Evaluation of a temporal causal model for predicting the mood of clients in an online therapy

Research output: Journal contributionsJournal articlesResearchpeer-review

Standard

Evaluation of a temporal causal model for predicting the mood of clients in an online therapy. / Becker, Dennis; Bremer, Vincent; Funk, Burkhardt et al.

In: BMJ mental health, Vol. 23, No. 1, 11.02.2020, p. 27-33.

Research output: Journal contributionsJournal articlesResearchpeer-review

Harvard

APA

Vancouver

Becker D, Bremer V, Funk B, Hoogendoorn M, Rocha A, Riper H. Evaluation of a temporal causal model for predicting the mood of clients in an online therapy. BMJ mental health. 2020 Feb 11;23(1):27-33. doi: 10.1136/ebmental-2019-300135

Bibtex

@article{c3789baf93444c6fa7689100c52b7966,
title = "Evaluation of a temporal causal model for predicting the mood of clients in an online therapy",
abstract = "Background Self-reported client assessments during online treatments enable the development of statistical models for the prediction of client improvement and symptom development. Evaluation of these models is mandatory to ensure their validity. Methods For this purpose, we suggest besides a model evaluation based on study data the use of a simulation analysis. The simulation analysis provides insight into the model performance and enables to analyse reasons for a low predictive accuracy. In this study, we evaluate a temporal causal model (TCM) and show that it does not provide reliable predictions of clients' future mood levels. Results Based on the simulation analysis we investigate the potential reasons for the low predictive performance, for example, noisy measurements and sampling frequency. We conclude that the analysed TCM in its current form is not sufficient to describe the underlying psychological processes. Conclusions The results demonstrate the importance of model evaluation and the benefit of a simulation analysis. The current manuscript provides practical guidance for conducting model evaluation including simulation analysis.",
keywords = "mood prediction, online treatment, predictive modelling, temporal causal model, Business informatics",
author = "Dennis Becker and Vincent Bremer and Burkhardt Funk and Mark Hoogendoorn and Artur Rocha and Heleen Riper",
note = "Publisher Copyright: {\textcopyright} Author(s) (or their employer(s)) 2020. No commercial re-use. See rights and permissions. Published by BMJ.",
year = "2020",
month = feb,
day = "11",
doi = "10.1136/ebmental-2019-300135",
language = "English",
volume = "23",
pages = "27--33",
journal = "BMJ mental health",
issn = "1362-0347",
publisher = "BMJ Publishing Group",
number = "1",

}

RIS

TY - JOUR

T1 - Evaluation of a temporal causal model for predicting the mood of clients in an online therapy

AU - Becker, Dennis

AU - Bremer, Vincent

AU - Funk, Burkhardt

AU - Hoogendoorn, Mark

AU - Rocha, Artur

AU - Riper, Heleen

N1 - Publisher Copyright: © Author(s) (or their employer(s)) 2020. No commercial re-use. See rights and permissions. Published by BMJ.

PY - 2020/2/11

Y1 - 2020/2/11

N2 - Background Self-reported client assessments during online treatments enable the development of statistical models for the prediction of client improvement and symptom development. Evaluation of these models is mandatory to ensure their validity. Methods For this purpose, we suggest besides a model evaluation based on study data the use of a simulation analysis. The simulation analysis provides insight into the model performance and enables to analyse reasons for a low predictive accuracy. In this study, we evaluate a temporal causal model (TCM) and show that it does not provide reliable predictions of clients' future mood levels. Results Based on the simulation analysis we investigate the potential reasons for the low predictive performance, for example, noisy measurements and sampling frequency. We conclude that the analysed TCM in its current form is not sufficient to describe the underlying psychological processes. Conclusions The results demonstrate the importance of model evaluation and the benefit of a simulation analysis. The current manuscript provides practical guidance for conducting model evaluation including simulation analysis.

AB - Background Self-reported client assessments during online treatments enable the development of statistical models for the prediction of client improvement and symptom development. Evaluation of these models is mandatory to ensure their validity. Methods For this purpose, we suggest besides a model evaluation based on study data the use of a simulation analysis. The simulation analysis provides insight into the model performance and enables to analyse reasons for a low predictive accuracy. In this study, we evaluate a temporal causal model (TCM) and show that it does not provide reliable predictions of clients' future mood levels. Results Based on the simulation analysis we investigate the potential reasons for the low predictive performance, for example, noisy measurements and sampling frequency. We conclude that the analysed TCM in its current form is not sufficient to describe the underlying psychological processes. Conclusions The results demonstrate the importance of model evaluation and the benefit of a simulation analysis. The current manuscript provides practical guidance for conducting model evaluation including simulation analysis.

KW - mood prediction

KW - online treatment

KW - predictive modelling

KW - temporal causal model

KW - Business informatics

UR - http://www.scopus.com/inward/record.url?scp=85079336693&partnerID=8YFLogxK

U2 - 10.1136/ebmental-2019-300135

DO - 10.1136/ebmental-2019-300135

M3 - Journal articles

C2 - 32046990

VL - 23

SP - 27

EP - 33

JO - BMJ mental health

JF - BMJ mental health

SN - 1362-0347

IS - 1

ER -