EUVIMEDEUVIMED entdecken
Open Access

Predicting postoperative chronic opioid use with fair machine learning models integrating multi-modal data sources: a demonstration of ethical machine learning in healthcare

Nidhi Soley, Ilia Rattsev, Traci J Speed iD, Anping Xie iD, Kadija S Ferryman, Casey Overby Taylor iD

Journal of the American Medical Informatics Association · 01.06.2025 · 32 (6) · 985-997

DOI: 10.1093/jamia/ocaf053 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, online erschienen am 27.03.2025. Verfasst von Nidhi Soley und 5 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Computational Medicine, Whiting School of Engineering, Johns Hopkins University, Baltimore, MD 21218, United States. Hauptthemen laut MEDLINE: Machine Learning, Opioid-Related Disorders, Postoperative Pain, Analgesics, Opioid. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 75 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Office of the Director: Regional Medical Centers, NIH HHS, NHGRI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Building upon our previous work on predicting chronic opioid use using electronic health records (EHR) and wearable data, this study leveraged the Health Equity Across the AI Lifecycle (HEAAL) framework to (a) fine tune the previously built model with genomic data and evaluate model performance in predicting chronic opioid use and (b) apply IBM’s AIF360 pre-processing toolkit to mitigate bias related to gender and race and evaluate the model performance using various fairness metrics. Materials and Methods Participants included approximately 271 All of Us Research Program subjects with EHR, wearable, and genomic data. We fine-tuned 4 machine learning models on the new dataset. The SHapley Additive exPlanations (SHAP) technique identified the best-performing predictors. A preprocessing toolkit boosted fairness by gender and race.

Results

The genetic data enhanced model performance from the prior model, with the area under the curve improving from 0.90 (95% CI, 0.88-0.92) to 0.95 (95% CI, 0.89-0.95). Key predictors included Dopamine D1 Receptor (DRD1) rs4532, general type of surgery, and time spent in physical activity. The reweighing preprocessing technique applied to the stacking algorithm effectively improved the model’s fairness across racial and gender groups without compromising performance.

Conclusion

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningOpioid-Related DisordersPostoperative PainAnalgesics, OpioidHumansElectronic Health RecordsMaleFemaleWearable Electronic DevicesMiddle AgedAdultInformation Sources

Stichwörter der Autor:innen

All of Uschronic opioid useethical machine learningmultimodal datasetresponsible AI

Substanzen

Analgesics, Opioid

Autor:innen und Institutionen

  • Institute for Computational Medicine, Whiting School of Engineering, Johns Hopkins University, Baltimore, MD 21218, United States.
  • Department of Biomedical Engineering, Johns Hopkins University School of Medicine, Baltimore, MD 21218, United States.
  • Department of Psychiatry and Behavioral Sciences, Johns Hopkins University School of Medicine, Baltimore, MD 21205, United States.
  • Armstrong Institute for Patient Safety and Quality, Johns Hopkins University School of Medicine, Baltimore, MD 21202, United States.
  • Department of Anesthesia and Critical Care Medicine, Johns Hopkins University School of Medicine, Baltimore, MD 21205, United States.
  • Department of Health Policy & Management, Johns Hopkins University, Bloomberg School of Public Health, Baltimore, MD 21205, United States.

ORCID-Profile: Traci J Speed, Anping Xie, Casey Overby Taylor

Förderung

  • Office of the Director: Regional Medical Centers
  • NIH HHS
  • NHGRI NIH HHS
  • NIMHD NIH HHS
  • National Institutes of Health
  • National Human Genome Research Institute
  • National Institute on Minority Health and Health Disparities

Zitieren

APA

Soley, N., Rattsev, I., Speed, T. J., Xie, A., Ferryman, K. S., & Taylor, C. O. (2025). Predicting postoperative chronic opioid use with fair machine learning models integrating multi-modal data sources: a demonstration of ethical machine learning in healthcare. Journal of the American Medical Informatics Association, 32(6), 985-997. https://doi.org/10.1093/jamia/ocaf053

Vancouver

Soley N, Rattsev I, Speed TJ, Xie A, Ferryman KS, Taylor CO. Predicting postoperative chronic opioid use with fair machine learning models integrating multi-modal data sources: a demonstration of ethical machine learning in healthcare. Journal of the American Medical Informatics Association. 2025;32(6):985-997. doi:10.1093/jamia/ocaf053

BibTeX
@article{Soley2025,
  author = {Soley, Nidhi and Rattsev, Ilia and Speed, Traci J and Xie, Anping and Ferryman, Kadija S and Taylor, Casey Overby},
  title = {Predicting postoperative chronic opioid use with fair machine learning models integrating multi-modal data sources: a demonstration of ethical machine learning in healthcare},
  journal = {Journal of the American Medical Informatics Association},
  year = {2025},
  volume = {32},
  number = {6},
  pages = {985--997},
  doi = {10.1093/jamia/ocaf053}
}
Kostenlos starten →