EUVIMEDEUVIMED entdecken
Open Access

FairICP: identifying biases and increasing transparency at the point of care in post-implementation clinical decision support using inductive conformal prediction

Xiaotan Sun, Makiya Nakashima, Christopher Nguyen, Po-Hao Chen, W H Wilson Tang, Deborah Kwon iD, David Chen iD

Journal of the American Medical Informatics Association · 2025

DOI: 10.1093/jamia/ocaf095 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, 2025. Verfasst von Xiaotan Sun und 6 weiteren Autor:innen. Beteiligte Einrichtung: Cardiovascular Innovation Research Center, Cleveland Clinic, Cleveland, OH 44195, United States. Hauptthemen laut MEDLINE: Decision Support Systems, Clinical, Artificial Intelligence, Point-of-Care Systems. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NHLBI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

Fairness concerns stemming from known and unknown biases in healthcare practices have raised questions about the trustworthiness of Artificial Intelligence (AI)-driven Clinical Decision Support Systems (CDSS). Studies have shown unforeseen performance disparities in subpopulations when applied to clinical settings different from training. Existing unfairness mitigation strategies often struggle with scalability and accessibility, while their pursuit of group-level prediction performance parity does not effectively translate into fairness at the point of care. This study introduces FairICP, a flexible and cost-effective post-implementation framework based on Inductive Conformal Prediction (ICP), to provide users with actionable knowledge of model uncertainty due to subpopulation level biases at the point of care. Materials and Methods FairICP applies ICP to identify the model’s scope of competence through group specific calibration, ensuring equitable prediction reliability by filtering predictions that fall within the trusted competence boundaries. We evaluated FairICP against four benchmarks on three medical imaging modalities: (1) Cardiac Magnetic Resonance Imaging (MRI), (2) Chest X-ray and (3) Dermatology Imaging, acquired from both private and large public datasets. Frameworks are assessed on prediction performance enhancement and unfairness mitigation capabilities.

Results

Compared to the baseline, FairICP improved prediction accuracy by 7.2% and reduced the accuracy gap between the privileged and unprivileged subpopulations by 2.2% on average across all three datasets. Discussion and Conclusion Our work provides a robust solution to promote trust and transparency in AI-CDSS, fostering equality and equity in healthcare for diverse patient populations. Such post-process methods are critical to enabling a robust framework for AI-CDSS implementation and monitoring for healthcare settings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Decision Support Systems, ClinicalArtificial IntelligencePoint-of-Care SystemsHumansBias

Stichwörter der Autor:innen

artificial intelligenceclinical decision supportfairnessmodel uncertainty

Autor:innen und Institutionen

  • Cardiovascular Innovation Research Center, Cleveland Clinic, Cleveland, OH 44195, United States.
  • Heart Vascular and Thoracic Institute, Cleveland Clinic, Cleveland, OH 44195, United States.
  • Department of Diagnostic Radiology, Diagnostics Institute, Cleveland Clinic, Cleveland, OH 44195, United States.

ORCID-Profile: Deborah Kwon, David Chen

Förderung

  • NHLBI NIH HHS

Zitieren

APA

Sun, X., Nakashima, M., Nguyen, C., Chen, P. H., Tang, W. H. W., Kwon, D., & Chen, D. (2025). FairICP: identifying biases and increasing transparency at the point of care in post-implementation clinical decision support using inductive conformal prediction. Journal of the American Medical Informatics Association. https://doi.org/10.1093/jamia/ocaf095

Vancouver

Sun X, Nakashima M, Nguyen C, Chen PH, Tang WHW, Kwon D, et al. FairICP: identifying biases and increasing transparency at the point of care in post-implementation clinical decision support using inductive conformal prediction. Journal of the American Medical Informatics Association. 2025. doi:10.1093/jamia/ocaf095

BibTeX
@article{Sun2025,
  author = {Sun, Xiaotan and Nakashima, Makiya and Nguyen, Christopher and Chen, Po-Hao and Tang, W H Wilson and Kwon, Deborah and Chen, David},
  title = {FairICP: identifying biases and increasing transparency at the point of care in post-implementation clinical decision support using inductive conformal prediction},
  journal = {Journal of the American Medical Informatics Association},
  year = {2025},
  doi = {10.1093/jamia/ocaf095}
}
Kostenlos starten →