🤖 AI Summary
This study addresses the scarcity of supportive tools for reminiscence therapy in patients with mild dementia by developing a browser-based, voice-first multimodal conversational AI assistant. Integrating voice interaction, multimodal content generation, and web technologies, this work introduces a novel audio-visual guided reminiscence intervention prototype tailored specifically for this population. The research successfully constructed and validated the feasibility of this system, demonstrating its potential to mitigate cognitive decline and enhance intervention accessibility. Consequently, this project establishes an innovative paradigm and provides technical validation for digital non-pharmacological interventions in dementia care.
📝 Abstract
With the global population aging and increasing prevalence of dementia, there is an urgent need for effective solutions to support patients across various stages of Alzheimer's Disease and Related Dementias (ADRD). Reminiscence Therapy (RT) is a validated intervention designed to trigger memories and is widely used for various stages of dementia. We present our preliminary prototype and exploration of RemiVoice, a browser-based voice-first conversational AI assistant that supports older adults with mild dementia in RT through conversationally grounded images and videos.