Identification of signs of depression relapse using audio-visual cues: A preliminary study

Muhammad Muzammel; Alice Othmani; Himadri Mukherjee; Hanan Salam

doi:10.1109/CBMS52027.2021.00018

Identification of signs of depression relapse using audio-visual cues: A preliminary study

Muhammad Muzammel, Alice Othmani, Himadri Mukherjee, Hanan Salam

Computer Science

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

Abstract

Depression is a serious mental disorder that affects many individuals across the globe. Depression (unipolar or bipolar) is characterized by a high rate of relapse or recurrence where a person might experience depressive episodes after non-depressive ones. The symptom patterns for recurrent depressive episodes have not been properly analyzed. Thus, there is a pressing need for systems which can monitor the mental health of individuals at risk to detect initial signs of relapse and recurrence. This points towards an automated system which identifies such signs and facilitates in timely treatment. In this paper, we introduce for the first time a deep learning based prospective monitoring system for the identification of relapse signs using audio-visual cues. The proposed model approximates relapse as the similarity between non-depression and depression samples. Experiments were performed on the DAIC-WOZ dataset and a highest accuracy of 73.21% was obtained using a Siamese network-based approach with one-shot learning regime.

Original language	English (US)
Title of host publication	Proceedings - 2021 IEEE 34th International Symposium on Computer-Based Medical Systems, CBMS 2021
Editors	Joao Rafael Almeida, Alejandro Rodriguez Gonzalez, Linlin Shen, Bridget Kane, Agma Traina, Paolo Soda, Jose Luis Oliveira
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	62-67
Number of pages	6
ISBN (Electronic)	9781665441216
DOIs	https://doi.org/10.1109/CBMS52027.2021.00018
State	Published - Jun 2021
Event	34th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2021 - Virtual, Online Duration: Jun 7 2021 → Jun 9 2021

Publication series

Name	Proceedings - IEEE Symposium on Computer-Based Medical Systems
Volume	2021-June
ISSN (Print)	1063-7125

Conference

Conference	34th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2021
City	Virtual, Online
Period	6/7/21 → 6/9/21

Keywords

Depression Relapse
One-shot learning
Recurrence
Siamese network

ASJC Scopus subject areas

Radiology Nuclear Medicine and imaging
Computer Science Applications

Access to Document

10.1109/CBMS52027.2021.00018

Cite this

Muzammel, M., Othmani, A., Mukherjee, H., & Salam, H. (2021). Identification of signs of depression relapse using audio-visual cues: A preliminary study. In J. R. Almeida, A. R. Gonzalez, L. Shen, B. Kane, A. Traina, P. Soda, & J. L. Oliveira (Eds.), Proceedings - 2021 IEEE 34th International Symposium on Computer-Based Medical Systems, CBMS 2021 (pp. 62-67). Article 9474716 (Proceedings - IEEE Symposium on Computer-Based Medical Systems; Vol. 2021-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CBMS52027.2021.00018

Identification of signs of depression relapse using audio-visual cues: A preliminary study. / Muzammel, Muhammad; Othmani, Alice; Mukherjee, Himadri et al.
Proceedings - 2021 IEEE 34th International Symposium on Computer-Based Medical Systems, CBMS 2021. ed. / Joao Rafael Almeida; Alejandro Rodriguez Gonzalez; Linlin Shen; Bridget Kane; Agma Traina; Paolo Soda; Jose Luis Oliveira. Institute of Electrical and Electronics Engineers Inc., 2021. p. 62-67 9474716 (Proceedings - IEEE Symposium on Computer-Based Medical Systems; Vol. 2021-June).

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

Muzammel, M, Othmani, A, Mukherjee, H & Salam, H 2021, Identification of signs of depression relapse using audio-visual cues: A preliminary study. in JR Almeida, AR Gonzalez, L Shen, B Kane, A Traina, P Soda & JL Oliveira (eds), Proceedings - 2021 IEEE 34th International Symposium on Computer-Based Medical Systems, CBMS 2021., 9474716, Proceedings - IEEE Symposium on Computer-Based Medical Systems, vol. 2021-June, Institute of Electrical and Electronics Engineers Inc., pp. 62-67, 34th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2021, Virtual, Online, 6/7/21. https://doi.org/10.1109/CBMS52027.2021.00018

Muzammel M, Othmani A, Mukherjee H, Salam H. Identification of signs of depression relapse using audio-visual cues: A preliminary study. In Almeida JR, Gonzalez AR, Shen L, Kane B, Traina A, Soda P, Oliveira JL, editors, Proceedings - 2021 IEEE 34th International Symposium on Computer-Based Medical Systems, CBMS 2021. Institute of Electrical and Electronics Engineers Inc. 2021. p. 62-67. 9474716. (Proceedings - IEEE Symposium on Computer-Based Medical Systems). doi: 10.1109/CBMS52027.2021.00018

Muzammel, Muhammad ; Othmani, Alice ; Mukherjee, Himadri et al. / Identification of signs of depression relapse using audio-visual cues : A preliminary study. Proceedings - 2021 IEEE 34th International Symposium on Computer-Based Medical Systems, CBMS 2021. editor / Joao Rafael Almeida ; Alejandro Rodriguez Gonzalez ; Linlin Shen ; Bridget Kane ; Agma Traina ; Paolo Soda ; Jose Luis Oliveira. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 62-67 (Proceedings - IEEE Symposium on Computer-Based Medical Systems).

