Cargando…

Dementia risks identified by vocal features via telephone conversations: A novel machine learning prediction model

Due to difficulty in early diagnosis of Alzheimer’s disease (AD) related to cost and differentiated capability, it is necessary to identify low-cost, accessible, and reliable tools for identifying AD risk in the preclinical stage. We hypothesized that cognitive ability, as expressed in the vocal fea...

Descripción completa

Detalles Bibliográficos
Autores principales: Shimoda, Akihiro, Li, Yue, Hayashi, Hana, Kondo, Naoki
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8279312/
https://www.ncbi.nlm.nih.gov/pubmed/34260593
http://dx.doi.org/10.1371/journal.pone.0253988
_version_ 1783722428261728256
author Shimoda, Akihiro
Li, Yue
Hayashi, Hana
Kondo, Naoki
author_facet Shimoda, Akihiro
Li, Yue
Hayashi, Hana
Kondo, Naoki
author_sort Shimoda, Akihiro
collection PubMed
description Due to difficulty in early diagnosis of Alzheimer’s disease (AD) related to cost and differentiated capability, it is necessary to identify low-cost, accessible, and reliable tools for identifying AD risk in the preclinical stage. We hypothesized that cognitive ability, as expressed in the vocal features in daily conversation, is associated with AD progression. Thus, we have developed a novel machine learning prediction model to identify AD risk by using the rich voice data collected from daily conversations, and evaluated its predictive performance in comparison with a classification method based on the Japanese version of the Telephone Interview for Cognitive Status (TICS-J). We used 1,465 audio data files from 99 Healthy controls (HC) and 151 audio data files recorded from 24 AD patients derived from a dementia prevention program conducted by Hachioji City, Tokyo, between March and May 2020. After extracting vocal features from each audio file, we developed machine-learning models based on extreme gradient boosting (XGBoost), random forest (RF), and logistic regression (LR), using each audio file as one observation. We evaluated the predictive performance of the developed models by describing the receiver operating characteristic (ROC) curve, calculating the areas under the curve (AUCs), sensitivity, and specificity. Further, we conducted classifications by considering each participant as one observation, computing the average of their audio files’ predictive value, and making comparisons with the predictive performance of the TICS-J based questionnaire. Of 1,616 audio files in total, 1,308 (81.0%) were randomly allocated to the training data and 308 (19.1%) to the validation data. For audio file-based prediction, the AUCs for XGboost, RF, and LR were 0.863 (95% confidence interval [CI]: 0.794–0.931), 0.882 (95% CI: 0.840–0.924), and 0.893 (95%CI: 0.832–0.954), respectively. For participant-based prediction, the AUC for XGboost, RF, LR, and TICS-J were 1.000 (95%CI: 1.000–1.000), 1.000 (95%CI: 1.000–1.000), 0.972 (95%CI: 0.918–1.000) and 0.917 (95%CI: 0.918–1.000), respectively. There was difference in predictive accuracy of XGBoost and TICS-J with almost approached significance (p = 0.065). Our novel prediction model using the vocal features of daily conversations demonstrated the potential to be useful for the AD risk assessment.
format Online
Article
Text
id pubmed-8279312
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-82793122021-07-31 Dementia risks identified by vocal features via telephone conversations: A novel machine learning prediction model Shimoda, Akihiro Li, Yue Hayashi, Hana Kondo, Naoki PLoS One Research Article Due to difficulty in early diagnosis of Alzheimer’s disease (AD) related to cost and differentiated capability, it is necessary to identify low-cost, accessible, and reliable tools for identifying AD risk in the preclinical stage. We hypothesized that cognitive ability, as expressed in the vocal features in daily conversation, is associated with AD progression. Thus, we have developed a novel machine learning prediction model to identify AD risk by using the rich voice data collected from daily conversations, and evaluated its predictive performance in comparison with a classification method based on the Japanese version of the Telephone Interview for Cognitive Status (TICS-J). We used 1,465 audio data files from 99 Healthy controls (HC) and 151 audio data files recorded from 24 AD patients derived from a dementia prevention program conducted by Hachioji City, Tokyo, between March and May 2020. After extracting vocal features from each audio file, we developed machine-learning models based on extreme gradient boosting (XGBoost), random forest (RF), and logistic regression (LR), using each audio file as one observation. We evaluated the predictive performance of the developed models by describing the receiver operating characteristic (ROC) curve, calculating the areas under the curve (AUCs), sensitivity, and specificity. Further, we conducted classifications by considering each participant as one observation, computing the average of their audio files’ predictive value, and making comparisons with the predictive performance of the TICS-J based questionnaire. Of 1,616 audio files in total, 1,308 (81.0%) were randomly allocated to the training data and 308 (19.1%) to the validation data. For audio file-based prediction, the AUCs for XGboost, RF, and LR were 0.863 (95% confidence interval [CI]: 0.794–0.931), 0.882 (95% CI: 0.840–0.924), and 0.893 (95%CI: 0.832–0.954), respectively. For participant-based prediction, the AUC for XGboost, RF, LR, and TICS-J were 1.000 (95%CI: 1.000–1.000), 1.000 (95%CI: 1.000–1.000), 0.972 (95%CI: 0.918–1.000) and 0.917 (95%CI: 0.918–1.000), respectively. There was difference in predictive accuracy of XGBoost and TICS-J with almost approached significance (p = 0.065). Our novel prediction model using the vocal features of daily conversations demonstrated the potential to be useful for the AD risk assessment. Public Library of Science 2021-07-14 /pmc/articles/PMC8279312/ /pubmed/34260593 http://dx.doi.org/10.1371/journal.pone.0253988 Text en © 2021 Shimoda et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Shimoda, Akihiro
Li, Yue
Hayashi, Hana
Kondo, Naoki
Dementia risks identified by vocal features via telephone conversations: A novel machine learning prediction model
title Dementia risks identified by vocal features via telephone conversations: A novel machine learning prediction model
title_full Dementia risks identified by vocal features via telephone conversations: A novel machine learning prediction model
title_fullStr Dementia risks identified by vocal features via telephone conversations: A novel machine learning prediction model
title_full_unstemmed Dementia risks identified by vocal features via telephone conversations: A novel machine learning prediction model
title_short Dementia risks identified by vocal features via telephone conversations: A novel machine learning prediction model
title_sort dementia risks identified by vocal features via telephone conversations: a novel machine learning prediction model
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8279312/
https://www.ncbi.nlm.nih.gov/pubmed/34260593
http://dx.doi.org/10.1371/journal.pone.0253988
work_keys_str_mv AT shimodaakihiro dementiarisksidentifiedbyvocalfeaturesviatelephoneconversationsanovelmachinelearningpredictionmodel
AT liyue dementiarisksidentifiedbyvocalfeaturesviatelephoneconversationsanovelmachinelearningpredictionmodel
AT hayashihana dementiarisksidentifiedbyvocalfeaturesviatelephoneconversationsanovelmachinelearningpredictionmodel
AT kondonaoki dementiarisksidentifiedbyvocalfeaturesviatelephoneconversationsanovelmachinelearningpredictionmodel