From Clinical Trials to Real‐World Impact: Introducing a Computational Framework to Detect Endpoint Bias in Opioid Use Disorder Research
Consistently performing endpoints for one demographic profile may lose generalisability during population shifts, potentially introducing endpoint bias. Increasing minority representation in the training data consistently improved generalisability. The endpoint bias trade-off reinforces the importance of diverse recruitment in OUD trials. The DAB Pipeline helps researchers systematically pinpoint when an endpoint may suffer 'performance variance' (i.e., bias). As an open-source tool, it promotes transparent endpoint evaluation and supports selecting demographically invariant OUD endpoints.
Authors
- Laura Brandt (ORCID: https://orcid.org/0000-0001-7551-221X)
- Larry Au (ORCID: https://orcid.org/0000-0003-0642-9134)
- Salvatore Giorgi (ORCID: https://orcid.org/0000-0001-7381-6295)
- Alexander J. Marker (ORCID: https://orcid.org/0009-0008-6645-8301)
- H. Andrew Schwartz (ORCID: https://orcid.org/0000-0002-6383-3339)
- Gabriel Odom (ORCID: https://orcid.org/0000-0003-1341-4555)
- Clinton Castro (ORCID: https://orcid.org/0000-0003-4740-0055)
- Ganesh Jainarain (ORCID: https://orcid.org/0009-0004-2714-1812)
Institutions
- City College of New York (US)
- University of Wisconsin–Madison (US)
- Florida International University (US)
- Stony Brook University (US)
Publication Details
- Journal
- Drug and Alcohol Review
- Published
- 2025-12-07
- DOI
- https://doi.org/10.1111/dar.70085
- Primary Topic
- Opioid Use Disorder Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00