Predicting U.S. veteran dropout from trauma-focused eye movement desensitization and reprocessing therapy using machine learning
This study explored the utility of machine learning for (a) predicting EMDR dropout in veterans (N = 279; Fairbanks et al., 2026) and (b) identifying variables linked with dropout.
Article Abstract
“Eye movement desensitization and reprocessing therapy (EMDR) is a first-line posttraumatic stress disorder treatment for veterans (U.S. Department of Veterans Affairs & U.S. Department of Defense, 2023). Yet, little is known about EMDR dropout in veterans. This study explored the utility of machine learning for (a) predicting EMDR dropout in veterans (N = 279; Fairbanks et al., 2026) and (b) identifying variables linked with dropout. Clients were randomized to training (n = 224; 80%) and testing (n = 55; 20%) data sets. At termination, veterans who dropped out (n = 114; 40.9%) reported worse posttraumatic stress disorder and depression symptoms than veterans who completed EMDR. Optimal performance for predicting dropout varied by algorithm and metric, including the final ensemble (precision-recall area under the receiver operating characteristic curve [AUC] = .83, Brier score = .13), random forest (precision-recall AUC = .83, AUC = .89, accuracy = .85), and logistic regression models (precision-recall AUC = .83, specificity = .94). Variables yielding the highest feature importance values that were linked with higher dropout included younger age, more trauma types, worsening posttraumatic stress disorder symptoms, improving depression symptoms, and missing symptom measures. Together, results underscore the importance of better understanding EMDR dropout among veterans. Findings suggest that dropout risk factors may operate differently across veteran subgroups and that machine learning may be useful for characterizing this heterogeneity. Therapists, researchers, and clinics may consider using research-based dropout prevention strategies for veterans at risk of dropping out. (PsycInfo Database Record (c) 2026 APA, all rights reserved)
Impact Statement
In a national sample of veterans (N = 279), 40.9% dropped out of eye movement desensitization and reprocessing therapy, and those who did reported worse outcomes. Findings suggest machine learning is a promising approach for predicting eye movement desensitization and reprocessing therapy dropout and variables that influence dropout risk. Therapists, researchers, and policymakers may consider integrating dropout prevention strategies for veterans initiating eye movement desensitization and reprocessing therapy.”
—Description from publisher
Article Access
Purchase/Subscription Required
Penix-Smith, E. A., Glitsos, S. C., & Quartana, P. J. (2026). Predicting U.S. veteran dropout from trauma-focused eye movement desensitization and reprocessing therapy using machine learning. Psychological Services, Online. https://doi.org/10.1037/ser0001103
Date
November 12, 2026
Creator(s)
Elizabeth A. Penix-Smith, Stephanie C. Glitsos, Philip J. Quartana
Topics
PTSD
Client Population
Military/Veterans
Publisher
Educational Publishing Foundation
APA Citation
Penix-Smith, E. A., Glitsos, S. C., & Quartana, P. J. (2026). Predicting U.S. veteran dropout from trauma-focused eye movement desensitization and reprocessing therapy using machine learning. Psychological Services, Online. https://doi.org/10.1037/ser0001103
Audience
EMDR Therapists
Language
English
Content Type
Article, Peer-Reviewed
Access Type
External Resource