INSIGHT & INSIGHT AI

Phase 1. Reviewing PGHD Integration Challenge

A comprehensive 10-year review of challenges in integrating PGHD into healthcare systems from the perspectives of both patients and healthcare professionals. This review resulted in the development of a conceptual 10-stage workflow model.

Phase 2. Towards Data Enabled Physical Activity Planning in Cardiac Rehabilitation

Study 1: Healthy participants collected data from wearable devices and discussed the findings with healthcare providers (HCPs) during physical activity planning sessions.

Study 2: A card-sorting workshop with HCPs identified their specific information needs for supporting physical activity consultations.

Study 3: Understanding Patient and HCP perspectives on Designing for Data-Enabled Physical Activity Planning in Cardiac Rehabilitation.

Key research questions included:

• What are the challenges and opportunities for integrating patient generated health data 
• What are patient experiences in sharing PGHD with HCPs? 
• What are HCP and CVD Patient needs and perspectives on integrating PGHD into clinical pathways for Physical Activity Planning? 

Phase 3. INSIGHT AI – Enhancing Data Sensemaking with AI Augmentation 

A follow-up study will explore how artificial intelligence (AI) can augment healthcare professionals in interpreting PGHD. This research-through-design approach focuses on the following research question:

• How do HCPs perceive AI integration for supporting patient generated health data sense-making during PA planning in cardiac rehabilitation? 
• How do CVD patients perceive AI integration in supporting clinicians in their clinical workflows? 

Further collaborators: 

• Prof. Dr. Albrecht Schmidt, Ludwig Maximilians University of Munich (LMU)
• Assoc. Prof. Tiago Guerreiro, Faculdade de Ciências, Universidade de Lisboa 

Related publications: 

VS Pakianathan, P. (2024). Human Centered Approach for Designing Data Enabled Tools: Exploring the potential of patient generated data for CVD Prevention and Rehabilitation. In Mensch und Computer 2024-Workshopband (pp. 10-18420). Gesellschaft für Informatik eV. https://doi.org/10.18420/muc2024-mci-dc-183   

VS Pakianathan, P., Fatehi, A., & Smeddinck, J. (2024). Towards AI Augmented Personalized Data Sensemaking. In Mensch und Computer 2024-Workshopband (pp. 10-18420). Gesellschaft für Informatik eV. https://doi.org/10.18420/muc2024-mci-ws05-182  

VS Pakianathan P, Kumar D, Prabath J, Hussein R, Niebauer J, Schmidt A, Smeddinck J. Scoping Review on Barriers and Enablers in Integrating Patient-Generated Health Data for Shared Decision-Making. JMIR Preprints. 02/10/2025:85197 DOI: 10.2196/preprints.85197 URL: https://preprints.jmir.org/preprint/85197

Pakianathan, P. V. S., Islambouli, R., McGowan, H., Branco, D., Guerreiro, T., & Smeddinck, J. D. (2025). Exploring Human-AI Interaction with Patient-Generated Health Data Sensemaking for Cardiac Risk Reduction. Presented as demonstration at the workshop on visual analytics in healthcare (VAHC) (in conjunction with IEEE VIS 2025) >> Link

Pakianathan, P. V. S., McGowan, H., Höppchen, I., Wurhofer, D., Treff, G., Sareban, M., Niebauer, J., Schmidt, A., & Smeddinck, J. D. (2025). Towards Data-Enabled Physical Activity Planning: An Exploratory Study of HCP Perspectives On The Integration Of Patient-Generated Health Data. 19th EAI International Conference on Pervasive Computing Technologies for Healthcare >> Link