Title: Predicting Future Dementia Onset from Drawing: An AI Model Born from Clinical Practice
Speaker: Ms. Mio Shinozaki (Specially Appointed Researcher, Department of Preventive Science, Center for Advanced Medical Development in Dementia, National Center for Geriatrics and Gerontology, National Research and Development Agency)
Abstract: Artificial intelligence (AI) is opening new possibilities in dementia care. While memory loss is often emphasized when discussing dementia, it may not appear in the early stages of the disease. Therefore, we focused on visuospatial cognition rather than memory and developed an AI model that predicts future dementia risk from drawing data. This model can highly accurately estimate the risk of onset several years later with just a few minutes of testing. Consequently, it is anticipated as a new screening method in the current era where early detection is crucial. In this presentation, we will introduce how clinical insights led to AI model development, the trial-and-error process using patient data, and the challenges and prospects for societal implementation.
- Date
-
9th January, 2026（Fri,）18:00～20:00
- Venue
-
Held online
- Organizer
-
Co-organizer (HRAM The Japan Society for Industrial and Applied Mathematics, D-DRIVE National Network)
- Participation Fee
-
Free（Advance registration required）
https://www-mmds.sigmath.es.osaka-u.ac.jp/structure/activity/ai_data.php?id=104
- web
-
https://www-mmds.sigmath.es.osaka-u.ac.jp/structure/activity/ai_data.php?id=104
- Contact
-
Takashi Suzuki
suzuki@sigmath.es.osaka-u.ac.jp