Co-Designing Patient-Facing Machine Learning for Prenatal Stress Reduction
PI: Maia Jacobs
Assistant Professor of Computer Science and Preventive Medicine
Northwestern University
Co-PI: Nabil Alshurafa
Associate Professor of Preventive Medicine and (by courtesy) Computer Science and Electrical and Computer Engineering
Northwestern University
Framework component: Interaction
This research involves a cross-disciplinary collaboration between human-computer interaction, machine learning, and healthcare researchers to evaluate how algorithms can support patients’ own healthcare decision-making. Machine learning is increasingly being used in the development of personalized patient-facing interventions. However, little work considers the patient perspective in the creation of these tools. By making tools that can be understood by the general public, we can allow for greater oversight of potential societal harms and ensure these tools align with the goals and values of those the tools are most likely to impact.
This study consists of designing a just-in-time adaptive intervention (JITAI) for prenatal stress reduction directly with pregnant people. We will use co-design and elicitation methods to enhance our understanding of what questions people have about health interventions driven by machine learning, how to design explanations that are interpretable to people with limited or no statistical background, and how they want to interact with these tools. Through this work, we intend to create machine learning predictions, explanations, and interactions that are interpretable to individuals with no technical background.
Key Personnel
Glenn Fernandes
Graduate Student, Computer Science
Northwestern University
Negar Kamali
Graduate Student, Computer Science
Northwestern University
Mara Ulloa
Graduate Student, Computer Science
Northwestern University