with census-based deprivation measures to reveal that nighttime light intensity predicts a 10x increase in opioid overdose mortality, with rising temporal trends across all urbanicity levels.

This study integrates over 1.5 million crowdsourced sidewalk labels with spatial machine learning to show that street-level accessibility deficits are structural determinants of health inequities, particularly depression, among persons with disabilities.

This ecological time-series study in Chicago links extreme heat events to a 20% increase in suicide risk per 1°C above threshold among adults aged 65+, highlighting the intersection of climate change and mental health disparities.

This study applies LLMs and LDA topic modeling to emergency department narratives in NEISS to improve surveillance and etiological classification of IPV-related head and neck injuries.

This study integrates cause-of-death narratives with neighborhood typologies using unsupervised ML and NLP to identify place-specific mortality mechanisms across Cook County, Illinois census tracts.

Using machine learning with temporal holdout validation on Albuquerque Public Schools data, this study finds that infraction severity dominates discipline predictions, yet racial disparities persist for Black and Hispanic/Native American students especially at moderate-severity infractions where administrative discretion is greatest.

Automated detection of IPV injury mechanisms from emergency department narratives using Large Language Models and Latent Dirichlet Allocation

Presentation on recovery housing research at the 2026 Ohio Recovery Housing Conference

Dr. Barboza-Salerno presents on spatial accessibility to abortion care and maternal health outcomes at the IPR Seminar Series

Abstract Understanding how neighborhood context shapes patterns of death is critical to identifying the spatial distribution of health inequities. Medical examiner data contain rich narrative descriptions of causes and circumstances of death that are often absent from clinical records and can offer novel insights for public health prevention.

Presented at the 2026 Hawaii International Conference on Education.

Presented at GIS Day.

Spatial random forest model predicting firearm violence risk across Chicago neighborhoods