Editorial

. 2024 Aug:82:154796.

doi: 10.1016/j.jcrc.2024.154796. Epub 2024 Mar 29.

Minimizing bias when using artificial intelligence in critical care medicine

Benjamin L Ranard¹, Soojin Park², Yugang Jia³, Yiye Zhang⁴, Fatima Alwan⁵, Leo Anthony Celi⁶, Elizabeth R Lusczek⁷

Affiliations

¹ Division of Pulmonary, Allergy, and Critical Care Medicine, Department of Medicine, Columbia University Vagelos College of Physicians and Surgeons and NewYork-Presbyterian Hospital, New York, NY, USA; Program for Hospital and Intensive Care Informatics, Columbia University Vagelos College of Physicians and Surgeons, New York, NY, USA. Electronic address: blr2152@cumc.columbia.edu.
² Program for Hospital and Intensive Care Informatics, Columbia University Vagelos College of Physicians and Surgeons, New York, NY, USA; Departments of Neurology and Bioinformatics, Columbia University Vagelos College of Physicians and Surgeons and NewYork-Presbyterian Hospital, New York, NY, USA.
³ Laboratory for Computational Physiology, Massachusetts Institute of Technology, Cambridge, MA, USA.
⁴ Department of Population Health Sciences, Weill Cornell Medicine, New York, NY, USA.
⁵ Department of Surgery, Hennepin Healthcare, Minneapolis, MN, USA.
⁶ Laboratory for Computational Physiology, Massachusetts Institute of Technology, Cambridge, MA, USA; Division of Pulmonary, Critical Care and Sleep Medicine, Beth Israel Deaconess Medical Center, Boston, MA, USA; Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA.
⁷ Department of Surgery, University of Minnesota Department of Surgery, Minneapolis, MN, USA. Electronic address: lusc0006@umn.edu.

PMID: 38552451
PMCID: PMC11139594
DOI: 10.1016/j.jcrc.2024.154796

Editorial

Minimizing bias when using artificial intelligence in critical care medicine

Benjamin L Ranard et al. J Crit Care. 2024 Aug.

. 2024 Aug:82:154796.

doi: 10.1016/j.jcrc.2024.154796. Epub 2024 Mar 29.

Authors

Benjamin L Ranard¹, Soojin Park², Yugang Jia³, Yiye Zhang⁴, Fatima Alwan⁵, Leo Anthony Celi⁶, Elizabeth R Lusczek⁷

Affiliations

¹ Division of Pulmonary, Allergy, and Critical Care Medicine, Department of Medicine, Columbia University Vagelos College of Physicians and Surgeons and NewYork-Presbyterian Hospital, New York, NY, USA; Program for Hospital and Intensive Care Informatics, Columbia University Vagelos College of Physicians and Surgeons, New York, NY, USA. Electronic address: blr2152@cumc.columbia.edu.
² Program for Hospital and Intensive Care Informatics, Columbia University Vagelos College of Physicians and Surgeons, New York, NY, USA; Departments of Neurology and Bioinformatics, Columbia University Vagelos College of Physicians and Surgeons and NewYork-Presbyterian Hospital, New York, NY, USA.
³ Laboratory for Computational Physiology, Massachusetts Institute of Technology, Cambridge, MA, USA.
⁴ Department of Population Health Sciences, Weill Cornell Medicine, New York, NY, USA.
⁵ Department of Surgery, Hennepin Healthcare, Minneapolis, MN, USA.
⁶ Laboratory for Computational Physiology, Massachusetts Institute of Technology, Cambridge, MA, USA; Division of Pulmonary, Critical Care and Sleep Medicine, Beth Israel Deaconess Medical Center, Boston, MA, USA; Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA.
⁷ Department of Surgery, University of Minnesota Department of Surgery, Minneapolis, MN, USA. Electronic address: lusc0006@umn.edu.

PMID: 38552451
PMCID: PMC11139594
DOI: 10.1016/j.jcrc.2024.154796

No abstract available

Keywords: Artificial intelligence; Bias; Critical Care; Disparities; Fairness; Health equity; Machine learning.

PubMed Disclaimer

Conflict of interest statement

Competing Interest Statement: YJ is currently also affiliated with Verily life science, SSF, CA.

