From 'What' to 'How' and 'Why': Sharing LLM-Generated Retrospective Summaries of Older Adults' Passive Tracking Data with Remote Family Members
Researchers have developed a new method using Large Language Models (LLMs) to generate retrospective summaries from passive tracking data for remote family members of older adults. The system, an evolution of Vital Insight, was refined based on feedback from 11 family members. The redesigned multi-layer, multi-agent approach significantly improved user satisfaction, perceived helpfulness, trust, and willingness to receive the summaries. AI
IMPACT Enhances LLM applications in healthcare by improving communication and trust between caregivers and patients' families.