Lab tests can be used to predict phosphatidylethanol-measured high-risk alcohol use among people with HIV: a proof-of-concept using machine learning
This study suggests that a combination of lab and health data is useful for identifying individuals engaging in high-risk alcohol use (PEth ≥200 ng/ml). Algorithms including other indirect markers of alcohol use (e.g. gamma glutamyltransferase) may improve identification of high-risk alcohol use, which could be useful in research and clinical settings where PEth testing is unavailable.
Authors
- Judith A. Hahn (ORCID: https://orcid.org/0000-0002-2697-8264)
- Cristina Espinosa da Silva (ORCID: https://orcid.org/0000-0003-1684-1616)
- Brian Beesiga (ORCID: https://orcid.org/0000-0001-5927-8857)
- Nneka Emenyonu (ORCID: https://orcid.org/0000-0003-4376-7810)
- Robin Fatch (ORCID: https://orcid.org/0000-0002-8423-3471)
- Allen Kekibiina (ORCID: https://orcid.org/0000-0002-2835-8528)
- Isabel Elaine Allen (ORCID: https://orcid.org/0000-0001-9029-9744)
- Christine Ngabirano (ORCID: https://orcid.org/0000-0003-0348-316X)
- Gabriel Chamie (ORCID: https://orcid.org/0000-0002-5860-8081)
- Winnie R. Muyindike (ORCID: https://orcid.org/0000-0002-6694-2645)
- Kara Marson
- Julian Adong (ORCID: https://orcid.org/0000-0001-9314-5257)
- Adah Tumwegamire (ORCID: https://orcid.org/0009-0006-7224-9106)
- E Kindoli
Institutions
- Mbarara University of Science and Technology (UG)
- University of California, San Francisco (US)
- Mbarara National Referral Hospital (UG)
- University of San Francisco (US)
Publication Details
- Journal
- Alcohol and Alcoholism
- Published
- 2025-11-14
- DOI
- https://doi.org/10.1093/alcalc/agaf078
- Primary Topic
- Alcohol Consumption and Health Effects
- Type
- article
- Field-Weighted Citation Impact
- 0.00