Who will respond to intensive PTSD treatment? A machine learning approach to predicting response prior to starting treatment

Held, Philip; Schubert, Ryan A.; Pridgen, Sarah; Kovacevic, Merdijana; Montes, Mauricio; Christ, Nicole M.; Banerjee, Uddyalok; Smith, Dale L.

doi:10.1016/j.jpsychires.2022.03.066

Cited by 7 publications

(8 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This was evaluated using three approaches; Mixed Effect Random Forest (MERF; Hajjem, Bellavance, & Larocque, 2011 and Mixed Effects Bayesian Additive Regression Trees (MixedBART; Spanbauer & Sparapani, 2021), which both appropriately model random effects, and gold-standard statistical linear mixed-effects longitudinal models (LMMs) were used to generate these updating predictions. As shown previously (Held et al, 2022b), we expected that models would provide acceptable performance with baseline predictors, but that accuracy would improve throughout the program with the incorporation of updated PTSD severity information as treatment progressed and change trajectories became more apparent. Testing continuously improving models could provide foundational information in implementing a precision medicine-based approach in PTSD treatment.…”

Section: Introductionmentioning

confidence: 94%

“…MixedBART and BART default parameters regarding priors and number of trees, without extensive cross-validation, are generally adequate and outperform other machine learning and statistical methods under many conditions. Based on insight from previous work (Held et al, 2022b), we used Dirichlet, rather than uniform, priors for variable selection probabilities. This allows models to adapt to the existence of more useful predictors in the dataset, thus accommodating the expectation that clinical features and updated PTSD severity values are likely to be more useful in prediction than demographic features (Held et al, 2021(Held et al, , 2022b.…”

Section: Analytic Strategymentioning

confidence: 99%

“…Based on insight from previous work (Held et al, 2022b), we used Dirichlet, rather than uniform, priors for variable selection probabilities. This allows models to adapt to the existence of more useful predictors in the dataset, thus accommodating the expectation that clinical features and updated PTSD severity values are likely to be more useful in prediction than demographic features (Held et al, 2021(Held et al, , 2022b. As a Bayesian analytic method, MixBART approaches inference by sampling from the posterior distribution generated computationally utilizing existing data and relevant priors.…”

Section: Analytic Strategymentioning

confidence: 99%

See 2 more Smart Citations

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

Smith

Held²

2022

Psychol. Med.

Self Cite

View full text Add to dashboard Cite

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 (R2 ~ 0.18), with increasing accuracy of predictions of final PTSD severity across program timepoints (e.g. mid-program R2 ~ 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.

show abstract

Section: Introductionmentioning

confidence: 94%

Section: Analytic Strategymentioning

confidence: 99%

Section: Analytic Strategymentioning

confidence: 99%

See 1 more Smart Citation

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

Smith

Held²

2022

Psychol. Med.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Die relevanten Variablen in Prädiktor- und Personalisierungsstudien sind unterschiedlich und abhängig von den zu Beginn der Therapie erfassten Variablen. Am häufigsten zeigen sich Zusammenhänge zwischen Prä-PTBS-Symptomschwere und Outcome, die jedoch in ihrer Richtung unterschiedlich sind [ 14 , 16 , 17 , 27 , 30 ]. In mehreren Studien zeigte sich eine schlechtere Wirksamkeit der traumafokussierten Behandlung bei sexueller Traumatisierung [ 7 , 14 , 30 ] und Komorbiditäten, insbesondere einer depressiven Symptombelastung [ 8 , 16 , 17 , 27 ].…”

