Abstract
Background: Previously, we identified sleep-electroencephalography (EEG) spectral power and synchrony features that differed significantly at a population-average level between subjects with and without posttraumatic stress disorder (PTSD). Here, we aimed to examine the extent to which a combination of such features could objectively identify individual subjects with PTSD.Methods: We analyzed EEG data recorded from 78 combat-exposed Veteran men with (n = 31) and without (n = 47) PTSD during two consecutive nights of sleep. To obviate the need for manual assessment of sleep staging and facilitate extraction of features from the EEG data, for each subject, we computed 780 stage-independent, whole-night features from the 10 most commonly used EEG channels. We performed feature selection and trained a logistic regression model using a training set consisting of the first 47 consecutive subjects (18 with PTSD) of the study. Then, we evaluated the model on a testing set consisting of the remaining 31 subjects (13 with PTSD).Results: Feature selection yielded three uncorrelated features that were consistent across the two consecutive nights and discriminative of PTSD. One feature was from the spectral power in the delta band (2–4 Hz) and the other two were from phase synchronies in the alpha (10–12 Hz) and gamma (32–40 Hz) bands. When we combined these features into a logistic regression model to predict the subjects in the testing set, the trained model yielded areas under the receiver operating characteristic curve of at least 0.80. Importantly, the model yielded a testing-set sensitivity of 0.85 and a positive predictive value (PPV) of 0.31.Conclusions: We identified robust stage-independent, whole-night features from EEG signals and combined them into a logistic regression model to discriminate subjects with and without PTSD. On the testing set, the model yielded a high sensitivity and a PPV that was twice the prevalence rate of PTSD in the U.S. Veteran population. We conclude that, using EEG signals collected during sleep, such a model can potentially serve as a means to objectively identify U.S. Veteran men with PTSD.
Highlights
Sleep disturbances are a hallmark of posttraumatic stress disorder (PTSD) [1]
We developed a multivariate classifier using a training set, which consisted of the first 47 consecutive subjects (18 with PTSD) of the study, and evaluated the classifier on the test set, which consisted of the remaining 31 subjects (13 with PTSD), in order to assess the reproducibility of our findings
We computed the AUC and the corresponding lower and upper bounds of the 95% confidence interval (CI) and selected features for which the lower bound of the CI exceeded 0.5 on each of the two nights to guard against chance associations (Figure 2, step 4)
Summary
Sleep disturbances are a hallmark of posttraumatic stress disorder (PTSD) [1]. For this reason, previous studies have analyzed electroencephalography (EEG) data from overnight sleep-polysomnography (PSG) recordings to identify differences in sleep patterns between groups of subjects with and without PTSD [2,3,4,5]. Analyzing the data from the same study using a similar procedure, we found that the synchrony of EEG signals between channel pairs [the average phase difference between two time-series signals over a given time interval [7]] could significantly discriminate the two groups [8] Another recent study by Modarres et al [9]—the only publication to date that investigated synchrony between EEG channels in PTSD subjects during sleep— reported grouplevel differences, they did not assess the reproducibility of their results across multiple nights or in an independent dataset.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
