EUVIMEDEUVIMED entdecken
Open Access

Measuring Implicit Bias in ICU Notes Using Word-Embedding Neural Network Models

Julien Cobert, Hunter Mills, Albert Lee, Oksana Gologorskaya, Edie Espejo, Sun Young Jeon, W John Boscardin, Timothy A Heintz, Christopher J Kennedy, Deepshikha C Ashana, Allyson Cook Chapman, Karthik Raghunathan und 2 weitere

CHEST · 2024

DOI: 10.1016/j.chest.2023.12.031 ↗

Kurz gefasst

Fachartikel in der Zeitschrift CHEST, 2024. Verfasst von Julien Cobert und 13 weiteren Autor:innen. Beteiligte Einrichtung: Anesthesia Service, San Francisco VA Health Care System, University of California, San Francisco, San Francisco, CA; Department of Anesthesia and Per…. Hauptthemen laut MEDLINE: Natural Language Processing, Intensive Care Units, Neural Networks, Computer. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIA NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Language in nonmedical data sets is known to transmit human-like biases when used in natural language processing (NLP) algorithms that can reinforce disparities. It is unclear if NLP algorithms of medical notes could lead to similar transmissions of biases. RESEARCH QUESTION: Can we identify implicit bias in clinical notes, and are biases stable across time and geography? STUDY DESIGN AND METHODS: To determine whether different racial and ethnic descriptors are similar contextually to stigmatizing language in ICU notes and whether these relationships are stable across time and geography, we identified notes on critically ill adults admitted to the University of California, San Francisco (UCSF), from 2012 through 2022 and to Beth Israel Deaconess Hospital (BIDMC) from 2001 through 2012. Because word meaning is derived largely from context, we trained unsupervised word-embedding algorithms to measure the similarity (cosine similarity) quantitatively of the context between a racial or ethnic descriptor (eg, African-American) and a stigmatizing target word (eg, nonco-operative) or group of words (violence, passivity, noncompliance, nonadherence). RESULTS: In UCSF notes, Black descriptors were less likely to be similar contextually to violent words compared with White descriptors. Contrastingly, in BIDMC notes, Black descriptors were more likely to be similar contextually to violent words compared with White descriptors. The UCSF data set also showed that Black descriptors were more similar contextually to passivity and noncompliance words compared with Latinx descriptors. INTERPRETATION: Implicit bias is identifiable in ICU notes. Racial and ethnic group descriptors carry different contextual relationships to stigmatizing words, depending on when and where notes were written. Because NLP models seem able to transmit implicit bias from training data, use of NLP algorithms in clinical prediction could reinforce disparities. Active debiasing strategies may be necessary to achieve algorithmic fairness when using language models in clinical research.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Natural Language ProcessingIntensive Care UnitsNeural Networks, ComputerHumansAlgorithmsCritical IllnessBiasElectronic Health RecordsMaleFemale

Stichwörter der Autor:innen

critical careinequitylinguisticsmachine learningnatural language processing

Autor:innen und Institutionen

  • Anesthesia Service, San Francisco VA Health Care System, University of California, San Francisco, San Francisco, CA; Department of Anesthesia and Perioperative Care, University of California, San Francisco, San Francisc…
  • Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, CA.
  • Division of Geriatrics, University of California, San Francisco, San Francisco, CA.
  • School of Medicine, University of California, San Diego, San Diego, CA.
  • Department of Psychiatry, Harvard Medical School, Boston, MA; Center for Precision Psychiatry, Massachusetts General Hospital, Boston, MA.
  • Division of Pulmonary, Allergy, and Critical Care Medicine, Duke University, Durham, NC.

Förderung

  • NIA NIH HHS

Zitieren

APA

Cobert, J., Mills, H., Lee, A., Gologorskaya, O., Espejo, E., Jeon, S. Y., Boscardin, W. J., Heintz, T. A., Kennedy, C. J., Ashana, D. C., Chapman, A. C., Raghunathan, K., Smith, A. K., & Lee, S. J. (2024). Measuring Implicit Bias in ICU Notes Using Word-Embedding Neural Network Models. CHEST. https://doi.org/10.1016/j.chest.2023.12.031

Vancouver

Cobert J, Mills H, Lee A, Gologorskaya O, Espejo E, Jeon SY, et al. Measuring Implicit Bias in ICU Notes Using Word-Embedding Neural Network Models. CHEST. 2024. doi:10.1016/j.chest.2023.12.031

BibTeX
@article{Cobert2024,
  author = {Cobert, Julien and Mills, Hunter and Lee, Albert and Gologorskaya, Oksana and Espejo, Edie and Jeon, Sun Young and Boscardin, W John and Heintz, Timothy A and Kennedy, Christopher J and Ashana, Deepshikha C and Chapman, Allyson Cook and Raghunathan, Karthik and Smith, Alex K and Lee, Sei J},
  title = {Measuring Implicit Bias in ICU Notes Using Word-Embedding Neural Network Models},
  journal = {CHEST},
  year = {2024},
  doi = {10.1016/j.chest.2023.12.031}
}
Kostenlos starten →