CloudEcho: Exploring the Role of Large Conversational Language Models in Enhancing Home Care Models and Communication Quality

Abstract

Depression is a prevalent and recurrent mental disorder affecting over one billion individuals annually, imposing significant burdens on healthcare systems and patient families. Although smart technologies facilitate real-time monitoring and data collection in depression care, research seldom examines mechanisms for preserving shared well-being between patients and family caregivers. This study introduces CloudEcho, a collaborative home-care management tool powered by fine-tuned Large Conversational Language Models (LLMs). CloudEcho enables free-form patient–LLM dialogue that adheres to mental health guidelines and supports timely sharing of personal experiences and vital clinical information when caregivers are unavailable. An exploratory evaluation involving 50 patients and five mental health professionals demonstrated enhancements in patient–caregiver communication, caregiver empathy, and the richness of patient daily records for diagnostic use. These findings offer insights into LLM integration in mental health and inform design recommendations for future AI-supported home-care systems.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 5 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.