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

A primer on the use of machine learning to distil knowledge from data in biological psychiatry

Applications of machine learning in the biomedical sciences are growing rapidly. This growth has been spurred by diverse cross-institutional and interdisciplinary collaborations, public availability of large datasets, an increase in the accessibility of analytic routines, and the availability of powerful computing resources. With this increased access and exposure to machine learning comes a responsibility for education and a deeper understanding of its bases and bounds, borne equally by data scientists seeking to ply their analytic wares in medical research and by biomedical scientists seeking to harness such methods to glean knowledge from data. This article provides an accessible and critical review of machine learning for a biomedically informed audience, as well as its applications in psychiatry. The review covers definitions and expositions of commonly used machine learning methods, and historical trends of their use in psychiatry. We also provide a set of standards, namely Guidelines for REporting Machine Learning Investigations in Neuropsychiatry (GREMLIN), for designing and reporting studies that use machine learning as a primary data-analysis approach. Lastly, we propose the establishment of the Machine Learning in Psychiatry (MLPsych) Consortium, enumerate its objectives, and identify areas of opportunity for future applications of machine learning in biological psychiatry. This review serves as a cautiously optimistic primer on machine learning for those on the precipice as they prepare to dive into the field, either as methodological practitioners or well-informed consumers.

The role of dissociation-related beliefs about memory in trauma-focused treatment

OBJECTIVE

Dysfunctional cognitions play a central role in the development of post-traumatic stress disorder (PTSD). However the role of specific dissociation-related beliefs about memory has not been previously investigated. This study aimed to investigate the role of dissociation-related beliefs about memory in trauma-focused treatment. It was hypothesized that patients with the dissociative subtype of PTSD would show higher levels of dissociation-related beliefs, dissociation-related beliefs about memory would decrease after trauma-focused treatment, and higher pre-treatment dissociation-related beliefs would be associated with fewer changes in PTSD symptoms.

METHOD

Post-traumatic symptoms, dissociative symptoms, and dissociation-related beliefs about memory were assessed in a sample of patients diagnosed with PTSD (n = 111) or the dissociative subtype of PTSD (n = 61). They underwent intensive trauma-focused treatment consisting of four or eight consecutive treatment days. On each treatment day, patients received 90 min of individual prolonged exposure (PE) in the morning and 90 min of individual eye movement desensitization and reprocessing (EMDR) therapy in the afternoon. The relationship between dissociation-related beliefs about memory and the effects of trauma-focused treatment was investigated.

RESULTS

Dissociation-related beliefs about memory were significantly associated with PTSD and its dissociative symptoms. In addition, consistent with our hypothesis, patients with the dissociative subtype of PTSD scored significantly higher on dissociation-related beliefs about memory pre-treatment than those without the dissociative subtype. Additionally, the severity of these beliefs decreased significantly after trauma-related treatment. Contrary to our hypothesis, elevated dissociation-related beliefs did not negatively influence treatment outcome.

CONCLUSION

The results of the current study suggest that dissociation-related beliefs do not influence the outcome of trauma-focused treatment, and that trauma-focused treatment does not need to be altered specifically for patients experiencing more dissociation-related beliefs about memory because these beliefs decrease in association with treatment.

Using machine learning algorithm to predict the risk of post-traumatic stress disorder among firefighters in Changsha

OBJECTIVES

Firefighters are prone to suffer from psychological trauma and post-traumatic stress disorder (PTSD) in the workplace, and have a poor prognosis after PTSD. Reliable models for predicting PTSD allow for effective identification and intervention for patients with early PTSD. By collecting the psychological traits, psychological states and work situations of firefighters, this study aims to develop a machine learning algorithm with the aim of effectively and accurately identifying the onset of PTSD in firefighters, as well as detecting some important predictors of PTSD onset.

METHODS

This study conducted a cross-sectional survey through convenient sampling of firefighters from 20 fire brigades in Changsha, which were evenly distributed across 6 districts and Changsha County, with a total of 628 firefighters. We used the synthetic minority oversampling technique (SMOTE) to process data sets and used grid search to finish the parameter tuning. The predictive capability of several commonly used machine learning models was compared by 5-fold cross-validation and using the area under the receiver operating characteristic curve (ROC-AUC), accuracy, precision, recall, and F1 score.

RESULTS

The random forest model achieved good performance in predicting PTSD with an average AUC score at 0.790. The mean accuracy of the model was 90.1%, with an F1 score of 0.945. The three most important predictors were perseverance, forced thinking, and reflective deep thinking, with weights of 0.165, 0.158, and 0.152, respectively. The next most important predictors were employment time, psychological power, and optimism.

CONCLUSIONS

PTSD onset prediction model for Changsha firefighters constructed by random forest has strong predictive ability, and both psychological characteristics and work situation can be used as predictors of PTSD onset risk for firefighters. In the next step of the study, validation using other large datasets is needed to ensure that the predictive models can be used in clinical setting.

Examining trauma cognition change trajectories among initial PTSD treatment non-optimal responders: a potential avenue to guide subsequent treatment selection

BACKGROUND

Despite their general effectiveness, 14-50% of individuals do not fully respond to evidence-based treatments for posttraumatic stress disorder (PTSD). Although changes in negative posttrauma cognitions (NPCs) are considered a likely PTSD treatment mechanism, less is known about how NPCs change among individuals who continue to be symptomatic following treatment (non-optimal responders).

OBJECTIVE

The objective of this study was to examine NPC change trajectories among individuals who were determined to be non-optimally responsive to intensive PTSD treatment.

METHOD

Using a 3-week Cognitive Processing Therapy-based intensive PTSD treatment sample (ITP; N = 243), the present study examined the number of distinct NPC change trajectories among non-optimal responders via Group Based Trajectory Modeling and assessed predictors of non-optimal responders' NPC change trajectory membership. Analyses were replicated in a separate 2-week ITP sample (N = 215).

RESULTS

In both non-optimal responder samples, two trajectories emerged; a no NPC change group which represented those with an overall lack of NPC change throughout treatment and an NPC change group which represented those with an overall reduction of NPCs occurring primarily later in treatment. Changes in PTSD symptom severity during treatment was the only consistent predictor of NPC change trajectory group membership among treatment non-optimal responders across ITPs.

CONCLUSIONS

Findings suggest NPC change among non-optimal responders is nuanced and may inform subsequent intervention selection, resulting in testable hypotheses for future research.