Use of Machine-Learning Algorithms Based on Text, Audio and Video Data in the Prediction of Anxiety and Post-Traumatic Stress in General and Clinical Populations: A Systematic Review

Publikation: Beiträge in ZeitschriftenÜbersichtsarbeitenForschung

Standard

Use of Machine-Learning Algorithms Based on Text, Audio and Video Data in the Prediction of Anxiety and Post-Traumatic Stress in General and Clinical Populations: A Systematic Review. / Ciharova, Marketa; Amarti, Khadicha; van Breda, Ward et al.
in: Biological Psychiatry, Jahrgang 96, Nr. 7, 01.10.2024, S. 519-531.

Publikation: Beiträge in ZeitschriftenÜbersichtsarbeitenForschung

Harvard

Ciharova, M, Amarti, K, van Breda, W, Peng, X, Lorente-Català, R, Funk, B, Hoogendoorn, M, Koutsouleris, N, Fusar-Poli, P, Karyotaki, E, Cuijpers, P & Riper, H 2024, 'Use of Machine-Learning Algorithms Based on Text, Audio and Video Data in the Prediction of Anxiety and Post-Traumatic Stress in General and Clinical Populations: A Systematic Review', Biological Psychiatry, Jg. 96, Nr. 7, S. 519-531. https://doi.org/10.1016/j.biopsych.2024.06.002

APA

Ciharova, M., Amarti, K., van Breda, W., Peng, X., Lorente-Català, R., Funk, B., Hoogendoorn, M., Koutsouleris, N., Fusar-Poli, P., Karyotaki, E., Cuijpers, P., & Riper, H. (2024). Use of Machine-Learning Algorithms Based on Text, Audio and Video Data in the Prediction of Anxiety and Post-Traumatic Stress in General and Clinical Populations: A Systematic Review. Biological Psychiatry, 96(7), 519-531. https://doi.org/10.1016/j.biopsych.2024.06.002

Vancouver

Ciharova M, Amarti K, van Breda W, Peng X, Lorente-Català R, Funk B et al. Use of Machine-Learning Algorithms Based on Text, Audio and Video Data in the Prediction of Anxiety and Post-Traumatic Stress in General and Clinical Populations: A Systematic Review. Biological Psychiatry. 2024 Okt 1;96(7):519-531. Epub 2024 Jun 10. doi: 10.1016/j.biopsych.2024.06.002

Bibtex

@article{45d19a6bfd604d938d58860c1d6bb8ae,
title = "Use of Machine-Learning Algorithms Based on Text, Audio and Video Data in the Prediction of Anxiety and Post-Traumatic Stress in General and Clinical Populations: A Systematic Review",
abstract = "Research in machine learning (ML) algorithms using natural behavior (i.e., text, audio, and video data) suggests that these techniques could contribute to personalization in psychology and psychiatry. However, a systematic review of the current state of the art is missing. Moreover, individual studies often target ML experts who may overlook potential clinical implications of their findings. In a narrative accessible to mental health professionals, we present a systematic review conducted in 5 psychology and 2 computer science databases. We included 128 studies that assessed the predictive power of ML algorithms using text, audio, and/or video data in the prediction of anxiety and posttraumatic stress disorder. Most studies (n = 87) were aimed at predicting anxiety, while the remainder (n = 41) focused on posttraumatic stress disorder. They were mostly published since 2019 in computer science journals and tested algorithms using text (n = 72) as opposed to audio or video. Studies focused mainly on general populations (n = 92) and less on laboratory experiments (n = 23) or clinical populations (n = 13). Methodological quality varied, as did reported metrics of the predictive power, hampering comparison across studies. Two-thirds of studies, which focused on both disorders, reported acceptable to very good predictive power (including high-quality studies only). The results of 33 studies were uninterpretable, mainly due to missing information. Research into ML algorithms using natural behavior is in its infancy but shows potential to contribute to diagnostics of mental disorders, such as anxiety and posttraumatic stress disorder, in the future if standardization of methods, reporting of results, and research in clinical populations are improved.",
keywords = "Informatics, Anxiety, Audio, Machine Learning, Posttraumatic stress, Text, Video",
author = "Marketa Ciharova and Khadicha Amarti and {van Breda}, Ward and Xianhua Peng and Rosa Lorente-Catal{\`a} and Burkhardt Funk and Mark Hoogendoorn and Nikolaos Koutsouleris and Paolo Fusar-Poli and Eirini Karyotaki and Pim Cuijpers and Heleen Riper",
note = "Publisher Copyright: {\textcopyright} 2024 Society of Biological Psychiatry",
year = "2024",
month = oct,
day = "1",
doi = "10.1016/j.biopsych.2024.06.002",
language = "English",
volume = "96",
pages = "519--531",
journal = "Biological Psychiatry",
issn = "0006-3223",
publisher = "Elsevier USA",
number = "7",

