Predicting Depression History from a Short Reward/Aversion Task with Behavioral Economic Features

L. Stefanopoulos; S. Lavlani; B. W. Kim; N. Vike; S. Bari; E. Azcona; S. Woodward; Martin Paul Block; N. Maglaveras; A. K. Katsaggelos; Hans C Breiter

doi:10.1007/978-3-031-59216-4_5

Predicting Depression History from a Short Reward/Aversion Task with Behavioral Economic Features

L. Stefanopoulos^*, S. Lavlani, B. W. Kim, N. Vike, S. Bari, E. Azcona, S. Woodward, Martin Paul Block, N. Maglaveras, A. K. Katsaggelos, Hans C Breiter

^*Corresponding author for this work

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

1 Scopus citations

Abstract

This paper presents a novel example of depression prediction, merging cognitive science with data-driven machine learning. Behavioral economic features were engineered from a short picture rating task. Relative Preference Theory was applied to rating data for quantifying the degree to which participants liked, disliked, or were neutral to several types of pictures; thus, behavioral economic variables including loss aversion, risk aversion, and 13 others that are amenable to psychological interpretation were mined. These variables were features of a logistic regression predictive model that targeted depression in a population-based sample (N = 281) with high test accuracy and no overfitting. Per our review of the literature, we cannot identify other papers that explicitly use behavioral economic features to predict depression with machine learning.

Original language	English (US)
Title of host publication	International Conference on Biomedical and Health Informatics 2022 - Proceedings of ICBHI 2022
Editors	Esteban Pino, Ratko Magjarevic, Paulo de Carvalho
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	44-50
Number of pages	7
ISBN (Print)	9783031592157
DOIs	https://doi.org/10.1007/978-3-031-59216-4_5
State	Published - 2024
Event	5th International Conference on Biomedical and Health Informatics, ICBHI 2022 - Concepcion, Chile Duration: Nov 24 2022 → Nov 26 2022

Publication series

Name	IFMBE Proceedings
Volume	108
ISSN (Print)	1680-0737
ISSN (Electronic)	1433-9277

Conference

Conference	5th International Conference on Biomedical and Health Informatics, ICBHI 2022
Country/Territory	Chile
City	Concepcion
Period	11/24/22 → 11/26/22

Funding

This work has been supported by the Office of Naval Research, Grant N000142112216.

Keywords

Behavioral Economic Features
Depression prediction
Machine Learning

ASJC Scopus subject areas

Bioengineering
Biomedical Engineering

Access to Document

10.1007/978-3-031-59216-4_5

Cite this

Stefanopoulos, L., Lavlani, S., Kim, B. W., Vike, N., Bari, S., Azcona, E., Woodward, S., Block, M. P., Maglaveras, N., Katsaggelos, A. K., & Breiter, H. C. (2024). Predicting Depression History from a Short Reward/Aversion Task with Behavioral Economic Features. In E. Pino, R. Magjarevic, & P. de Carvalho (Eds.), International Conference on Biomedical and Health Informatics 2022 - Proceedings of ICBHI 2022 (pp. 44-50). (IFMBE Proceedings; Vol. 108). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-59216-4_5

Stefanopoulos, L. ; Lavlani, S. ; Kim, B. W. et al. / Predicting Depression History from a Short Reward/Aversion Task with Behavioral Economic Features. International Conference on Biomedical and Health Informatics 2022 - Proceedings of ICBHI 2022. editor / Esteban Pino ; Ratko Magjarevic ; Paulo de Carvalho. Springer Science and Business Media Deutschland GmbH, 2024. pp. 44-50 (IFMBE Proceedings).

@inproceedings{6bb1684f4ae24167919fac821f7099c7,

title = "Predicting Depression History from a Short Reward/Aversion Task with Behavioral Economic Features",

abstract = "This paper presents a novel example of depression prediction, merging cognitive science with data-driven machine learning. Behavioral economic features were engineered from a short picture rating task. Relative Preference Theory was applied to rating data for quantifying the degree to which participants liked, disliked, or were neutral to several types of pictures; thus, behavioral economic variables including loss aversion, risk aversion, and 13 others that are amenable to psychological interpretation were mined. These variables were features of a logistic regression predictive model that targeted depression in a population-based sample (N = 281) with high test accuracy and no overfitting. Per our review of the literature, we cannot identify other papers that explicitly use behavioral economic features to predict depression with machine learning.",

keywords = "Behavioral Economic Features, Depression prediction, Machine Learning",

author = "L. Stefanopoulos and S. Lavlani and Kim, \{B. W.\} and N. Vike and S. Bari and E. Azcona and S. Woodward and Block, \{Martin Paul\} and N. Maglaveras and Katsaggelos, \{A. K.\} and Breiter, \{Hans C\}",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.; 5th International Conference on Biomedical and Health Informatics, ICBHI 2022 ; Conference date: 24-11-2022 Through 26-11-2022",