Section: Ergebnisseunclassified

Personalized psychotherapy of posttraumatic stress disorder

Steuwe,

Blaß,

Herpertz

et al. 2023

Nervenarzt

View full text Add to dashboard Cite

Zusammenfassung Hintergrund Eine relevante Heterogenität von Behandlungseffekten bei der posttraumatischen Belastungsstörung (PTBS) wird vor dem Hintergrund der Debatte um die Notwendigkeit einer phasenbasierten Behandlung sowie in Anbetracht der neuen Diagnose der komplexen PTBS diskutiert und ist inzwischen nachgewiesen. Dennoch gibt es bisher wenig Personalisierung in der Therapie der PTBS. Ziel der vorliegenden Arbeit ist es, den aktuellen Forschungsstand zur personalisierten Auswahl bestimmter Psychotherapiemethoden zur Behandlung der PTBS anhand von Patient:innenmerkmalen durch statistische Verfahren darzustellen. Methodik Es wurde eine systematische Literaturrecherche in den Datenbanken PubMed (inkl. Medline), Embase, Web of Science Core Collection, Google Scholar, PsycINFO und PSYNDEX zu klinischen Studien und Übersichtsarbeiten zu personalisierter Therapie der PTBS durchgeführt. Ergebnisse 13 relevante Publikationen wurden identifiziert, hiervon waren 5 Artikel Prädiktoranalysen in Stichproben ohne Kontrollbedingung. 7 Artikel zeigten Analysen von randomisiert-kontrollierten Studien (RCT) mit einem Post-hoc-Vergleich der Behandlungseffekte optimal und nichtoptimal zugeordneter Patient:innen. Zudem liegt ein Review-Artikel zur Behandlungsauswahl bei PTBS und komorbider BPS vor. Diskussion Die vorliegenden Publikationen deuten auf Bedeutung und Nutzen personalisierter Behandlung bei der PTBS hin. Die für die Personalisierung ermittelten relevanten Prädiktorvariablen sollten als Anregung genutzt werden, diese in prospektiven Studien genauer zu untersuchen.

show abstract

“…To our knowledge, researchers have not applied the prognostic index approach to digital interventions for trauma survivors. Clues into predictors may be gleaned from studies of PTSD psychotherapies, for which a range of prognostic predictors have been identified (Held et al, 2022; Herzog et al, 2021; Nixon et al, 2021; Stirman et al, 2021). For example, examining a sample of women military service members who received either prolonged exposure or present-centered therapy, Stirman et al (2021) identified the following as predicting higher posttreatment PTSD severity: higher baseline PTSD severity, lower perceived treatment credibility, poorer mental and physical functioning, and history of military sexual trauma.…”

mentioning

confidence: 99%

A prognostic index to predict symptom and functional outcomes of a coached, web-based intervention for trauma-exposed veterans.

Hallenbeck,

Wielgosz,

Cohen

et al. 2024

Psychological Services

View full text Add to dashboard Cite

Researchers at the Department of Veterans Affairs (VA) have studied interventions for posttraumatic stress disorder and co-occurring conditions in both traditional and digital formats. One such empirically supported intervention is web skills training in affective and interpersonal regulation (webSTAIR), a coached, 10-module web program based on STAIR. To understand which patient characteristics were predictive of webSTAIR outcomes in a sample of trauma-exposed veterans (N = 189), we used machine learning (ML) to develop a prognostic index from among 18 baseline characteristics (i.e., demographic, military, trauma history, and clinical) to predict posttreatment posttraumatic stress disorder severity, depression severity, and psychosocial functioning impairment. We compared the ML models to a benchmark of linear regression models in which the only predictor was the baseline severity score of the outcome measure. The ML and "severity-only" models performed similarly, explaining 39%-45% of the variance in outcomes. This suggests that baseline symptom severity and functioning are strong indicators for webSTAIR outcomes in veterans, with higher severity indicating worse prognosis, and that the other variables examined did not contribute significant added predictive signal. Findings also highlight the importance of comparing ML models to an appropriate benchmark. Future research with larger samples could potentially detect smaller patient-level effects as well as effects driven by other types of variables (e.g., therapeutic process variables). As a transdiagnostic, digital intervention, webSTAIR can potentially serve a diverse veteran population with varying trauma histories and may be best conceptualized as a beneficial first step of a stepped care model for those with heightened symptoms or impairment. Impact StatementWeb skills training in affective and interpersonal regulation (webSTAIR) is a coached, web-based intervention for trauma survivors that improves posttraumatic stress disorder, depression, and psychosocial functioning. Veterans receiving webSTAIR who begin treatment with more severe symptoms or functioning impairment tend to have more symptoms or impairment after treatment; no other patient characteristics including age, gender, race, or type of trauma were predictive of treatment outcomes. webSTAIR may be offered to veterans with diverse backgrounds and trauma histories, and for those with more initial symptoms, can be a helpful first treatment before potentially pursuing higher intensity treatment.

show abstract

Who will respond to intensive PTSD treatment? A machine learning approach to predicting response prior to starting treatment

Cited by 7 publications

References 30 publications

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

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

Personalized psychotherapy of posttraumatic stress disorder

A prognostic index to predict symptom and functional outcomes of a coached, web-based intervention for trauma-exposed veterans.

Contact Info

Product

Resources

About