Detecting early stage dementia based on natural language processing

Daisaku Shibata, Kaoru Ito, Shoko Wakamiya, Eiji Aramaki

Research output: Contribution to journalArticle

Abstract

We construct an elderly corpus with a control group (EC) comprising narratives of elderly people with Mild Cognitive Impairment (MCI), healthy elderly people, and younger people in order to develop a method to classify the elderly into healthy and MCI by analyzing the corpus. To do so, we carry out three tasks (picture description task: PDT, episode picture description task: EDT, and animation description task: ADT) to participants (n = 80) and their voices to the tasks are recorded andmanually transcribed. 60 out of the participants are the elderly and classified into MCI and healthy control based on Mini Mental State Examination (MMSE). Then, language features such as Type Token Ratio and Idea Density are extracted by analyzing the elderly people’s data and machine learning models are built with the extracted features. In the experiments, our classification model using combined language features obtained from all tasks’ data achieved the highest performance (AUC = 0.85). The results indicate that it would be important to carry out multiple tasks to detect the elderly with MCI.

Original languageEnglish
JournalTransactions of the Japanese Society for Artificial Intelligence
Volume34
Issue number4
DOIs
Publication statusPublished - Jan 1 2019

Fingerprint

Processing
Animation
Learning systems
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

Detecting early stage dementia based on natural language processing. / Shibata, Daisaku; Ito, Kaoru; Wakamiya, Shoko; Aramaki, Eiji.

In: Transactions of the Japanese Society for Artificial Intelligence, Vol. 34, No. 4, 01.01.2019.

Research output: Contribution to journalArticle

@article{863ebd8ee89c4ae29c75b87018184a25,
title = "Detecting early stage dementia based on natural language processing",
abstract = "We construct an elderly corpus with a control group (EC) comprising narratives of elderly people with Mild Cognitive Impairment (MCI), healthy elderly people, and younger people in order to develop a method to classify the elderly into healthy and MCI by analyzing the corpus. To do so, we carry out three tasks (picture description task: PDT, episode picture description task: EDT, and animation description task: ADT) to participants (n = 80) and their voices to the tasks are recorded andmanually transcribed. 60 out of the participants are the elderly and classified into MCI and healthy control based on Mini Mental State Examination (MMSE). Then, language features such as Type Token Ratio and Idea Density are extracted by analyzing the elderly people’s data and machine learning models are built with the extracted features. In the experiments, our classification model using combined language features obtained from all tasks’ data achieved the highest performance (AUC = 0.85). The results indicate that it would be important to carry out multiple tasks to detect the elderly with MCI.",
author = "Daisaku Shibata and Kaoru Ito and Shoko Wakamiya and Eiji Aramaki",
year = "2019",
month = "1",
day = "1",
doi = "10.1527/tjsai.B-J11",
language = "English",
volume = "34",
journal = "Transactions of the Japanese Society for Artificial Intelligence",
issn = "1346-0714",
publisher = "Japanese Society for Artificial Intelligence",
number = "4",

}

TY - JOUR

T1 - Detecting early stage dementia based on natural language processing

AU - Shibata, Daisaku

AU - Ito, Kaoru

AU - Wakamiya, Shoko

AU - Aramaki, Eiji

PY - 2019/1/1

Y1 - 2019/1/1

N2 - We construct an elderly corpus with a control group (EC) comprising narratives of elderly people with Mild Cognitive Impairment (MCI), healthy elderly people, and younger people in order to develop a method to classify the elderly into healthy and MCI by analyzing the corpus. To do so, we carry out three tasks (picture description task: PDT, episode picture description task: EDT, and animation description task: ADT) to participants (n = 80) and their voices to the tasks are recorded andmanually transcribed. 60 out of the participants are the elderly and classified into MCI and healthy control based on Mini Mental State Examination (MMSE). Then, language features such as Type Token Ratio and Idea Density are extracted by analyzing the elderly people’s data and machine learning models are built with the extracted features. In the experiments, our classification model using combined language features obtained from all tasks’ data achieved the highest performance (AUC = 0.85). The results indicate that it would be important to carry out multiple tasks to detect the elderly with MCI.

AB - We construct an elderly corpus with a control group (EC) comprising narratives of elderly people with Mild Cognitive Impairment (MCI), healthy elderly people, and younger people in order to develop a method to classify the elderly into healthy and MCI by analyzing the corpus. To do so, we carry out three tasks (picture description task: PDT, episode picture description task: EDT, and animation description task: ADT) to participants (n = 80) and their voices to the tasks are recorded andmanually transcribed. 60 out of the participants are the elderly and classified into MCI and healthy control based on Mini Mental State Examination (MMSE). Then, language features such as Type Token Ratio and Idea Density are extracted by analyzing the elderly people’s data and machine learning models are built with the extracted features. In the experiments, our classification model using combined language features obtained from all tasks’ data achieved the highest performance (AUC = 0.85). The results indicate that it would be important to carry out multiple tasks to detect the elderly with MCI.

UR - http://www.scopus.com/inward/record.url?scp=85071239229&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071239229&partnerID=8YFLogxK

U2 - 10.1527/tjsai.B-J11

DO - 10.1527/tjsai.B-J11

M3 - Article

AN - SCOPUS:85071239229

VL - 34

JO - Transactions of the Japanese Society for Artificial Intelligence

JF - Transactions of the Japanese Society for Artificial Intelligence

SN - 1346-0714

IS - 4

ER -