Exploring AI-generated images as memory aids in elderly care

• Published in: Studies in Science and Technology Vol. 13; no. 2; pp. 101 - 108
• Main Authors: Shimizu Kousuke, Hamaguchi Naoki, Dongeun Choi, Iwamoto Miyuki, Siriaraya Panote, Kuwahara Noriaki
• Format: Journal Article
• Language: English
• Published: 科学・技術研究会 2024; Society for Science and Technology
• ISSN: 2186-4942; 2187-1590
• DOI: 10.11425/sst.13.101

The rapidly aging population in Japan presents significant challenges for elderly care, particularly in enhancing communication and memory retention for individuals with dementia. This preliminary study explores the potential of AI-generated images as memory aids to improve communication between caregivers and elderly individuals. Utilizing a Stable Diffusion AI model, we generated images based on personal episodes and assessed their impact on memory retention and comprehension. Initial experiments with university students highlighted the importance of image relevance and quality, leading to improvements in AI-generated images. Subsequent tests with elderly participants demonstrated that AI-generated images significantly enhanced memory retention and understanding of the episodes compared to text-only descriptions. Our findings suggest that AI-generated images can serve as effective memory aids, facilitating better communication and potentially improving the quality of life for the elderly. This study opens avenues for developing advanced AI-based tools to support caregivers and address the growing needs of an aging society.