MCI Detection Based on Deep Learning with Voice Spectrogram

Hong Han Hank Chau; Yawgeng Chau; Hsiao Lun Wang; Yi Fang Chuang; Chien Cheng Lee

doi:10.1109/ECBIOS54627.2022.9945032

MCI Detection Based on Deep Learning with Voice Spectrogram

Hong Han Hank Chau, Yawgeng Chau, Hsiao Lun Wang, Yi Fang Chuang, Chien Cheng Lee

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

We conduct a study on the classification of mild cognitive impairment (MCI) which is an early stage of dementia. We employ deep learning with a voice spectrogram for MCI detection. In accordance with the psychiatrist's diagnosis and the patient's score on the Mini-Mental State Examination (MMSE), the true status of the potential patient is labeled. Using the images of the voice spectrogram, we applied the convolutional neural networks (CNN) for MCI classification, where the optimal decision threshold was explored. With the optimal threshold, the precision and recall of patient-based classification are 75 and 82%, respectively.

Original language	English
Title of host publication	Proceedings of the 2022 IEEE 4th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022
Editors	Teen-Hang Meen
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	212-216
Number of pages	5
ISBN (Electronic)	9781728195797
DOIs	https://doi.org/10.1109/ECBIOS54627.2022.9945032
State	Published - 2022
Event	4th IEEE Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022 - Tainan, Taiwan Duration: 27 May 2022 → 29 May 2022

Publication series

Name	Proceedings of the 2022 IEEE 4th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022

Conference

Conference	4th IEEE Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022
Country/Territory	Taiwan
City	Tainan
Period	27/05/22 → 29/05/22

Keywords

Deep Learning
Dementia
Mild Cognitive Impairment
Voice Spectrogram

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ECBIOS54627.2022.9945032

Cite this

Chau, H. H. H., Chau, Y., Wang, H. L., Chuang, Y. F., & Lee, C. C. (2022). MCI Detection Based on Deep Learning with Voice Spectrogram. In T.-H. Meen (Ed.), Proceedings of the 2022 IEEE 4th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022 (pp. 212-216). (Proceedings of the 2022 IEEE 4th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ECBIOS54627.2022.9945032

Chau, Hong Han Hank ; Chau, Yawgeng ; Wang, Hsiao Lun et al. / MCI Detection Based on Deep Learning with Voice Spectrogram. Proceedings of the 2022 IEEE 4th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022. editor / Teen-Hang Meen. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 212-216 (Proceedings of the 2022 IEEE 4th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022).

@inproceedings{a09d03df6c3e4b7fa05037d7769acc52,

title = "MCI Detection Based on Deep Learning with Voice Spectrogram",

abstract = "We conduct a study on the classification of mild cognitive impairment (MCI) which is an early stage of dementia. We employ deep learning with a voice spectrogram for MCI detection. In accordance with the psychiatrist's diagnosis and the patient's score on the Mini-Mental State Examination (MMSE), the true status of the potential patient is labeled. Using the images of the voice spectrogram, we applied the convolutional neural networks (CNN) for MCI classification, where the optimal decision threshold was explored. With the optimal threshold, the precision and recall of patient-based classification are 75 and 82%, respectively.",

keywords = "Deep Learning, Dementia, Mild Cognitive Impairment, Voice Spectrogram",

author = "Chau, {Hong Han Hank} and Yawgeng Chau and Wang, {Hsiao Lun} and Chuang, {Yi Fang} and Lee, {Chien Cheng}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 4th IEEE Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022 ; Conference date: 27-05-2022 Through 29-05-2022",

year = "2022",

doi = "10.1109/ECBIOS54627.2022.9945032",

language = "English",

series = "Proceedings of the 2022 IEEE 4th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "212--216",

editor = "Teen-Hang Meen",

booktitle = "Proceedings of the 2022 IEEE 4th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022",

address = "美國",

}

Chau, HHH, Chau, Y, Wang, HL, Chuang, YF & Lee, CC 2022, MCI Detection Based on Deep Learning with Voice Spectrogram. in T-H Meen (ed.), Proceedings of the 2022 IEEE 4th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022. Proceedings of the 2022 IEEE 4th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022, Institute of Electrical and Electronics Engineers Inc., pp. 212-216, 4th IEEE Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022, Tainan, Taiwan, 27/05/22. https://doi.org/10.1109/ECBIOS54627.2022.9945032

MCI Detection Based on Deep Learning with Voice Spectrogram. / Chau, Hong Han Hank; Chau, Yawgeng; Wang, Hsiao Lun et al.
Proceedings of the 2022 IEEE 4th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022. ed. / Teen-Hang Meen. Institute of Electrical and Electronics Engineers Inc., 2022. p. 212-216 (Proceedings of the 2022 IEEE 4th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - MCI Detection Based on Deep Learning with Voice Spectrogram

AU - Chau, Hong Han Hank

AU - Chau, Yawgeng

AU - Wang, Hsiao Lun

AU - Chuang, Yi Fang

AU - Lee, Chien Cheng

PY - 2022

Y1 - 2022

N2 - We conduct a study on the classification of mild cognitive impairment (MCI) which is an early stage of dementia. We employ deep learning with a voice spectrogram for MCI detection. In accordance with the psychiatrist's diagnosis and the patient's score on the Mini-Mental State Examination (MMSE), the true status of the potential patient is labeled. Using the images of the voice spectrogram, we applied the convolutional neural networks (CNN) for MCI classification, where the optimal decision threshold was explored. With the optimal threshold, the precision and recall of patient-based classification are 75 and 82%, respectively.

AB - We conduct a study on the classification of mild cognitive impairment (MCI) which is an early stage of dementia. We employ deep learning with a voice spectrogram for MCI detection. In accordance with the psychiatrist's diagnosis and the patient's score on the Mini-Mental State Examination (MMSE), the true status of the potential patient is labeled. Using the images of the voice spectrogram, we applied the convolutional neural networks (CNN) for MCI classification, where the optimal decision threshold was explored. With the optimal threshold, the precision and recall of patient-based classification are 75 and 82%, respectively.

KW - Deep Learning

KW - Dementia

KW - Mild Cognitive Impairment

KW - Voice Spectrogram

UR - http://www.scopus.com/inward/record.url?scp=85143130773&partnerID=8YFLogxK

U2 - 10.1109/ECBIOS54627.2022.9945032

DO - 10.1109/ECBIOS54627.2022.9945032

M3 - Conference contribution

AN - SCOPUS:85143130773

T3 - Proceedings of the 2022 IEEE 4th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022

SP - 212

EP - 216

BT - Proceedings of the 2022 IEEE 4th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022

A2 - Meen, Teen-Hang

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 4th IEEE Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022

Y2 - 27 May 2022 through 29 May 2022

ER -

Chau HHH, Chau Y, Wang HL, Chuang YF, Lee CC. MCI Detection Based on Deep Learning with Voice Spectrogram. In Meen TH, editor, Proceedings of the 2022 IEEE 4th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 212-216. (Proceedings of the 2022 IEEE 4th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022). doi: 10.1109/ECBIOS54627.2022.9945032

MCI Detection Based on Deep Learning with Voice Spectrogram

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this