Exploring Self-Tracking Practices of Older Adults with CVD to Design LLM-Enabled Health Data Sensemaking
D. Dai, P. V. S. Pakianathan, G. Treff, M. Sareban … S. Kuoppamäki
Proceedings of Mensch und Computer ’26 (MuC)
Abstract
Wearables and mobile health applications are increasingly adopted for self-management of chronic illnesses; yet the data feels overwhelming for older adults with cardiovascular disease (CVD). This study explores how they make sense of self-tracked data and identifies design opportunities for Large Language Model (LLM)-enabled support. We conducted a seven-day diary study and follow-up interviews with eight CVD patients aged 64–82. Findings highlight that self-tracking is affective, interpretive, and socially situated, and are guided by six themes: navigating emotional complexity, owning health narratives, prioritizing bodily sensations, selective engagement with health metrics, negotiating the socio-technical dynamics of sharing, and cautious optimism toward AI. We outline design directions for LLM-enabled data sensemaking systems.