Predicting postoperative chronic opioid use with fair machine learning models integrating multi-modal data sources: a demonstration of ethical machine learning in healthcare
We leveraged 2 dimensions of the HEAAL framework to build a fair artificial intelligence (AI) solution. Multi-modal datasets (including wearable and genetic data) and applying bias mitigation strategies can help models to more fairly and accurately assess risk across diverse populations, promoting fairness in AI in healthcare.
Authors
- Traci J. Speed (ORCID: https://orcid.org/0000-0001-6102-2682)
- Anping Xie (ORCID: https://orcid.org/0000-0002-7306-5257)
- Casey Overby Taylor (ORCID: https://orcid.org/0000-0001-9302-5968)
- Nidhi Soley (ORCID: https://orcid.org/0000-0002-3575-6997)
- Ilia Rattsev (ORCID: https://orcid.org/0000-0001-6284-3204)
- Kadija Ferryman (ORCID: https://orcid.org/0000-0001-8552-1822)
Institutions
- Johns Hopkins University (US)
- Johns Hopkins Medicine (US)
- Johns Hopkins Berman Institute of Bioethics (US)
- National Patient Safety Foundation (US)
Publication Details
- Journal
- Journal of the American Medical Informatics Association
- Published
- 2025-03-27
- DOI
- https://doi.org/10.1093/jamia/ocaf053
- Citations
- 5
- Primary Topic
- Opioid Use Disorder Treatment
- Type
- article
- Field-Weighted Citation Impact
- 9.39
Funders
- National Human Genome Research Institute
- National Institute on Minority Health and Health Disparities