Assessment of adjunct cognitive functioning through intake interviews integrated with natural language processing models

In this article, we developed an interview framework and natural language processing model for estimating cognitive function, based on an intake interview with psychologists in a hospital setting. The questionnaire consisted of 30 questions in five categories. To evaluate the developed interview ite...

Full description

Bibliographic Details
Main Authors: Toshiharu Igarashi, Yumi Umeda-Kameyama, Taro Kojima, Masahiro Akishita, Misato Nihei
Format: Article
Language:English
Published: Frontiers Media S.A. 2023-04-01
Series:Frontiers in Medicine
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmed.2023.1145314/full
_version_ 1797842606122598400
author Toshiharu Igarashi
Yumi Umeda-Kameyama
Taro Kojima
Masahiro Akishita
Misato Nihei
Misato Nihei
author_facet Toshiharu Igarashi
Yumi Umeda-Kameyama
Taro Kojima
Masahiro Akishita
Misato Nihei
Misato Nihei
author_sort Toshiharu Igarashi
collection DOAJ
description In this article, we developed an interview framework and natural language processing model for estimating cognitive function, based on an intake interview with psychologists in a hospital setting. The questionnaire consisted of 30 questions in five categories. To evaluate the developed interview items and the accuracy of the natural language processing model, we recruited participants with the approval of the University of Tokyo Hospital and obtained the cooperation of 29 participants (7 men and 22 women) aged 72–91 years. Based on the MMSE results, a multilevel classification model was created to classify the three groups, and a binary classification model to sort the two groups. For each of these models, we tested whether the accuracy would improve when text augmentation was performed. The accuracy in the multi-level classification results for the test data was 0.405 without augmentation and 0.991 with augmentation. The accuracy of the test data in the results of the binary classification without augmentation was 0.488 for the moderate dementia and mild dementia groups, 0.767 for the moderate dementia and MCI groups, and 0.700 for the mild dementia and MCI groups. In contrast, the accuracy of the test data in the augmented binary classification results was 0.972 for moderate dementia and mild dementia groups, 0.996 for moderate dementia and MCI groups, and 0.985 for mild dementia and MCI groups.
first_indexed 2024-04-09T16:50:40Z
format Article
id doaj.art-e743a184bd4d4a5a8a11c1c7e5ffd9a7
institution Directory Open Access Journal
issn 2296-858X
language English
last_indexed 2024-04-09T16:50:40Z
publishDate 2023-04-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Medicine
spelling doaj.art-e743a184bd4d4a5a8a11c1c7e5ffd9a72023-04-21T14:16:59ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2023-04-011010.3389/fmed.2023.11453141145314Assessment of adjunct cognitive functioning through intake interviews integrated with natural language processing modelsToshiharu Igarashi0Yumi Umeda-Kameyama1Taro Kojima2Masahiro Akishita3Misato Nihei4Misato Nihei5Department of Human and Engineered Environmental Studies, The University of Tokyo, Kashiwa, JapanDepartment of Geriatric Medicine, The University of Tokyo, Bunkyo-ku, Tokyo, JapanDepartment of Geriatric Medicine, The University of Tokyo, Bunkyo-ku, Tokyo, JapanDepartment of Geriatric Medicine, The University of Tokyo, Bunkyo-ku, Tokyo, JapanDepartment of Human and Engineered Environmental Studies, The University of Tokyo, Kashiwa, JapanInstitute of Gerontology, The University of Tokyo, Bunkyo-ku, Tokyo, JapanIn this article, we developed an interview framework and natural language processing model for estimating cognitive function, based on an intake interview with psychologists in a hospital setting. The questionnaire consisted of 30 questions in five categories. To evaluate the developed interview items and the accuracy of the natural language processing model, we recruited participants with the approval of the University of Tokyo Hospital and obtained the cooperation of 29 participants (7 men and 22 women) aged 72–91 years. Based on the MMSE results, a multilevel classification model was created to classify the three groups, and a binary classification model to sort the two groups. For each of these models, we tested whether the accuracy would improve when text augmentation was performed. The accuracy in the multi-level classification results for the test data was 0.405 without augmentation and 0.991 with augmentation. The accuracy of the test data in the results of the binary classification without augmentation was 0.488 for the moderate dementia and mild dementia groups, 0.767 for the moderate dementia and MCI groups, and 0.700 for the mild dementia and MCI groups. In contrast, the accuracy of the test data in the augmented binary classification results was 0.972 for moderate dementia and mild dementia groups, 0.996 for moderate dementia and MCI groups, and 0.985 for mild dementia and MCI groups.https://www.frontiersin.org/articles/10.3389/fmed.2023.1145314/fullgerontologyintake interviewnatural language processingdata augmentationcognitive function
spellingShingle Toshiharu Igarashi
Yumi Umeda-Kameyama
Taro Kojima
Masahiro Akishita
Misato Nihei
Misato Nihei
Assessment of adjunct cognitive functioning through intake interviews integrated with natural language processing models
Frontiers in Medicine
gerontology
intake interview
natural language processing
data augmentation
cognitive function
title Assessment of adjunct cognitive functioning through intake interviews integrated with natural language processing models
title_full Assessment of adjunct cognitive functioning through intake interviews integrated with natural language processing models
title_fullStr Assessment of adjunct cognitive functioning through intake interviews integrated with natural language processing models
title_full_unstemmed Assessment of adjunct cognitive functioning through intake interviews integrated with natural language processing models
title_short Assessment of adjunct cognitive functioning through intake interviews integrated with natural language processing models
title_sort assessment of adjunct cognitive functioning through intake interviews integrated with natural language processing models
topic gerontology
intake interview
natural language processing
data augmentation
cognitive function
url https://www.frontiersin.org/articles/10.3389/fmed.2023.1145314/full
work_keys_str_mv AT toshiharuigarashi assessmentofadjunctcognitivefunctioningthroughintakeinterviewsintegratedwithnaturallanguageprocessingmodels
AT yumiumedakameyama assessmentofadjunctcognitivefunctioningthroughintakeinterviewsintegratedwithnaturallanguageprocessingmodels
AT tarokojima assessmentofadjunctcognitivefunctioningthroughintakeinterviewsintegratedwithnaturallanguageprocessingmodels
AT masahiroakishita assessmentofadjunctcognitivefunctioningthroughintakeinterviewsintegratedwithnaturallanguageprocessingmodels
AT misatonihei assessmentofadjunctcognitivefunctioningthroughintakeinterviewsintegratedwithnaturallanguageprocessingmodels
AT misatonihei assessmentofadjunctcognitivefunctioningthroughintakeinterviewsintegratedwithnaturallanguageprocessingmodels