CGM-Led Multimodal Tracking with Chatbot Support: An Autoethnography in Sub-Health

TL;DR

This study explores how combining continuous glucose monitoring with multimodal data and chatbot support can influence health behaviors in at-risk populations, extending CGM use beyond diabetes management.

Contribution

It introduces a novel approach integrating CGM, multimodal indicators, and LLM-based chatbots for preventive health in sub-health populations.

Findings

CGM-led tracking influences diet and activity choices

Chatbot support enhances health reflection and awareness

Multimodal data integration improves health monitoring

Abstract

Metabolic disorders present a pressing global health challenge, with China carrying the world's largest burden. While continuous glucose monitoring (CGM) has transformed diabetes care, its potential for supporting sub-health populations -- such as individuals who are overweight, prediabetic, or anxious -- remains underexplored. At the same time, large language models (LLMs) are increasingly used in health coaching, yet CGM is rarely incorporated as a first-class signal. To address this gap, we conducted a six-week autoethnography, combining CGM with multimodal indicators captured via common digital devices and a chatbot that offered personalized reflections and explanations of glucose fluctuations. Our findings show how CGM-led, data-first multimodal tracking, coupled with conversational support, shaped everyday practices of diet, activity, stress, and wellbeing. This work contributes to HCI by extending CGM research beyond clinical diabetes and demonstrating how LLM-driven agents can support preventive health and reflection in at-risk populations.