A Machine Learning approach to optimize the assessment of depressive symptomatology

Maekawa Eduardo; Glavin Darragh; Grua Eoin Martino; Nakamura Carina Akemi; Scazufca Marcia; Araya Ricardo; J. Peters Tim; Van De Ven Pepijn

doi:10.1016/j.procs.2022.09.090

A Machine Learning approach to optimize the assessment of depressive symptomatology

Maekawa Eduardo
, Glavin Darragh
, Grua Eoin Martino
, Nakamura Carina Akemi
, Scazufca Marcia
, Araya Ricardo
, J. Peters Tim
, Van De Ven Pepijn

University of Limerick
Universidade de São Paulo
Centre for Global Mental Health
University of Bristol

Research output: Contribution to journal › Conference article › peer-review

Abstract

In this work, we developed a machine learning model to predict depressive symptomatology (DS). The model achieved an AUC of 0.71 and a sensitivity of 74.8%. When developing the model, we applied a Bayesian network approach to select its predictors. This probabilistic approach facilitates the understanding of the relationships between predictors and DS. In consequence, we were able to identify that having balance problems and experiencing shortness of breath are directly related to DS.

Original language	English
Pages (from-to)	111-120
Number of pages	10
Journal	Procedia Computer Science
Volume	206
DOIs	https://doi.org/10.1016/j.procs.2022.09.090
Publication status	Published - 2022
Event	11th Scientific Meeting of the International Society for Research on Internet Interventions, ISRII 2022 - Pittsburgh, United States Duration: 18 Sep 2022 → 22 Sep 2022

Keywords

Bayesian networks
Depressive symptomatology
Machine learning

Access to Document

10.1016/j.procs.2022.09.090

Cite this

@article{3be056c32bc44f34a1c10d082a797516,

title = "A Machine Learning approach to optimize the assessment of depressive symptomatology",

abstract = "In this work, we developed a machine learning model to predict depressive symptomatology (DS). The model achieved an AUC of 0.71 and a sensitivity of 74.8\%. When developing the model, we applied a Bayesian network approach to select its predictors. This probabilistic approach facilitates the understanding of the relationships between predictors and DS. In consequence, we were able to identify that having balance problems and experiencing shortness of breath are directly related to DS.",

keywords = "Bayesian networks, Depressive symptomatology, Machine learning",

author = "Maekawa Eduardo and Glavin Darragh and \{Eoin Martino\}, Grua and \{Carina Akemi\}, Nakamura and Scazufca Marcia and Araya Ricardo and \{Peters Tim\}, J. and Pepijn, \{Van De Ven\}",

note = "Publisher Copyright: {\textcopyright} 2022 The Author(s).; 11th Scientific Meeting of the International Society for Research on Internet Interventions, ISRII 2022 ; Conference date: 18-09-2022 Through 22-09-2022",

year = "2022",

doi = "10.1016/j.procs.2022.09.090",

language = "English",

volume = "206",

pages = "111--120",

journal = "Procedia Computer Science",

issn = "1877-0509",

}

TY - JOUR

T1 - A Machine Learning approach to optimize the assessment of depressive symptomatology

AU - Eduardo, Maekawa

AU - Darragh, Glavin

AU - Eoin Martino, Grua

AU - Carina Akemi, Nakamura

AU - Marcia, Scazufca

AU - Ricardo, Araya

AU - Peters Tim, J.

AU - Pepijn, Van De Ven

PY - 2022

Y1 - 2022

N2 - In this work, we developed a machine learning model to predict depressive symptomatology (DS). The model achieved an AUC of 0.71 and a sensitivity of 74.8%. When developing the model, we applied a Bayesian network approach to select its predictors. This probabilistic approach facilitates the understanding of the relationships between predictors and DS. In consequence, we were able to identify that having balance problems and experiencing shortness of breath are directly related to DS.

AB - In this work, we developed a machine learning model to predict depressive symptomatology (DS). The model achieved an AUC of 0.71 and a sensitivity of 74.8%. When developing the model, we applied a Bayesian network approach to select its predictors. This probabilistic approach facilitates the understanding of the relationships between predictors and DS. In consequence, we were able to identify that having balance problems and experiencing shortness of breath are directly related to DS.

KW - Bayesian networks

KW - Depressive symptomatology

KW - Machine learning

UR - https://www.scopus.com/pages/publications/85143629626

U2 - 10.1016/j.procs.2022.09.090

DO - 10.1016/j.procs.2022.09.090

M3 - Conference article

AN - SCOPUS:85143629626

SN - 1877-0509

VL - 206

SP - 111

EP - 120

JO - Procedia Computer Science

JF - Procedia Computer Science

T2 - 11th Scientific Meeting of the International Society for Research on Internet Interventions, ISRII 2022

Y2 - 18 September 2022 through 22 September 2022

ER -

A Machine Learning approach to optimize the assessment of depressive symptomatology

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this