Study on indicators for depression in the elderly using voice and attribute information

Masakazu Higuchi; Shuji Shinohara; Mitsuteru Nakamura; Yasuhiro Omiya; Naoki Hagiwara; Takeshi Takano; Shunji Mitsuyoshi; Shinichi Tokuno

doi:10.1007/978-3-319-93644-4_7

Study on indicators for depression in the elderly using voice and attribute information

Masakazu Higuchi, Shuji Shinohara, Mitsuteru Nakamura, Yasuhiro Omiya, Naoki Hagiwara, Takeshi Takano, Shunji Mitsuyoshi, Shinichi Tokuno

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

Abstract

As the age of the human population increases worldwide, depression in elderly patients has become a problem in medical care. In this study, we analyzed voice-emotion component data, attribute data, and Beck Depression Inventory (BDI) scores by multivariate analysis, particularly in the elderly, and proposed evaluation indicators for estimating the state of depression of elderly patients. We divided the data into two groups according to BDI scores: a state of depression and the absence of this state. The labels distinguishing the two groups were dependent variables, while the voice-emotion component and attribute information were set as independent variables, and we performed logistic regression analysis on the data. We obtained a prediction model with significantly sufficient fitness. In the receiver operating characteristic curve for the proposed depression evaluation indicator, a sorting performance with an area under the curve of approximately 0.93 was obtained.

Original language	English (US)
Title of host publication	Information and Communication Technologies for Ageing Well and e-Health - 3rd International Conference, ICT4AWE 2017, Revised Selected Papers
Editors	Leszek Maciaszek, John O Donoghue, William Molloy, Carsten Rocker, Martina Ziefle
Publisher	Springer Verlag
Pages	127-146
Number of pages	20
ISBN (Print)	9783319936437
DOIs	https://doi.org/10.1007/978-3-319-93644-4_7
State	Published - 2018
Externally published	Yes
Event	3rd International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2017 - Porto, Portugal Duration: Apr 28 2017 → Apr 29 2017

Publication series

Name	Communications in Computer and Information Science
Volume	869
ISSN (Print)	1865-0929

Conference

Conference	3rd International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2017
Country	Portugal
City	Porto
Period	4/28/17 → 4/29/17

Keywords

Attribute information
Beck depression inventory
Depression
Emotion recognition
Voice

ASJC Scopus subject areas

Computer Science(all)
Mathematics(all)

Access to Document

10.1007/978-3-319-93644-4_7

Fingerprint Dive into the research topics of 'Study on indicators for depression in the elderly using voice and attribute information'. Together they form a unique fingerprint.

Cite this

Higuchi, M., Shinohara, S., Nakamura, M., Omiya, Y., Hagiwara, N., Takano, T., Mitsuyoshi, S., & Tokuno, S. (2018). Study on indicators for depression in the elderly using voice and attribute information. In L. Maciaszek, J. O Donoghue, W. Molloy, C. Rocker, & M. Ziefle (Eds.), Information and Communication Technologies for Ageing Well and e-Health - 3rd International Conference, ICT4AWE 2017, Revised Selected Papers (pp. 127-146). (Communications in Computer and Information Science; Vol. 869). Springer Verlag. https://doi.org/10.1007/978-3-319-93644-4_7

Study on indicators for depression in the elderly using voice and attribute information. / Higuchi, Masakazu; Shinohara, Shuji; Nakamura, Mitsuteru; Omiya, Yasuhiro; Hagiwara, Naoki; Takano, Takeshi; Mitsuyoshi, Shunji; Tokuno, Shinichi.

Information and Communication Technologies for Ageing Well and e-Health - 3rd International Conference, ICT4AWE 2017, Revised Selected Papers. ed. / Leszek Maciaszek; John O Donoghue; William Molloy; Carsten Rocker; Martina Ziefle. Springer Verlag, 2018. p. 127-146 (Communications in Computer and Information Science; Vol. 869).

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

Higuchi, M, Shinohara, S, Nakamura, M, Omiya, Y, Hagiwara, N, Takano, T, Mitsuyoshi, S & Tokuno, S 2018, Study on indicators for depression in the elderly using voice and attribute information. in L Maciaszek, J O Donoghue, W Molloy, C Rocker & M Ziefle (eds), Information and Communication Technologies for Ageing Well and e-Health - 3rd International Conference, ICT4AWE 2017, Revised Selected Papers. Communications in Computer and Information Science, vol. 869, Springer Verlag, pp. 127-146, 3rd International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2017, Porto, Portugal, 4/28/17. https://doi.org/10.1007/978-3-319-93644-4_7

Higuchi M, Shinohara S, Nakamura M, Omiya Y, Hagiwara N, Takano T et al. Study on indicators for depression in the elderly using voice and attribute information. In Maciaszek L, O Donoghue J, Molloy W, Rocker C, Ziefle M, editors, Information and Communication Technologies for Ageing Well and e-Health - 3rd International Conference, ICT4AWE 2017, Revised Selected Papers. Springer Verlag. 2018. p. 127-146. (Communications in Computer and Information Science). https://doi.org/10.1007/978-3-319-93644-4_7

Higuchi, Masakazu ; Shinohara, Shuji ; Nakamura, Mitsuteru ; Omiya, Yasuhiro ; Hagiwara, Naoki ; Takano, Takeshi ; Mitsuyoshi, Shunji ; Tokuno, Shinichi. / Study on indicators for depression in the elderly using voice and attribute information. Information and Communication Technologies for Ageing Well and e-Health - 3rd International Conference, ICT4AWE 2017, Revised Selected Papers. editor / Leszek Maciaszek ; John O Donoghue ; William Molloy ; Carsten Rocker ; Martina Ziefle. Springer Verlag, 2018. pp. 127-146 (Communications in Computer and Information Science).

