Back

Formative Assessment and Cluster Membership of the Homeless Person's ER Visits

Cavanaugh, G.; Hardigan, P.; Ownby, R. L.; Stanis, S.; Karur, P.

2023-10-10 epidemiology
10.1101/2023.10.10.23296828 medRxiv
Show abstract

The evidence is limited as to whether homeless individuals who visit Emergency Departments share similar characteristics with individuals from private households who, upon examination, are confirmed to need emergency health services beyond preventative healthcare. While the literature heavily addresses the homeless person in the ED, similarity and differences in characteristics with other social groups are lacking to guide the development of targeted health care and emergency health services for the homeless person. This explorative study investigates hospital ER data to draw inferences on ER patient characteristics and attempts to categorize patients according to residence. Nominal regression analyses reveal that cluster membership generated from ER data can predict patient residence and suggest that substance abuse and depression can predict 72-hour ER visit recurrence. Despite reporting low comorbidities, homeless patients were more likely to experience frequent ER visits within 72 hours and had higher rates of depression and substance abuse. Based on behavioral, health, and social characteristics of the homeless person, hospitals could consider targeted provisions and a follow-up mechanism to meet the health care needs of homeless patients.

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.