RemiAssist: A Therapist-Supporting System for Photo-Based Reminiscence Therapy in Dementia Care

2026-07-27

AI Summary

This study addresses a critical gap in existing photo-based reminiscence therapy systems, which predominantly emphasize patient–AI interaction while overlooking the central role of therapists in therapeutic interventions. To bridge this gap, the authors propose a therapist-in-the-loop AI-assisted paradigm that structures patients’ life events into personalized memory graphs and employs context-aware algorithms to deliver real-time conversational guidance, thereby empowering therapists to lead tailored interventions. Field evaluations demonstrate that this approach significantly enhances intervention planning efficiency by 44% and increases dialogue duration by 54%, while also strengthening therapists’ responsiveness in sensitive situations. These findings underscore the paradigm’s innovative potential to elevate the quality and efficacy of reminiscence therapy through synergistic human–AI collaboration.

Abstract

Despite growing interest in applying AI to photo-based reminiscence therapy (PRT) for people with dementia (PwD), existing systems primarily focus on PwD-AI interaction and often overlook therapists' critical role in practical PRT delivery. We present RemiAssist, a system that supports therapist-in-the-loop PRT through AI-assisted planning and real-time facilitation. RemiAssist incorporates two core techniques: (1) a Memory Graph, which organizes key life events from a PwD's photo collection into a hierarchical graph to support theme-centered intervention planning; and (2) a Context-Aware Guiding Strategy, which provides real-time suggestions to help therapists guide reminiscence conversations and respond to sensitive situations. A field study with eight therapist-PwD dyads suggests that RemiAssist was associated with a 44% improvement in planning efficiency and a 54% increase in conversation duration, and provided timely support for handling sensitive situations. We highlight opportunities for AI systems to empower therapists and enable more personalized reminiscence therapy in dementia care.

Problem

• reminiscence therapy
• dementia care
• therapist support
• AI-assisted planning
• photo-based intervention

Innovation

• Memory Graph
• Context-Aware Guiding Strategy
• therapist-in-the-loop
• reminiscence therapy
• dementia care