EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Moving toward precision PTSD treatment: predicting veterans' intensive PTSD treatment response using continuously updating machine learning models

Dale L Smith iD, Philip Held

Psychological Medicine · 2023-09 · 53 (12) · 5500-5509

DOI: 10.1017/s0033291722002689 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Psychological Medicine, online erschienen am 19.10.2022. Verfasst von Dale L Smith und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychiatry and Behavioral Sciences, Rush University Medical Center, 325 S. Paulina St., Suite 200, Chicago, IL 60612, USA. Hauptthemen laut MEDLINE: Veterans, Stress Disorders, Post-Traumatic, Cognitive Behavioral Therapy. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Considerable heterogeneity exists in treatment response to first-line posttraumatic stress disorder (PTSD) treatments, such as Cognitive Processing Therapy (CPT). Relatively little is known about the timing of when during a course of care the treatment response becomes apparent. Novel machine learning methods, especially continuously updating prediction models, have the potential to address these gaps in our understanding of response and optimize PTSD treatment.

Methods

Using data from a 3-week ( n = 362) CPT-based intensive PTSD treatment program (ITP), we explored three methods for generating continuously updating prediction models to predict endpoint PTSD severity. These included Mixed Effects Bayesian Additive Regression Trees (MixedBART), Mixed Effects Random Forest (MERF) machine learning models, and Linear Mixed Effects models (LMM). Models used baseline and self-reported PTSD symptom severity data collected every other day during treatment. We then validated our findings by examining model performances in a separate, equally established, 2-week CPT-based ITP ( n = 108).

Results

Results across approaches were very similar and indicated modest prediction accuracy at baseline ( R 2 ~ 0.18), with increasing accuracy of predictions of final PTSD severity across program timepoints (e.g. mid-program R 2 ~ 0.62). Similar findings were obtained when the models were applied to the 2-week ITP. Neither the MERF nor the MixedBART machine learning approach outperformed LMM prediction, though benefits of each may differ based on the application.

Conclusions

Utilizing continuously updating models in PTSD treatments may be beneficial for clinicians in determining whether an individual is responding, and when this determination can be made.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

VeteransStress Disorders, Post-TraumaticCognitive Behavioral TherapyHumansBayes TheoremMachine LearningTreatment Outcome

Stichwörter der Autor:innen

Cognitive processing therapyPTSDlongitudinal analysismachine learningprecision medicineveterans

Autor:innen und Institutionen

  • Department of Psychiatry and Behavioral Sciences, Rush University Medical Center, 325 S. Paulina St., Suite 200, Chicago, IL 60612, USA.
  • Behavioral Sciences, Olivet Nazarene University, 1 University Ave., Bourbonnais, Illinois 60914, USA.

ORCID-Profile: Dale L Smith

Zitieren

APA

Smith, D. L., & Held, P. (2023). Moving toward precision PTSD treatment: predicting veterans' intensive PTSD treatment response using continuously updating machine learning models. Psychological Medicine, 53(12), 5500-5509. https://doi.org/10.1017/s0033291722002689

Vancouver

Smith DL, Held P. Moving toward precision PTSD treatment: predicting veterans' intensive PTSD treatment response using continuously updating machine learning models. Psychological Medicine. 2023;53(12):5500-5509. doi:10.1017/s0033291722002689

BibTeX
@article{Smith2023,
  author = {Smith, Dale L and Held, Philip},
  title = {Moving toward precision PTSD treatment: predicting veterans' intensive PTSD treatment response using continuously updating machine learning models},
  journal = {Psychological Medicine},
  year = {2023},
  volume = {53},
  number = {12},
  pages = {5500--5509},
  doi = {10.1017/s0033291722002689}
}
Kostenlos starten →