year = "2024",

doi = "10.1007/978-3-031-59216-4\_5",

language = "English (US)",

isbn = "9783031592157",

series = "IFMBE Proceedings",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "44--50",

editor = "Esteban Pino and Ratko Magjarevic and \{de Carvalho\}, Paulo",

booktitle = "International Conference on Biomedical and Health Informatics 2022 - Proceedings of ICBHI 2022",

address = "Germany",

}

Stefanopoulos, L, Lavlani, S, Kim, BW, Vike, N, Bari, S, Azcona, E, Woodward, S, Block, MP, Maglaveras, N, Katsaggelos, AK & Breiter, HC 2024, Predicting Depression History from a Short Reward/Aversion Task with Behavioral Economic Features. in E Pino, R Magjarevic & P de Carvalho (eds), International Conference on Biomedical and Health Informatics 2022 - Proceedings of ICBHI 2022. IFMBE Proceedings, vol. 108, Springer Science and Business Media Deutschland GmbH, pp. 44-50, 5th International Conference on Biomedical and Health Informatics, ICBHI 2022, Concepcion, Chile, 11/24/22. https://doi.org/10.1007/978-3-031-59216-4_5

Predicting Depression History from a Short Reward/Aversion Task with Behavioral Economic Features. / Stefanopoulos, L.; Lavlani, S.; Kim, B. W. et al.
International Conference on Biomedical and Health Informatics 2022 - Proceedings of ICBHI 2022. ed. / Esteban Pino; Ratko Magjarevic; Paulo de Carvalho. Springer Science and Business Media Deutschland GmbH, 2024. p. 44-50 (IFMBE Proceedings; Vol. 108).

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

TY - GEN

T1 - Predicting Depression History from a Short Reward/Aversion Task with Behavioral Economic Features

AU - Stefanopoulos, L.

AU - Lavlani, S.

AU - Kim, B. W.

AU - Vike, N.

AU - Bari, S.

AU - Azcona, E.

AU - Woodward, S.

AU - Block, Martin Paul

AU - Maglaveras, N.

AU - Katsaggelos, A. K.

AU - Breiter, Hans C

PY - 2024

Y1 - 2024

N2 - This paper presents a novel example of depression prediction, merging cognitive science with data-driven machine learning. Behavioral economic features were engineered from a short picture rating task. Relative Preference Theory was applied to rating data for quantifying the degree to which participants liked, disliked, or were neutral to several types of pictures; thus, behavioral economic variables including loss aversion, risk aversion, and 13 others that are amenable to psychological interpretation were mined. These variables were features of a logistic regression predictive model that targeted depression in a population-based sample (N = 281) with high test accuracy and no overfitting. Per our review of the literature, we cannot identify other papers that explicitly use behavioral economic features to predict depression with machine learning.

AB - This paper presents a novel example of depression prediction, merging cognitive science with data-driven machine learning. Behavioral economic features were engineered from a short picture rating task. Relative Preference Theory was applied to rating data for quantifying the degree to which participants liked, disliked, or were neutral to several types of pictures; thus, behavioral economic variables including loss aversion, risk aversion, and 13 others that are amenable to psychological interpretation were mined. These variables were features of a logistic regression predictive model that targeted depression in a population-based sample (N = 281) with high test accuracy and no overfitting. Per our review of the literature, we cannot identify other papers that explicitly use behavioral economic features to predict depression with machine learning.

KW - Behavioral Economic Features

KW - Depression prediction

KW - Machine Learning

UR - http://www.scopus.com/inward/record.url?scp=85193590962&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85193590962&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-59216-4_5

DO - 10.1007/978-3-031-59216-4_5

M3 - Conference contribution

AN - SCOPUS:85193590962

SN - 9783031592157

T3 - IFMBE Proceedings

SP - 44

EP - 50

BT - International Conference on Biomedical and Health Informatics 2022 - Proceedings of ICBHI 2022

A2 - Pino, Esteban

A2 - Magjarevic, Ratko

A2 - de Carvalho, Paulo

PB - Springer Science and Business Media Deutschland GmbH

T2 - 5th International Conference on Biomedical and Health Informatics, ICBHI 2022

Y2 - 24 November 2022 through 26 November 2022

ER -

Stefanopoulos L, Lavlani S, Kim BW, Vike N, Bari S, Azcona E et al. Predicting Depression History from a Short Reward/Aversion Task with Behavioral Economic Features. In Pino E, Magjarevic R, de Carvalho P, editors, International Conference on Biomedical and Health Informatics 2022 - Proceedings of ICBHI 2022. Springer Science and Business Media Deutschland GmbH. 2024. p. 44-50. (IFMBE Proceedings). doi: 10.1007/978-3-031-59216-4_5

Predicting Depression History from a Short Reward/Aversion Task with Behavioral Economic Features

Abstract

Publication series

Conference

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this