Improving diagnosis-based quality measures: an application of machine learning to the prediction of substance use disorder among outpatients
This analysis shows that use of model-based performance measures may help address measurement blind spots that arise due to differences in diagnostic accuracy across sites. Although model-based estimates better estimate SUD prevalence relative to diagnoses alone for facility quality assessment, further improvements and individual SUD detection both require enhanced direct screening for non-alcohol drug use.
Authors
- Katherine J. Hoggatt (ORCID: https://orcid.org/0000-0002-9431-5438)
- Donna L. Washington (ORCID: https://orcid.org/0000-0001-7917-4609)
- Alex H. S. Harris (ORCID: https://orcid.org/0000-0001-7267-3077)
- Emily C. Williams (ORCID: https://orcid.org/0000-0002-8210-6137)
- Corey J. Hayes (ORCID: https://orcid.org/0000-0002-7776-6157)
Institutions
- University of California, Los Angeles (US)
- University of California, San Francisco (US)
- University of Washington (US)
- VA Palo Alto Health Care System (US)
- VA Puget Sound Health Care System (US)
- Central Arkansas Veterans Healthcare System (US)
- Stanford Medicine (US)
- San Francisco VA Health Care System (US)
- VA Greater Los Angeles Healthcare System (US)
- University of Arkansas for Medical Sciences (US)
Publication Details
- Journal
- BMJ Open Quality
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1136/bmjoq-2024-003017
- Primary Topic
- Substance Abuse Treatment and Outcomes
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- U.S. Department of Veterans Affairs
- Health Services Research and Development