}

RIS

TY - JOUR

T1 - Use of Machine-Learning Algorithms Based on Text, Audio and Video Data in the Prediction of Anxiety and Post-Traumatic Stress in General and Clinical Populations

T2 - A Systematic Review

AU - Ciharova, Marketa

AU - Amarti, Khadicha

AU - van Breda, Ward

AU - Peng, Xianhua

AU - Lorente-Català, Rosa

AU - Funk, Burkhardt

AU - Hoogendoorn, Mark

AU - Koutsouleris, Nikolaos

AU - Fusar-Poli, Paolo

AU - Karyotaki, Eirini

AU - Cuijpers, Pim

AU - Riper, Heleen

N1 - Publisher Copyright: © 2024 Society of Biological Psychiatry

PY - 2024/10/1

Y1 - 2024/10/1

N2 - Research in machine learning (ML) algorithms using natural behavior (i.e., text, audio, and video data) suggests that these techniques could contribute to personalization in psychology and psychiatry. However, a systematic review of the current state of the art is missing. Moreover, individual studies often target ML experts who may overlook potential clinical implications of their findings. In a narrative accessible to mental health professionals, we present a systematic review conducted in 5 psychology and 2 computer science databases. We included 128 studies that assessed the predictive power of ML algorithms using text, audio, and/or video data in the prediction of anxiety and posttraumatic stress disorder. Most studies (n = 87) were aimed at predicting anxiety, while the remainder (n = 41) focused on posttraumatic stress disorder. They were mostly published since 2019 in computer science journals and tested algorithms using text (n = 72) as opposed to audio or video. Studies focused mainly on general populations (n = 92) and less on laboratory experiments (n = 23) or clinical populations (n = 13). Methodological quality varied, as did reported metrics of the predictive power, hampering comparison across studies. Two-thirds of studies, which focused on both disorders, reported acceptable to very good predictive power (including high-quality studies only). The results of 33 studies were uninterpretable, mainly due to missing information. Research into ML algorithms using natural behavior is in its infancy but shows potential to contribute to diagnostics of mental disorders, such as anxiety and posttraumatic stress disorder, in the future if standardization of methods, reporting of results, and research in clinical populations are improved.

AB - Research in machine learning (ML) algorithms using natural behavior (i.e., text, audio, and video data) suggests that these techniques could contribute to personalization in psychology and psychiatry. However, a systematic review of the current state of the art is missing. Moreover, individual studies often target ML experts who may overlook potential clinical implications of their findings. In a narrative accessible to mental health professionals, we present a systematic review conducted in 5 psychology and 2 computer science databases. We included 128 studies that assessed the predictive power of ML algorithms using text, audio, and/or video data in the prediction of anxiety and posttraumatic stress disorder. Most studies (n = 87) were aimed at predicting anxiety, while the remainder (n = 41) focused on posttraumatic stress disorder. They were mostly published since 2019 in computer science journals and tested algorithms using text (n = 72) as opposed to audio or video. Studies focused mainly on general populations (n = 92) and less on laboratory experiments (n = 23) or clinical populations (n = 13). Methodological quality varied, as did reported metrics of the predictive power, hampering comparison across studies. Two-thirds of studies, which focused on both disorders, reported acceptable to very good predictive power (including high-quality studies only). The results of 33 studies were uninterpretable, mainly due to missing information. Research into ML algorithms using natural behavior is in its infancy but shows potential to contribute to diagnostics of mental disorders, such as anxiety and posttraumatic stress disorder, in the future if standardization of methods, reporting of results, and research in clinical populations are improved.

KW - Informatics

KW - Anxiety

KW - Audio

KW - Machine Learning

KW - Posttraumatic stress

KW - Text

KW - Video

UR - http://www.scopus.com/inward/record.url?scp=85199080534&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/9a11e3ab-e4a0-3289-8084-a5065ef7f98c/

U2 - 10.1016/j.biopsych.2024.06.002

DO - 10.1016/j.biopsych.2024.06.002

M3 - Scientific review articles

C2 - 38866173

VL - 96

SP - 519

EP - 531

JO - Biological Psychiatry

JF - Biological Psychiatry

SN - 0006-3223

IS - 7

ER -

DOI