@inproceedings{b47b5ed760ca4545b762809ec26d24e2,

title = "Study on indicators for depression in the elderly using voice and attribute information",

abstract = "As the age of the human population increases worldwide, depression in elderly patients has become a problem in medical care. In this study, we analyzed voice-emotion component data, attribute data, and Beck Depression Inventory (BDI) scores by multivariate analysis, particularly in the elderly, and proposed evaluation indicators for estimating the state of depression of elderly patients. We divided the data into two groups according to BDI scores: a state of depression and the absence of this state. The labels distinguishing the two groups were dependent variables, while the voice-emotion component and attribute information were set as independent variables, and we performed logistic regression analysis on the data. We obtained a prediction model with significantly sufficient fitness. In the receiver operating characteristic curve for the proposed depression evaluation indicator, a sorting performance with an area under the curve of approximately 0.93 was obtained.",

keywords = "Attribute information, Beck depression inventory, Depression, Emotion recognition, Voice",

author = "Masakazu Higuchi and Shuji Shinohara and Mitsuteru Nakamura and Yasuhiro Omiya and Naoki Hagiwara and Takeshi Takano and Shunji Mitsuyoshi and Shinichi Tokuno",

note = "Funding Information: Acknowledgements. This research is (partially) supported by the Center of Innovation Program from Japan Science and Technology Agency, JST. This work was supported by JSPS KAKENHI Grant Numbers JP15H03002 and JP17K01404.; 3rd International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2017 ; Conference date: 28-04-2017 Through 29-04-2017",

year = "2018",

doi = "10.1007/978-3-319-93644-4_7",

language = "English (US)",

isbn = "9783319936437",

series = "Communications in Computer and Information Science",

publisher = "Springer Verlag",

pages = "127--146",

editor = "Leszek Maciaszek and {O Donoghue}, John and William Molloy and Carsten Rocker and Martina Ziefle",

booktitle = "Information and Communication Technologies for Ageing Well and e-Health - 3rd International Conference, ICT4AWE 2017, Revised Selected Papers",

}

TY - GEN

T1 - Study on indicators for depression in the elderly using voice and attribute information

AU - Higuchi, Masakazu

AU - Shinohara, Shuji

AU - Nakamura, Mitsuteru

AU - Omiya, Yasuhiro

AU - Hagiwara, Naoki

AU - Takano, Takeshi

AU - Mitsuyoshi, Shunji

AU - Tokuno, Shinichi

N1 - Funding Information: Acknowledgements. This research is (partially) supported by the Center of Innovation Program from Japan Science and Technology Agency, JST. This work was supported by JSPS KAKENHI Grant Numbers JP15H03002 and JP17K01404.

PY - 2018

Y1 - 2018

N2 - As the age of the human population increases worldwide, depression in elderly patients has become a problem in medical care. In this study, we analyzed voice-emotion component data, attribute data, and Beck Depression Inventory (BDI) scores by multivariate analysis, particularly in the elderly, and proposed evaluation indicators for estimating the state of depression of elderly patients. We divided the data into two groups according to BDI scores: a state of depression and the absence of this state. The labels distinguishing the two groups were dependent variables, while the voice-emotion component and attribute information were set as independent variables, and we performed logistic regression analysis on the data. We obtained a prediction model with significantly sufficient fitness. In the receiver operating characteristic curve for the proposed depression evaluation indicator, a sorting performance with an area under the curve of approximately 0.93 was obtained.

AB - As the age of the human population increases worldwide, depression in elderly patients has become a problem in medical care. In this study, we analyzed voice-emotion component data, attribute data, and Beck Depression Inventory (BDI) scores by multivariate analysis, particularly in the elderly, and proposed evaluation indicators for estimating the state of depression of elderly patients. We divided the data into two groups according to BDI scores: a state of depression and the absence of this state. The labels distinguishing the two groups were dependent variables, while the voice-emotion component and attribute information were set as independent variables, and we performed logistic regression analysis on the data. We obtained a prediction model with significantly sufficient fitness. In the receiver operating characteristic curve for the proposed depression evaluation indicator, a sorting performance with an area under the curve of approximately 0.93 was obtained.

KW - Attribute information

KW - Beck depression inventory

KW - Depression

KW - Emotion recognition

KW - Voice

UR - http://www.scopus.com/inward/record.url?scp=85049044868&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049044868&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-93644-4_7

DO - 10.1007/978-3-319-93644-4_7

M3 - Conference contribution

AN - SCOPUS:85049044868

SN - 9783319936437

T3 - Communications in Computer and Information Science

SP - 127

EP - 146

BT - Information and Communication Technologies for Ageing Well and e-Health - 3rd International Conference, ICT4AWE 2017, Revised Selected Papers

A2 - Maciaszek, Leszek

A2 - O Donoghue, John

A2 - Molloy, William

A2 - Rocker, Carsten

A2 - Ziefle, Martina

PB - Springer Verlag

T2 - 3rd International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2017

Y2 - 28 April 2017 through 29 April 2017

ER -