APD: An Autoencoder-based Prediction Model for Depression Diagnosis

Hyeseong Park; Myung Won Raymond Jung; Uran Oh

doi:10.1109/IRI51335.2021.00058

APD: An Autoencoder-based Prediction Model for Depression Diagnosis

Hyeseong Park, Myung Won Raymond Jung, Uran Oh

Department of Computer Science & Engineering

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

1 Scopus citations

Abstract

Depression is one of the most common mental health problems, which can lead to significant mental disorders and suicidal behavior. To diagnose depression levels, patients with depressive disorders are required to complete self-assessment questionnaires. However, many depressed patients are misdiagnosed in clinical practice due to patients' missing data. In this paper, we introduce, APD, a novel data-driven approach based on autoencoder to predict the missing responses accurately. Inspired by existing autoencoder-based recommender systems, our autoencoder is based on collaborative filtering, which estimates unobserved data by cooperation with other patients' responses. Experimental results show that the proposed autoencoder-based prediction system outperforms the averaging and the linear models. We demonstrate that this model can be used to predict patients' depression status with a low error of 2.85%.

Original language	English
Title of host publication	Proceedings - 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science, IRI 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	376-379
Number of pages	4
ISBN (Electronic)	9781665438759
DOIs	https://doi.org/10.1109/IRI51335.2021.00058
State	Published - 2021
Event	22nd IEEE International Conference on Information Reuse and Integration for Data Science, IRI 2021 - Virtual, Online, United States Duration: 10 Aug 2021 → 12 Aug 2021

Publication series

Name	Proceedings - 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science, IRI 2021

Conference

Conference	22nd IEEE International Conference on Information Reuse and Integration for Data Science, IRI 2021
Country/Territory	United States
City	Virtual, Online
Period	10/08/21 → 12/08/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Keywords

Autoencoder
Depression
Psychological Assessment
Surveys
patients' response

Access to Document

10.1109/IRI51335.2021.00058

Cite this

Park, H., Raymond Jung, M. W., & Oh, U. (2021). APD: An Autoencoder-based Prediction Model for Depression Diagnosis. In Proceedings - 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science, IRI 2021 (pp. 376-379). (Proceedings - 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science, IRI 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IRI51335.2021.00058

Park, Hyeseong ; Raymond Jung, Myung Won ; Oh, Uran. / APD : An Autoencoder-based Prediction Model for Depression Diagnosis. Proceedings - 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science, IRI 2021. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 376-379 (Proceedings - 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science, IRI 2021).

@inproceedings{f9921b84c3e14d308f62d03e7f9d3833,

title = "APD: An Autoencoder-based Prediction Model for Depression Diagnosis",

abstract = "Depression is one of the most common mental health problems, which can lead to significant mental disorders and suicidal behavior. To diagnose depression levels, patients with depressive disorders are required to complete self-assessment questionnaires. However, many depressed patients are misdiagnosed in clinical practice due to patients' missing data. In this paper, we introduce, APD, a novel data-driven approach based on autoencoder to predict the missing responses accurately. Inspired by existing autoencoder-based recommender systems, our autoencoder is based on collaborative filtering, which estimates unobserved data by cooperation with other patients' responses. Experimental results show that the proposed autoencoder-based prediction system outperforms the averaging and the linear models. We demonstrate that this model can be used to predict patients' depression status with a low error of 2.85%.",

keywords = "Autoencoder, Depression, Psychological Assessment, Surveys, patients' response",

author = "Hyeseong Park and {Raymond Jung}, {Myung Won} and Uran Oh",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 22nd IEEE International Conference on Information Reuse and Integration for Data Science, IRI 2021 ; Conference date: 10-08-2021 Through 12-08-2021",

year = "2021",

doi = "10.1109/IRI51335.2021.00058",

language = "English",

series = "Proceedings - 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science, IRI 2021",

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

pages = "376--379",

booktitle = "Proceedings - 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science, IRI 2021",

}

Park, H, Raymond Jung, MW & Oh, U 2021, APD: An Autoencoder-based Prediction Model for Depression Diagnosis. in Proceedings - 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science, IRI 2021. Proceedings - 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science, IRI 2021, Institute of Electrical and Electronics Engineers Inc., pp. 376-379, 22nd IEEE International Conference on Information Reuse and Integration for Data Science, IRI 2021, Virtual, Online, United States, 10/08/21. https://doi.org/10.1109/IRI51335.2021.00058

APD: An Autoencoder-based Prediction Model for Depression Diagnosis. / Park, Hyeseong; Raymond Jung, Myung Won; Oh, Uran.
Proceedings - 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science, IRI 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 376-379 (Proceedings - 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science, IRI 2021).

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

TY - GEN

T1 - APD

T2 - 22nd IEEE International Conference on Information Reuse and Integration for Data Science, IRI 2021

AU - Park, Hyeseong

AU - Raymond Jung, Myung Won

AU - Oh, Uran

PY - 2021

Y1 - 2021

N2 - Depression is one of the most common mental health problems, which can lead to significant mental disorders and suicidal behavior. To diagnose depression levels, patients with depressive disorders are required to complete self-assessment questionnaires. However, many depressed patients are misdiagnosed in clinical practice due to patients' missing data. In this paper, we introduce, APD, a novel data-driven approach based on autoencoder to predict the missing responses accurately. Inspired by existing autoencoder-based recommender systems, our autoencoder is based on collaborative filtering, which estimates unobserved data by cooperation with other patients' responses. Experimental results show that the proposed autoencoder-based prediction system outperforms the averaging and the linear models. We demonstrate that this model can be used to predict patients' depression status with a low error of 2.85%.

AB - Depression is one of the most common mental health problems, which can lead to significant mental disorders and suicidal behavior. To diagnose depression levels, patients with depressive disorders are required to complete self-assessment questionnaires. However, many depressed patients are misdiagnosed in clinical practice due to patients' missing data. In this paper, we introduce, APD, a novel data-driven approach based on autoencoder to predict the missing responses accurately. Inspired by existing autoencoder-based recommender systems, our autoencoder is based on collaborative filtering, which estimates unobserved data by cooperation with other patients' responses. Experimental results show that the proposed autoencoder-based prediction system outperforms the averaging and the linear models. We demonstrate that this model can be used to predict patients' depression status with a low error of 2.85%.

KW - Autoencoder

KW - Depression

KW - Psychological Assessment

KW - Surveys

KW - patients' response

UR - http://www.scopus.com/inward/record.url?scp=85123454477&partnerID=8YFLogxK

U2 - 10.1109/IRI51335.2021.00058

DO - 10.1109/IRI51335.2021.00058

M3 - Conference contribution

AN - SCOPUS:85123454477

T3 - Proceedings - 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science, IRI 2021

SP - 376

EP - 379

BT - Proceedings - 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science, IRI 2021

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 10 August 2021 through 12 August 2021

ER -

Park H, Raymond Jung MW, Oh U. APD: An Autoencoder-based Prediction Model for Depression Diagnosis. In Proceedings - 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science, IRI 2021. Institute of Electrical and Electronics Engineers Inc. 2021. p. 376-379. (Proceedings - 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science, IRI 2021). doi: 10.1109/IRI51335.2021.00058

APD: An Autoencoder-based Prediction Model for Depression Diagnosis

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this