Engineering & Computer Science Graduate Poster Competition  ·  University of Ottawa  ·  Mar 12, 2026

Testing a co-designed structured chatbot to guide people living with Parkinson's selecting their self-care goals

✦ Try CAFY, the Prototype ↓ Download Poster PDF

Research Team

Authors

Janette Mujica
PhD Student, Digital Transformation & Innovation
Faculty of Engineering, University of Ottawa
Mackenson Joseph
PhD Student, Organizational Communications
Faculty of Arts, University of Ottawa
Nadim Fadi Saadeh
Master of Arts, Health Communication
Faculty of Arts, University of Ottawa
Sylvie Grosjean
Professor, Department of Communication
University of Ottawa
Dr. Tiago Mestre
Associate Professor, Division of Neurology
Ottawa Hospital – Civic Campus, University of Ottawa

Abstract

Overview

Motivation

People living with Parkinson's disease (PWPs) face ongoing difficulties prioritizing self-care goals due to the variability and unpredictability of symptoms (Tonnesen & Nielsen, 2023). While digital health technologies show growing potential to support Parkinson's self-care (Lee et al., 2022; Silva de Lima et al., 2020; Riggare et al., 2021), many PWPs still lack structured, conversational guidance to help them decide "what to focus on today" (Tonnesen & Nielsen, 2023). This work addresses that gap by developing and evaluating CAFY (Conversational Assistant For You)— a structured, co-designed chatbot that helps PWPs clarify self-care priorities and formulate personalized self-care goals.

Methodology

To develop CAFY, we employed a co-design approach with PWPs using a usage diary study (n = 18) and qualitative interviews (n = 18) (Grosjean et al., 2025), alongside facilitated workshops inspired by the dialogue labs method (Lucero et al., 2012). Insights from these activities informed: (1) a revised self-care taxonomy spanning five categories—physical health, lifestyle, mental health, medication management, and well-being— with 42 associated subcategories; (2) guided question flows to support goal selection; and (3) tone and message refinements grounded in health communication frameworks (Yap et al., 2019; Cho, 2012; Stokoe et al., 2024). Through patient workshops (n = 26), we evaluated interaction clarity, perceived usefulness of CAFY, and how participants understood, used, and discussed the taxonomy during chatbot goal-setting and card-sorting activities, including their hesitations and suggestions for refinement. To analyze the data, we conducted a reflexive thematic analysis (Braun & Clarke, 2019; Byrne, 2022). Our interdisciplinary team collaboratively coded the material, iteratively generating and refining themes with attention to interpretive depth.

Preliminary Results

Our analysis shows that PWPs generally found CAFY helpful for clarifying self-care priorities, particularly when it supported self-reflection, aligned with their thinking style, or facilitated shared interpretation with caregivers. Participants valued CAFY's structured guidance but encountered challenges when categories felt ambiguous or when interaction design elements created confusion or accessibility barriers. The taxonomy card-sorting activity confirmed the relevance of a five-domain framework rooted in patient intentions, while also revealing five "continuum logics" that shape how PWPs understand their self-care needs as interconnected rather than discrete categories. This continuum-based way of grouping experiences highlighted several areas where the taxonomy requires reframing or consolidation to better reflect how patients relate one domain to another.

Conclusion

CAFY functions both as a supportive tool for prioritizing self-care goals and as a design probe that yields actionable insights for the interface and the future development of an AI-based conversational recommendation system. It shows promise for helping people living with Parkinson's keep up with their self-care in daily life.

Collaboration

Our Partners

Bibliography

References

  1. Braun, V., & Clarke, V. (2019). Reflecting on reflexive thematic analysis. Qualitative Research in Sport, Exercise and Health, 11(4), 589–597.
  2. Byrne, D. (2022). A worked example of Braun and Clarke's approach to reflexive thematic analysis. Quality & Quantity, 56(3), 1391–1412.
  3. Cho, H. (Ed.). (2012). Health communication message design: Theory and practice. SAGE Publications.
  4. Espay, A. J., Hausdorff, J. M., Sánchez-Ferro, Á., Klucken, J., Merola, A., Bonato, P., … Maetzler, W. (2019). A roadmap for implementation of patient-centered digital outcome measures in Parkinson's disease obtained using mobile health technologies. Movement Disorders, 34(5), 657–663.
  5. Grosjean, S., Giguère, L., Leach, J., & Mestre, T. (2025). Empowering self-care: Leveraging user insights to co-design AI-powered self-care technology for Parkinson's disease. FACETS, 10, 1–18.
  6. Grosjean, S., Mujica, J., Saadeh, N., Mestre, T., & Grimes, D. (2025). "What Should I Focus on Today?" Co-Designing a Goal-Setting Dialogue Tool for Parkinson's Self-Care. Infrahealth 2025 – Proceedings of the 10th International Conference on Infrastructures in Healthcare.
  7. Lee, J., Yeom, I., Chung, M. L., Kim, Y., Yoo, S., & Kim, E. (2022). Use of mobile apps for self-care in people with Parkinson disease: Systematic review. JMIR mHealth and uHealth, 10(1), e33944.
  8. Riggare, S., Stamford, J., & Hägglund, M. (2021). A long way to go: Patient perspectives on digital health for Parkinson's disease. Journal of Parkinson's Disease, 11(s1), S5–S10.
  9. Silva De Lima, A. L., Smits, T., Darweesh, S. K. L., Valenti, G., Milosevic, M., Pijl, M., … Bloem, B. R. (2020). Home-based monitoring of falls using wearable sensors in Parkinson's disease. Movement Disorders, 35(1), 109–115.
  10. Stokoe, E., Albert, S., Buschmeier, H., & Stommel, W. (2024). Conversation analysis and conversational technologies: Finding the common ground between academia and industry. Discourse & Communication, 18(6), 837–847.
  11. Tonnesen, M., Nielsen, C. V., & Andersen, R. S. (2022). Moving goals: Goal-work in Parkinson's disease rehabilitation. Frontiers in Rehabilitation Sciences, 3, 819862.
  12. Yap, J. E., Zubcevic-Basic, N., Johnson, L. W., & Lodewyckx, M. A. (2019). Mental health message appeals and audience engagement: Evidence from Australia. Health Promotion International, 34(1), 28–37.