Centering Care in the Design of AI in Global Health
Author(s)
Ismail, Azra
Advisor(s)
Editor(s)
Collections
Supplementary to:
Permanent Link
Abstract
There has been growing interest in the application of Artificial Intelligence (AI) in healthcare, motivated by scarce and unequal resources globally. These technologies promise improved health outcomes but they also risk increasing health inequities, particularly for communities and care workers on the margins. This dissertation engages in the study and design of AI systems in resource-constrained health settings. I focus on the context of maternal and child care delivery in India—which on the one hand has become synonymous with the global development goals of health equity and gender equality, while on the other, reflects a history of violating reproductive rights and relying on exploited care workers in the Global South. I propose that a focus on care can bring attention to and help resolve some of these tensions, and support the ethical application of AI in health settings.
Synthesizing prior AI efforts in global health and my own ethnographic research on frontline health in an underserved setting in India, my dissertation first outlines the gaps and opportunities in current AI efforts. I then examine AI integration from a feminist lens of care in three areas—with existing data flows and practices, multi-stakeholder care ecologies, and everyday care work. First, I trace the movement of data from the site of collection from communities to use in machine learning (ML) systems, highlighting the caring labor that must go into making data “good” for ML, particularly by already overworked and underpaid health workers. Second, I consider the implementation of ML in a real-world setting, highlighting how care shapes the configuration of a human-AI system and the alignment of program goals for design and implementation, through continual dialogue across multiple diverse stakeholders. Third, I engage in the co-design of a conversational agent that aims to support care work while centering worker agency, drawing on a deep understanding of existing digital practices and their increasing work burden. Across these three areas, I pay attention to the gendered nature of work and technology use, and the broader care ecology within which these technologies are embedded. Finally, I reflect on my own position and orientation to care as a researcher engaging with workers and communities on the margins, using various methods and points of entry. Through a reflective and participatory approach, my research contributes an understanding of how AI-based technologies may (and where they may not) enable healthier and more caring futures for communities globally.
Sponsor
Date
2023-05-02
Extent
Resource Type
Text
Resource Subtype
Dissertation