Evaluating the predictive performance of different data sources to forecast overdose deaths at the neighborhood level with machine learning in Rhode Island
Prioritizing neighborhoods for overdose prevention with forecasting is feasible using a simple-to-implement model trained on publicly available ACS data combined with only one other administrative data source in Rhode Island, offering a starting point for other jurisdictions.
Authors
- Alexandra Skinner (ORCID: https://orcid.org/0000-0001-5071-6937)
- Bennett Allen (ORCID: https://orcid.org/0000-0002-6321-2436)
- Claire Pratty (ORCID: https://orcid.org/0000-0001-9674-0983)
- Jennifer Ahern (ORCID: https://orcid.org/0000-0002-3853-9760)
- Daniel B. Neill (ORCID: https://orcid.org/0000-0001-6282-1240)
- Victoria Jent (ORCID: https://orcid.org/0000-0002-5695-081X)
- Magdalena Cerdá (ORCID: https://orcid.org/0000-0001-8441-7046)
- Brandon D. L. Marshall (ORCID: https://orcid.org/0000-0002-0134-7052)
- John C Halifax
Institutions
- Brown University (US)
- Courant Institute of Mathematical Sciences (US)
- Berkeley Public Health Division (US)
- New York University (US)
- University of California, Berkeley (US)
Publication Details
- Journal
- Preventive Medicine
- Published
- 2025-03-29
- DOI
- https://doi.org/10.1016/j.ypmed.2025.108276
- Citations
- 2
- Primary Topic
- Artificial Intelligence in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 5.88