Figures

**Figure 1:. Ways Bias can be Introduced into the AI Lifecycle.**
Conceptual framework for bias in the AI lifecycle. Arrows indicate where feedback loops can occur, creating a nested chain of interdependent processes, each of which can perpetuate bias. Effective mitigation of bias is necessary at each stage of the lifecycle and can be most effectively handled by skilled teams diverse in background and domain expertise. Created with BioRender.com

See this image and copyright information in PMC

Cited by

Challenges with reinforcement learning model transportability for sepsis treatment in emergency care.
Nauka PC, Kennedy JN, Brant EB, Komorowski M, Pirracchio R, Angus DC, Seymour CW. Nauka PC, et al. NPJ Digit Med. 2025 Feb 6;8(1):91. doi: 10.1038/s41746-025-01485-6. NPJ Digit Med. 2025. PMID: 39915643 Free PMC article.
Global disparities in artificial intelligence-based mammogram interpretation for breast cancer: A scientometric analysis of representation, trends, and equity.
Miyawaki IA, Banerjee I, Batalini F, Campello Jorge CA, Celi LA, Cobanaj M, Dee EC, Gichoya JW, Kaffey Z, Lloyd MR, McCullum L, Ranganathan S, Corti C. Miyawaki IA, et al. Eur J Cancer. 2025 May 2;220:115394. doi: 10.1016/j.ejca.2025.115394. Epub 2025 Apr 1. Eur J Cancer. 2025. PMID: 40209572 Free PMC article.
Ethical Challenges and Opportunities of AI in End-of-Life Palliative Care: Integrative Review.
García Abejas A, Geraldes Santos D, Leite Costa F, Cordero Botejara A, Mota-Filipe H, Salvador Vergés À. García Abejas A, et al. Interact J Med Res. 2025 May 14;14:e73517. doi: 10.2196/73517. Interact J Med Res. 2025. PMID: 40302210 Free PMC article. Review.
Critical Data for Critical Care: A Primer on Leveraging Electronic Health Record Data for Research From Society of Critical Care Medicine's Panel on Data Sharing and Harmonization.
Heavner SF, Kumar VK, Anderson W, Al-Hakim T, Dasher P, Armaignac DL, Clermont G, Cobb JP, Manion S, Remy KE, Reuter-Rice K, Haendel M; Society of Critical Care Medicine (SCCM) Discovery Panel on Data Sharing and Harmonization. Heavner SF, et al. Crit Care Explor. 2024 Nov 15;6(11):e1179. doi: 10.1097/CCE.0000000000001179. eCollection 2024 Nov. Crit Care Explor. 2024. PMID: 39559555 Free PMC article. Review.

References

1. Fagan LM, Kunz JC, Feigenbaum EA, Osborn JJ. Representation of dynamic clinical knowledge: measurement interpretation in the intensive care unit. Proceedings of the 6th international joint conference on Artificial intelligence - Volume 1. Tokyo, Japan: Morgan Kaufmann Publishers Inc.; 1979:260–2.
1. van de Sande D, van Genderen ME, Huiskens J, Gommers D, van Bommel J. Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit. Intensive Care Med 2021;47(7):750–60. - PMC - PubMed
1. Yoon JH, Pinsky MR, Clermont G. Artificial Intelligence in Critical Care Medicine. Crit Care 2022;26(1):75. - PMC - PubMed
1. Dantes RB, Kaur H, Bouwkamp BA, et al. Sepsis Program Activities in Acute Care Hospitals — National Healthcare Safety Network, United States, 2022. MMWR Morb Mortal Wkly Rep 2023;72:907–911. DOI: 10.15585/mmwr.mm7234a2. - DOI - PMC - PubMed
1. U.S. Department of Health and Human Services. Health Equity and Health Disparities Environmental Scan. Rockville, MD: U.S. Department of Health and Human Services, Office of the Assistant Secretary for Health, Office of Disease Prevention and Health Promotion; 2022.

Publication types

Actions

MeSH terms

Actions
Actions
Actions
Actions

Grants and funding

R01 NS129760/NS/NINDS NIH HHS/United States

LinkOut - more resources

Full Text Sources
Medical
- MedlinePlus Health Information

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

Minimizing bias when using artificial intelligence in critical care medicine

Affiliations

Minimizing bias when using artificial intelligence in critical care medicine

Authors

Affiliations

Conflict of interest statement

Figures

Similar articles

Cited by

References

Publication types

MeSH terms

Grants and funding

LinkOut - more resources

Full Text Sources

Medical