CASMI: Co-designing Patient-Facing Machine Learning for Prenatal Stress Reduction

The goal of this research is to include patients in the development and design of machine learning (ML) prediction tools. We aim to co-design and evaluate decision support tools (DSTs) embodying machine learning models directly with patients. Patients refers to pregnant people interested in next-day stress predictions and management with the assistance of machine learning. Phase one of the project, where we co-designing intervention components, will inform Phase two, where we evaluate behavior change principles in ML design.

Publications and Presentations

Co-Designing Patient-Facing Machine Learning for Prenatal Stress Reduction

Poster presented by Mara Ulloa at ISRII conference in Limerick, Ireland. June 2024.
Mara Ulloa, MS; Negar Kamali, PhD; Glenn Fernandes, MS; Elizabeth Soyemi; Miranda Beltzer, PhD; Benji Kaveladze, PhD; Nabil Alshurafa, PhD; Maia Jacobs, PhD. ISRII ’24

Co-Designing Patient-Facing ML For Prenatal Stress Reduction

Poster presented by Mara Ulloa at CRA IDEALS conference in Minneapolis, MN. April 2024.
Mara Ulloa, MS; Negar Kamali, PhD; Glenn Fernandes, MS; Elizabeth Soyemi; Miranda Beltzer, PhD; Benji Kaveladze, PhD; Nabil Alshurafa, PhD; Maia Jacobs, PhD. CRA IDEALS ’24

Predicting the Next-Day Perceived and Physiological Stress of Pregnant Women by Using Machine Learning and Explainability: Algorithm Development and Validation

Ada Ng, Boyang Wei, Jayalakshmi Jain, Erin A Ward, S Darius Tandon, Judith T Moskowitz, Sheila Krogh-Jespersen, Lauren S Wakschlag, Nabil Alshurafa. JMIR mHealth and uHealth ’22

micro-Stress EMA: A Passive Sensing Framework for Detecting in-the-wild Stress in Pregnant Mothers

Zachary D. King, Judith Moskowitz, Begum Egilmez, Shibo Zhang, Lisa Zhang, Michael Bass, John Rogers, Roozbeh Ghaffari, Laurie Wakschlag, Nabil Alshurafa. JProc ACM Interact Mob Wearable Ubiquitous Technol. ’20