@inproceedings{15b548a1d8d446b2b77d92a0b8c557c3,

title = "Identification of signs of depression relapse using audio-visual cues: A preliminary study",

abstract = "Depression is a serious mental disorder that affects many individuals across the globe. Depression (unipolar or bipolar) is characterized by a high rate of relapse or recurrence where a person might experience depressive episodes after non-depressive ones. The symptom patterns for recurrent depressive episodes have not been properly analyzed. Thus, there is a pressing need for systems which can monitor the mental health of individuals at risk to detect initial signs of relapse and recurrence. This points towards an automated system which identifies such signs and facilitates in timely treatment. In this paper, we introduce for the first time a deep learning based prospective monitoring system for the identification of relapse signs using audio-visual cues. The proposed model approximates relapse as the similarity between non-depression and depression samples. Experiments were performed on the DAIC-WOZ dataset and a highest accuracy of 73.21% was obtained using a Siamese network-based approach with one-shot learning regime. ",

keywords = "Depression Relapse, One-shot learning, Recurrence, Siamese network",

author = "Muhammad Muzammel and Alice Othmani and Himadri Mukherjee and Hanan Salam",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 34th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2021 ; Conference date: 07-06-2021 Through 09-06-2021",

year = "2021",

month = jun,

doi = "10.1109/CBMS52027.2021.00018",

language = "English (US)",

series = "Proceedings - IEEE Symposium on Computer-Based Medical Systems",

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

pages = "62--67",

editor = "Almeida, {Joao Rafael} and Gonzalez, {Alejandro Rodriguez} and Linlin Shen and Bridget Kane and Agma Traina and Paolo Soda and Oliveira, {Jose Luis}",

booktitle = "Proceedings - 2021 IEEE 34th International Symposium on Computer-Based Medical Systems, CBMS 2021",

}

TY - GEN

T1 - Identification of signs of depression relapse using audio-visual cues

T2 - 34th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2021

AU - Muzammel, Muhammad

AU - Othmani, Alice

AU - Mukherjee, Himadri

AU - Salam, Hanan

PY - 2021/6

Y1 - 2021/6

N2 - Depression is a serious mental disorder that affects many individuals across the globe. Depression (unipolar or bipolar) is characterized by a high rate of relapse or recurrence where a person might experience depressive episodes after non-depressive ones. The symptom patterns for recurrent depressive episodes have not been properly analyzed. Thus, there is a pressing need for systems which can monitor the mental health of individuals at risk to detect initial signs of relapse and recurrence. This points towards an automated system which identifies such signs and facilitates in timely treatment. In this paper, we introduce for the first time a deep learning based prospective monitoring system for the identification of relapse signs using audio-visual cues. The proposed model approximates relapse as the similarity between non-depression and depression samples. Experiments were performed on the DAIC-WOZ dataset and a highest accuracy of 73.21% was obtained using a Siamese network-based approach with one-shot learning regime.

AB - Depression is a serious mental disorder that affects many individuals across the globe. Depression (unipolar or bipolar) is characterized by a high rate of relapse or recurrence where a person might experience depressive episodes after non-depressive ones. The symptom patterns for recurrent depressive episodes have not been properly analyzed. Thus, there is a pressing need for systems which can monitor the mental health of individuals at risk to detect initial signs of relapse and recurrence. This points towards an automated system which identifies such signs and facilitates in timely treatment. In this paper, we introduce for the first time a deep learning based prospective monitoring system for the identification of relapse signs using audio-visual cues. The proposed model approximates relapse as the similarity between non-depression and depression samples. Experiments were performed on the DAIC-WOZ dataset and a highest accuracy of 73.21% was obtained using a Siamese network-based approach with one-shot learning regime.

KW - Depression Relapse

KW - One-shot learning

KW - Recurrence

KW - Siamese network

UR - http://www.scopus.com/inward/record.url?scp=85110818123&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85110818123&partnerID=8YFLogxK

U2 - 10.1109/CBMS52027.2021.00018

DO - 10.1109/CBMS52027.2021.00018

M3 - Conference contribution

AN - SCOPUS:85110818123

T3 - Proceedings - IEEE Symposium on Computer-Based Medical Systems

SP - 62

EP - 67

BT - Proceedings - 2021 IEEE 34th International Symposium on Computer-Based Medical Systems, CBMS 2021

A2 - Almeida, Joao Rafael

A2 - Gonzalez, Alejandro Rodriguez

A2 - Shen, Linlin

A2 - Kane, Bridget

A2 - Traina, Agma

A2 - Soda, Paolo

A2 - Oliveira, Jose Luis

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 7 June 2021 through 9 June 2021

ER -

Identification of signs of depression relapse using audio-visual cues: A preliminary study

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this