Comparing the performance of screening surveys versus predictive models in identifying patients in need of health-related social need services in the emergency department
ML predictive models leveraging several robust EHR data sources outperformed models using screening questions only. Nevertheless, all models indicated biases. Additional work is needed to design predictive models for effectively identifying all patients with HRSNs.
Authors
- Olena Mazurenko (ORCID: https://orcid.org/0000-0002-1003-9262)
- Christopher A. Harle (ORCID: https://orcid.org/0000-0002-4803-3632)
- Joshua R. Vest (ORCID: https://orcid.org/0000-0002-7226-9688)
- Adam Todd Hirsh (ORCID: https://orcid.org/0000-0001-5647-8941)
- Cassidy McNamee (ORCID: https://orcid.org/0009-0006-4991-0613)
- Joanna Shen
Institutions
- Regenstrief Institute (US)
- Harvard University (US)
- Richard M. Fairbanks Foundation (US)
- Indiana University – Purdue University Indianapolis (US)
Publication Details
- Journal
- PLoS ONE
- Published
- 2024-11-20
- DOI
- https://doi.org/10.1371/journal.pone.0312193
- Citations
- 3
- Primary Topic
- Food Security and Health in Diverse Populations
- Type
- article
- Field-Weighted Citation Impact
- 2.55