EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Bias in medical AI: Implications for clinical decision-making

James L Cross iD, Michael A Choma, John A Onofrey iD

PLOS Digital Health · 07.11.2024 · 3 (11) · e0000651

DOI: 10.1371/journal.pdig.0000651 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift PLOS Digital Health, online erschienen am 07.11.2024. Verfasst von James L Cross und 2 weiteren Autor:innen. Beteiligte Einrichtung: Yale School of Medicine, New Haven, Connecticut, United States of America. Die Arbeit wurde bisher 657-mal zitiert (Crossref) und nennt 132 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Biases in medical artificial intelligence (AI) arise and compound throughout the AI lifecycle. These biases can have significant clinical consequences, especially in applications that involve clinical decision-making. Left unaddressed, biased medical AI can lead to substandard clinical decisions and the perpetuation and exacerbation of longstanding healthcare disparities. We discuss potential biases that can arise at different stages in the AI development pipeline and how they can affect AI algorithms and clinical decision-making. Bias can occur in data features and labels, model development and evaluation, deployment, and publication. Insufficient sample sizes for certain patient groups can result in suboptimal performance, algorithm underestimation, and clinically unmeaningful predictions. Missing patient findings can also produce biased model behavior, including capturable but nonrandomly missing data, such as diagnosis codes, and data that is not usually or not easily captured, such as social determinants of health. Expertly annotated labels used to train supervised learning models may reflect implicit cognitive biases or substandard care practices. Overreliance on performance metrics during model development may obscure bias and diminish a model’s clinical utility. When applied to data outside the training cohort, model performance can deteriorate from previous validation and can do so differentially across subgroups. How end users interact with deployed solutions can introduce bias. Finally, where models are developed and published, and by whom, impacts the trajectories and priorities of future medical AI development. Solutions to mitigate bias must be implemented with care, which include the collection of large and diverse data sets, statistical debiasing methods, thorough model evaluation, emphasis on model interpretability, and standardized bias reporting and transparency requirements. Prior to real-world implementation in clinical settings, rigorous validation through clinical trials is critical to demonstrate unbiased application. Addressing biases across model development stages is crucial for ensuring all patients benefit equitably from the future of medical AI.

Autor:innen und Institutionen

  • Yale School of Medicine, New Haven, Connecticut, United States of America.
  • Department of Radiology & Biomedical Imaging, Yale University, New Haven, Connecticut, United States of America.
  • Department of Urology, Yale University, New Haven, Connecticut, United States of America.
  • Department of Biomedical Engineering, Yale University, New Haven, Connecticut, United States of America.

ORCID-Profile: James L Cross, John A Onofrey

Zitieren

APA

Cross, J. L., Choma, M. A., & Onofrey, J. A. (2024). Bias in medical AI: Implications for clinical decision-making. PLOS Digital Health, 3(11), e0000651. https://doi.org/10.1371/journal.pdig.0000651

Vancouver

Cross JL, Choma MA, Onofrey JA. Bias in medical AI: Implications for clinical decision-making. PLOS Digital Health. 2024;3(11):e0000651. doi:10.1371/journal.pdig.0000651

BibTeX
@article{Cross2024,
  author = {Cross, James L and Choma, Michael A and Onofrey, John A},
  title = {Bias in medical AI: Implications for clinical decision-making},
  journal = {PLOS Digital Health},
  year = {2024},
  volume = {3},
  number = {11},
  pages = {e0000651},
  doi = {10.1371/journal.pdig.0000651}
}
Kostenlos starten →