The Untapped Potential of Nursing and Allied Health Data for Improved Representation of Social Determinants of Health and Intersectionality in Artificial Intelligence Applications: A Rapid Review

International Journal of Engineering Pedagogy

article

Charlene Esteban Ronquillo¹  James Mitchell²  Dari Alhuwail³  Laura-Maria Peltonen⁴  Maxim Topaz⁵  Lorraine J. Block⁶ 

[1] School of Nursing, University of British Columbia Okanagan;School of Computing and Mathematics, Keele University;Information Science Department, Kuwait University, Kuwait and Health Informatics Unit, Dasman Diabetes Institute;Department of Nursing Science, University of Turku;School of Nursing, Columbia University;School of Nursing University of British Columbia Vancouver

关键词: Artificial intelligence;    health equity;    social determinants of health;    health personnel;    informatics;   

DOI  :  10.1055/s-0042-1742504

来源: International Society for Engineering Education (IGIP), Kassel University Press

【 摘 要 】

Objectives: The objective of this paper is to draw attention to thecurrently underused potential of clinical documentation by nursing and allied health professions to improve the representation ofsocial determinants of health (SDoH) and intersectionality datain electronic health records (EHRs), towards the development ofequitable artificial intelligence (AI) technologies.Methods: A rapid review of the literature on the inclusion ofnursing and allied health data and the nature of health equityinformation representation in the development and/or use ofartificial intelligence approaches alongside expert perspectivesfrom the International Medical Informatics Association (IMIA)Student and Emerging Professionals Working Group.Results: Consideration of social determinants of health andintersectionality data are limited in both the medical AI andnursing and allied health AI literature. As a concept being newlydiscussed in the context of AI, the lack of discussion of intersectionality in the literature was unsurprising. However, the limitedconsideration of social determinants of health was surprising, given its relatively longstanding recognition and the importanceof representation of the features of diverse populations as a keyrequirement for equitable AI.Conclusions: Leveraging the rich contextual data collected bynursing and allied health professions has the potential to improvethe capture and representation of social determinants of healthand intersectionality. This will require addressing issues related tovaluing AI goals (e.g., diagnostics versus supporting care delivery) and improved EHR infrastructure to facilitate documentationof data beyond medicine. Leveraging nursing and allied healthdata to support equitable AI development represents a currentopen question for further exploration and research.

【 授权许可】

Unknown