軽度認知障害のスクリーニングに向けた階層型ニューラルネットワークモデルの提案

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2023/04/01

タイトル(英語): A Hierarchical Neural Network Model for Japanese Toward Detecting Mild Cognitive Impairment

著者名: 後藤　哲史（帝京平成大学 健康メディカル学部）

著者名(英語): Tetsuji Goto (Faculty of Health and Medical Science, Teikyo Heisei University)

キーワード: 軽度認知障害，スクリーニング，ニューラルネットワーク，LSTM，自然言語処理　　mild cognitive impairment，screening，neural netowork，long short term memory，natural language processing

要約(英語): We found that some signs of Mild Cognitive Impairment (MCI) might be presented in a structure of a sentence and a relation between sentences talked by a man, and develop a neural network model which has an analogy with the hierarchical structure of speakers, tpoics, sentences and words in Japanese. We build our model based on 2-layered bi-directional LSTM, corresponding to words-sentences and sentences-topics hierarchy. As a layer corresponding to speakers, we use a linear classifier with self-attention. The test result shows a largely improved AUC, compared with our another test by using the normal 2-layered bi-directional LSTM with TBPTT. The result also indicates that there are some characteristic patterns in a talk by an elderly person with MCI. We classify the character vectors of topics generated from our model through learning into clusters whose number is 1/10 of the number of persons in our data. Since these clusters have almost less than 10% or more than 90% rate of positive share, we conclude that we can develop a screening method based on a talk in Japanese by an elderly person in the near future.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.143 No.4 （2023） 特集：医療/ヘルスケア×AI－量子・情報・エレクトロニクスの応用として

本誌掲載ページ: 465-470 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/143/4/143_465/_article/-char/ja/