Development and validation of a machine learning model to predict cognitive behavioral therapy outcome in obsessive-compulsive disorder using clinical and neuroimaging data
Journal of Affective Disorders · 2025
DOI: 10.1016/j.jad.2025.119729 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift Journal of Affective Disorders, 2025. Verfasst von Laurens A van de Mortel und 21 weiteren Autor:innen. Beteiligte Einrichtung: Amsterdam UMC location University of Amsterdam, Department of Psychiatry, Meibergdreef 9, Amsterdam, the Netherlands; Amsterdam Neuroscience, Amsterd…. Hauptthemen laut MEDLINE: Obsessive-Compulsive Disorder, Cognitive Behavioral Therapy, Machine Learning. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Institute of Mental Health, Government of Catalonia Agency for Administration of University and Research Grants, South African Medical Research Council.
Abstract (Originalsprache)
BACKGROUND: Cognitive behavioral therapy (CBT) is a first-line treatment for obsessive-compulsive disorder (OCD), but clinical response is difficult to predict. In this study, we aimed to develop predictive models using clinical and neuroimaging data from the multicenter Enhancing Neuro-Imaging and Genetics through Meta-Analysis (ENIGMA)-OCD consortium. METHODS: Baseline clinical and resting-state functional magnetic imaging (rs-fMRI) data from 159 adult patients aged 18-60 years (88 female) with OCD who received CBT at four treatment/neuroimaging sites were included. Fractional amplitude of low frequency fluctuations, regional homogeneity and atlas-based functional connectivity were computed. Clinical CBT response and remission were predicted using support vector machine and random forest classifiers on clinical data only, rs-fMRI data only, and the combination of both clinical and rs-fMRI data. RESULTS: The use of only clinical data yielded an area under the ROC curve (AUC) of 0.69 for predicting remission (p = 0.001). Lower baseline symptom severity, younger age, an absence of cleaning obsessions, unmedicated status, and higher education had the highest model impact in predicting remission. The best predictive performance using only rs-fMRI was obtained with regional homogeneity for remission (AUC = 0.59). Predicting response with rs-fMRI generally did not exceed chance level. CONCLUSIONS: Machine learning models based on clinical data may thus hold promise in predicting remission after CBT for OCD, but the predictive power of multicenter rs-fMRI data is limited.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Amsterdam UMC location University of Amsterdam, Department of Psychiatry, Meibergdreef 9, Amsterdam, the Netherlands; Amsterdam Neuroscience, Amsterdam, the Netherlands. Electronic address: l.a.vandemortel@amsterdamumc.…
- Amsterdam UMC location University of Amsterdam, Department of Psychiatry, Meibergdreef 9, Amsterdam, the Netherlands; Amsterdam Neuroscience, Amsterdam, the Netherlands; Leiden University, Institute of Education & Child…
- Bellvitge Biomedical Research Insitute-IDIBELL, Bellvitge University Hospital, Barcelona, Spain; CIBERSAM, Barcelona, Spain; Department of Clinical Sciences, University of Barcelona, Barcelona, Spain.
- Department of Psychiatry, University of Toronto, Toronto, Ontario, Canada; Centre for Addiction and Mental Health, Toronto, Ontario, Canada; Department of Women's and Children's Health, Karolinska Institutet, Stockholm,…
- Department of Radiology, University of California, San Diego, CA, USA; Imaging Research Center, the University of California at Davis, Sacramento, CA, USA; Center for Neuroscience, the University of California at Davis,…
- Bergen Center for Brain Plasticity, Haukeland University Hospital, Bergen, Norway; Psychiatric Department, Hospital of Molde, Molde, Norway.
Förderung
- National Institute of Mental Health
- Government of Catalonia Agency for Administration of University and Research Grants
- South African Medical Research Council
- European Social Fund Plus
- Helse Vest
- National Institute on Aging
- International OCD Foundation
- Carlos III Health Institute
Zitieren
APA
van de Mortel, L. A., Bruin, W. B., Alonso, P., Bertolín, S., Feusner, J. D., Guo, J., Hagen, K., Hansen, B., Thorsen, A. L., Martínez-Zalacaín, I., Menchón, J. M., Nurmi, E. L., O'Neill, J., Piacentini, J. C., Real, E., Segalàs, C., Soriano-Mas, C., Thomopoulos, S. I., Stein, D. J., …, & van Wingen, G. A. (2025). Development and validation of a machine learning model to predict cognitive behavioral therapy outcome in obsessive-compulsive disorder using clinical and neuroimaging data. Journal of Affective Disorders. https://doi.org/10.1016/j.jad.2025.119729
Vancouver
van de Mortel LA, Bruin WB, Alonso P, Bertolín S, Feusner JD, Guo J, et al. Development and validation of a machine learning model to predict cognitive behavioral therapy outcome in obsessive-compulsive disorder using clinical and neuroimaging data. Journal of Affective Disorders. 2025. doi:10.1016/j.jad.2025.119729
BibTeX
@article{vandeMortel2025,
author = {van de Mortel, Laurens A and Bruin, Willem B and Alonso, Pino and Bertolín, Sara and Feusner, Jamie D and Guo, Joyce and Hagen, Kristen and Hansen, Bjarne and Thorsen, Anders Lillevik and Martínez-Zalacaín, Ignacio and Menchón, Jose M and Nurmi, Erika L and O'Neill, Joseph and Piacentini, John C and Real, Eva and Segalàs, Cinto and Soriano-Mas, Carles and Thomopoulos, Sophia I and Stein, Dan J and Thompson, Paul M and van den Heuvel, Odile A and van Wingen, Guido A},
title = {Development and validation of a machine learning model to predict cognitive behavioral therapy outcome in obsessive-compulsive disorder using clinical and neuroimaging data},
journal = {Journal of Affective Disorders},
year = {2025},
doi = {10.1016/j.jad.2025.119729}
}
EUVIMED