Cognitive and Motor Functions Evaluation Using Daily Activities for Integrated Dementia Assessment Systems

2023 Fiscal Year Final Research Report

• Project/Area Number: 20K12764
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 90150:Medical assistive technology-related
• Research Institution: Mie University
• Principal Investigator: Kawanaka Hiroharu 三重大学, 工学研究科, 教授 (30437115)
• Co-Investigator(Kenkyū-buntansha): 鶴岡 信治 鈴鹿医療科学大学, 医用工学部, 教授 (30126982)
• Project Period (FY): 2020-04-01 – 2024-03-31
• Keywords: 認知機能評価 / 運動機能評価 / 歩行機能 / 福祉情報システム / 画像認識 / 機械学習 / 深層学習

Outline of Final Research Achievements

In this research project, we aimed to develop a platform that integrates dementia evaluation systems and care records to comprehensively assess cognitive and motor functions. Specifically, we advanced the development of technologies related to systems that measure changes in daily conversation, text, shapes, and facial expressions, which we had been working on. Additionally, we researched methods to assess the progression of dementia by measuring finger movements and gaze movements using puzzle games, and developed a prototype system. Furthermore, we proposed a method to evaluate walking function by extracting features from videos of pedestrians and analyzing their time-series data, and examined the feasibility of its use in clinical settings. The experimental results suggested the effectiveness of the proposed method and its potential for practical use in clinical settings.

Free Research Field

福祉情報工学，知能情報システム，医療情報学

Academic Significance and Societal Importance of the Research Achievements

本研究課題は，従来の対話式や記述式の認知症判定テストを使用せず，日常会話や文字，図形，表情，仕草などを通じて認知機能と運動機能を評価するシステムの開発を目指すものである．このアプローチにより，被験者がテストを意識せずに自然な状態で評価が可能となり，テストに対する嫌悪感を軽減し，定期的かつ正確な評価を実現することができる．また，介護記録と連携することで，施設職員の負担を軽減し，機能訓練の代替となる．各利用者の認知症の進行度や運動機能の経時変化を把握し，介護環境の改善や利用者のQOL向上にも寄与する．複数施設での導入により，介護記録の標準化や施設横断的なデータ分析も可能になると考えられる．