Multi-domain potential biomarkers for post-traumatic stress disorder (PTSD) severity in recent trauma survivors

Abstract

Contemporary symptom-based diagnosis of post-traumatic stress disorder (PTSD) largely overlooks related neurobehavioral mechanisms and relies entirely on subjective interpersonal reporting. Previous studies associating biomarkers with PTSD have mostly used symptom-based diagnosis as the main outcome measure, disregarding the wide variability and richness of PTSD phenotypical features. Here, we aimed to computationally derive potential biomarkers that could efficiently differentiate PTSD subtypes among recent trauma survivors. A three-staged semi-unsupervised method ("3C") was used to firstly categorize individuals by current PTSD symptom severity, then derive clusters based on clinical features related to PTSD (e.g. anxiety and depression), and finally to classify participants' cluster membership using objective multi-domain features. A total of 256 features were extracted from psychometrics, cognitive functioning, and both structural and functional MRI data, obtained from 101 adult civilians (age = 34.80 ± 11.95; 51 females) evaluated within 1 month of trauma exposure. The features that best differentiated cluster membership were assessed by importance analysis, classification tree, and ANOVA. Results revealed that entorhinal and rostral anterior cingulate cortices volumes (structural MRI domain), in-task amygdala's functional connectivity with the insula and thalamus (functional MRI domain), executive function and cognitive flexibility (cognitive testing domain) best differentiated between two clusters associated with PTSD severity. Cross-validation established the results' robustness and consistency within this sample. The neural and cognitive potential biomarkers revealed by the 3C analytics offer objective classifiers of post-traumatic morbidity shortly following trauma. They also map onto previously documented neurobehavioral mechanisms associated with PTSD and demonstrate the usefulness of standardized and objective measurements as differentiating clinical sub-classes shortly after trauma.

Fig. 1. Parallel coordinates plot of assigned diagnosis and clinical measurements.

a Confusion matrix of PTSD diagnosis versus proposed clusters. Table rows represent individuals’ current clinical DSM-based PTSD diagnosis (PTSD/No PTSD), while the columns represent the two proposed clusters (Cluster1 = LoClus = low-symptomatic cluster/Cluster2 = HiClus = high-symptomatic cluster). This division to clinical diagnosis and proposed clusters created four different groups, colored according to the four lines they represent in part b of this figure. b Parallel coordinates plot of the different groups. The X-axis depicts the four clinical measurements on which the clusters were built (BDI, BAI, PCL, and CGI), as well as the assigned diagnosis (total CAPS score), while the Y-axis depicts their percentiles (standardized values, ranging from 0 to 1). The figure presents the means of each variable for each of the four groups, created by the division to two clusters (HiClus – turquoise, squares; LoClus – red, triangles) and two clinical DSM-based diagnosis (PTSD – darker colors; No PTSD – lighter colors). CGI = Total Score of Clinical Global Impression Scale Questionnaire, PCL = Total Score of PTSD Checklist Questionnaire, BAI = Total Score of Beck Anxiety Inventory Questionnaire, BDI = Total Score of Beck Depression Inventory Questionnaire.

Fig. 2. Parallel coordinates plot of potential biomarkers.

The Y-axis depicts the top 10 most important potential biomarkers in classifying the two clusters, together with their mean decrease GINI measure (i.e. importance index). The domain of each biomarker is presented as a prefix – structural brain measurements (“structural”), functional brain measurements (“functional”), and cognitive domains. Average CAPS-4 total scores is presented for both “low-symptomatic” cluster (cluster 1, LoClus, red) and “high-symptomatic” cluster (cluster 2, HiClus, turquoise). The medians of 400 Bootstrap samplings were drawn, and their median and 0.025 and 0.975 percentiles are plotted per cluster.

Fig. 3. Classification tree based on the two clusters.

The classification tree depicts variables important for the division of the participants to the two clusters, starting from the most important one at the top of the tree (left entorhinal cortex volume). Each block is labeled either HiClus or LoClus, indicating whether most of the subjects in that block belong to the HiClus or the LoClus (turquoise or red) and their proportion (from 50%=lighter colors to 100%=darker colors, see color bar at the top right). Furthermore, each block shows the number of subjects belonging to the dominant cluster (either HiClus or LoClus), and the total number of subjects in that specific block. Inspecting the top block for example, 70 out of 101 participants had left EC volume ≥1449 mm³, out of which 39 belonged to the LoClus. The other 31 participants had a left EC volume <1449 mm³, out of which the most (n = 26) belonged to the HiClus.