Mahdi Sareban

Duosi Dai, Pavithren V S Pakianathan, Gunnar Treff et al.

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. We identified six themes: navigating emotional complexity, owning health narratives, prioritizing bodily sensations, selective engagement with health metrics, negotiating socio-technical dynamics of sharing, and cautious optimism toward AI. Findings highlight that self-tracking is affective, interpretive, and socially situated. We outline design directions for LLM-enabled data sensemaking systems: supporting emotional engagement, reinforcing patient agency, acknowledging embodied experiences, and prompting dialogue in clinical and social contexts. To support safety, expert-in-the-loop mechanisms are essential. These directions articulate how LLMs can help translate data into narratives and carry implications for human-data interaction and behavior-change support.

David Haag, Devender Kumar, Sebastian Gruber et al.

We evaluated the viability of using Large Language Models (LLMs) to trigger and personalize content in Just-in-Time Adaptive Interventions (JITAIs) in digital health. As an interaction pattern representative of context-aware computing, JITAIs are being explored for their potential to support sustainable behavior change, adapting interventions to an individual's current context and needs. Challenging traditional JITAI implementation models, which face severe scalability and flexibility limitations, we tested GPT-4 for suggesting JITAIs in the use case of heart-healthy activity in cardiac rehabilitation. Using three personas representing patients affected by CVD with varying severeness and five context sets per persona, we generated 450 JITAI decisions and messages. These were systematically evaluated against those created by 10 laypersons (LayPs) and 10 healthcare professionals (HCPs). GPT-4-generated JITAIs surpassed human-generated intervention suggestions, outperforming both LayPs and HCPs across all metrics (i.e., appropriateness, engagement, effectiveness, and professionalism). These results highlight the potential of LLMs to enhance JITAI implementations in personalized health interventions, demonstrating how generative AI could revolutionize context-aware computing.