Clinical predictors of treatment response towards exposure therapy in virtuo in spider phobia: A machine learning and external cross-validation approach

Elisabeth J Leehr; Kati Roesmann; Joscha Böhnlein; Udo Dannlowski; Bettina Gathmann; Martin J Herrmann; Markus Junghöfer; Hanna Schwarzmeier; Fabian R Seeger; Niklas Siminski; Thomas Straube; Ulrike Lueken; Kevin Hilbert

doi:10.1016/j.janxdis.2021.102448

Clinical predictors of treatment response towards exposure therapy in virtuo in spider phobia: A machine learning and external cross-validation approach

J Anxiety Disord. 2021 Oct:83:102448. doi: 10.1016/j.janxdis.2021.102448. Epub 2021 Jul 10.

Authors

Affiliations

¹ Institute for Translational Psychiatry, University of Münster, Germany.
² Institute of Clinical Psychology and Psychotherapy, University of Siegen, Germany; Institute for Biomagnetism and Biosignalanalysis, University of Münster, Germany. Electronic address: kati.roesmann@uni-siegen.de.
³ Institute of Medical Psychology and Systems Neuroscience, University of Münster, Germany.
⁴ Department of Psychiatry, Psychosomatics, and Psychotherapy, Center for Mental Health, University Hospital of Würzburg, Germany.
⁵ Institute for Biomagnetism and Biosignalanalysis, University of Münster, Germany; Otto-Creutzfeld Center for Cognitive and Behavioral Neuroscience, University of Münster, Germany.
⁶ Institute for Translational Psychiatry, University of Münster, Germany; Institute of Medical Psychology and Systems Neuroscience, University of Münster, Germany.
⁷ Department of Psychiatry, Psychosomatics, and Psychotherapy, Center for Mental Health, University Hospital of Würzburg, Germany; Department of Psychology, Humboldt-Universität zu Berlin, Berlin, Germany.
⁸ Department of Psychology, Humboldt-Universität zu Berlin, Berlin, Germany.

PMID: 34298236
DOI: 10.1016/j.janxdis.2021.102448

Abstract

While being highly effective on average, exposure-based treatments are not equally effective in all patients. The a priori identification of patients with a poor prognosis may enable the application of more personalized psychotherapeutic interventions. We aimed at identifying sociodemographic and clinical pre-treatment predictors for treatment response in spider phobia (SP). N = 174 patients with SP underwent a highly standardized virtual reality exposure therapy (VRET) at two independent sites. Analyses on group-level were used to test the efficacy. We applied a state-of-the-art machine learning protocol (Random Forests) to evaluate the predictive utility of clinical and sociodemographic predictors for a priori identification of individual treatment response assessed directly after treatment and at 6-month follow-up. The reliability and generalizability of predictive models was tested via external cross-validation. Our study shows that one session of VRET is highly effective on a group-level and is among the first to reveal long-term stability of this treatment effect. Individual short-term symptom reductions could be predicted above chance, but accuracies dropped to non-significance in our between-site prediction and for predictions of long-term outcomes. With performance metrics hardly exceeding chance level and the lack of generalizability in the employed between-site replication approach, our study suggests limited clinical utility of clinical and sociodemographic predictors. Predictive models including multimodal predictors may be more promising.

Keywords: Exposure; Machine learning; Predictive modelling; Specific phobia; Treatment response.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Animals
Humans
Implosive Therapy*
Machine Learning
Phobic Disorders* / therapy
Reproducibility of Results
Spiders*