Early Detection of Dementia Based on the Bayesian Classification Using Voice-fNIRS Signals during Cognitive Tasks

2016 Fiscal Year Final Research Report

• Project/Area Number: 25280100
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Partial Multi-year Fund
• Section: 一般
• Research Field: Kansei informatics
• Research Institution: Nagoya Institute of Technology
• Principal Investigator: Kato Shohei 名古屋工業大学, 工学(系)研究科(研究院), 教授 (70311032)
• Co-Investigator(Kenkyū-buntansha): 本間 昭 社会福祉法人浴風会認知症介護研究・研修東京センター, その他部局等, その他 (40081707) ; 遠藤 英俊 国立研究開発法人国立長寿医療研究センター, その他部局等, その他 (80501121)
• Project Period (FY): 2013-04-01 – 2017-03-31
• Keywords: 認知症スクリーニング / 医療・福祉サービス / 発話音声・脳血流解析 / 近赤外分光法 / 加齢工学

Outline of Final Research Achievements

This study proposes a novel approach for the early detection of cognitive impairment in the elderly, in which we focused on the prosodic features of speech sound during the subject’s answers to the questionnaire; the first was to detect signal and prosodic signs of cognitive impairment, the second was to take a measurement of cerebral blood flow (CBF). We then have developed a prototype of prosody-CBF hybrid screening system and discussed the cost-effectiveness and the discrimination performance.　Moreover, MCI group is divided into two subtypes of Nonamnestic-MCI (N-MCI) composed of ten participants and Amnestic-MCI (A-MCI) composed of nine participants. We will present a comparative analysis of CBF activation between CN, N-MCI, A-MCI, and AD, by statistical tests of between-group significant differences using fNIRS signals of oxy-Hb during the cognitive task.

Free Research Field

人工知能、知能・感性ロボティクス、医工連携情報処理