Machine learning applied to fMRI patterns of brain activation in response to mutilation pictures predicts PTSD symptoms.

BACKGROUND: The present study aimed to apply multivariate pattern recognition methods to predict posttraumatic stress symptoms from whole-brain activation patterns during two contexts where the aversiveness of unpleasant pictures was manipulated by the presence or absence of safety cues. METHODS: Trauma-exposed participants were presented with neutral and mutilation pictures during functional magnetic resonance imaging (fMRI) collection. Before the presentation of pictures, a text informed the subjects that the pictures were fictitious ("safe context") or real-life scenes ("real context"). We trained machine learning regression models (Gaussian process regression (GPR)) to predict PTSD symptoms in real and safe contexts. RESULTS: The GPR model could predict PTSD symptoms from brain responses to mutilation pictures in the real context but not in the safe context. The brain regions with the highest contribution to the model were the occipito-parietal regions, including the superior parietal gyrus, inferior parietal gyrus, and supramarginal gyrus. Additional analysis showed that GPR regression models accurately predicted clusters of PTSD symptoms, nominal intrusion, avoidance, and alterations in cognition. As expected, we obtained very similar results as those obtained in a model predicting PTSD total symptoms. CONCLUSION: This study is the first to show that machine learning applied to fMRI data collected in an aversive context can predict not only PTSD total symptoms but also clusters of PTSD symptoms in a more aversive context. Furthermore, this approach was able to identify potential biomarkers for PTSD, especially in occipitoparietal regions.

The top-100 cited articles on post-traumatic stress disorder: a historical bibliometric analysis.

This is a bibliometric analysis of the most-cited articles on post-traumatic stress disorder (PTSD) with the objective of identifying citation patterns for researchers, journals, centers, periods, topics, and nations. A search was conducted in Thomson Reuters' WoS Core Collection employing the expression TI = (posttraumatic stress disorder OR post-traumatic stress disorder OR PTSD). The 100 most-cited articles were downloaded, and the relevant data were extracted and analyzed. These studies had a total of 69,649 citations, ranging from a minimum of 360 to a maximum of 6029 citations, with an average of 696.49, a standard deviation of 720.92, mode of 369, and a median of 512. Eighty-eight percent of the most-cited articles on PTSD originated from the USA, with just six cities accounting for 52% of the publications and the Boston area alone responsible for almost one-fifth of the total output. The universities of Yale and Harvard headed the ranking of institutions with larger numbers of highly-cited articles. Female researchers represented 42.3% of all authors, 51% of the first authors, and 48% of the corresponding authors. The proportion of M.D. authors decreased significantly between the 1980-1999 (42%) and the 2000-2019 (27.2%) periods while that of Ph.D. authors increased from 44% to 57.4%. The most studied population was military veterans (28%). Female victims of sexual or physical violence, traumatized children, and adult survivors of childhood abuse were assessed in only 6-7% of the most-cited publications. Ten clinical trials evaluated psychological interventions but only three investigated pharmacotherapy. We concluded that influential research on PTSD remains centralized in the USA. A balanced gender representation in publications was found. There was a heavy reliance on combat veterans as the study population. Few highly-cited studies on the pharmacotherapy for PTSD were identified. Focused efforts are needed to address these challenges.

The increasing internationalization of mainstream posttraumatic stress disorder research: a bibliometric study.

The aim of this study was to quantify changes in the national contributions to research related to posttraumatic stress disorder (PTSD) from 1983 through 2002. Using the Web of Science database (Thomson Scientific, Philadelphia, PA), we classified articles according to the year of publication and the country of the authors. The number of publishing countries increased from 7 between 1983 and 1987 to 39 between 1998 and 2002. Meanwhile, the U.S. output share declined from 87.6% in the first period to 62.4%. Although the number of countries publishing on PTSD has steadily increased, research is still dominated qualitatively and quantitatively by developed countries. These findings suggest a growing international acceptance of this diagnostic category. However, the immaturity of PTSD research is demonstrated by the concentration of publications in a few countries.