Neuroimaging-based classification of PTSD using data-driven computational approaches: A multisite big data study from the ENIGMA-PGC PTSD consortium.

BACKGROUND: Recent advances in data-driven computational approaches have been helpful in devising tools to objectively diagnose psychiatric disorders. However, current machine learning studies limited to small homogeneous samples, different methodologies, and different imaging collection protocols, limit the ability to directly compare and generalize their results. Here we aimed to classify individuals with PTSD versus controls and assess the generalizability using a large heterogeneous brain datasets from the ENIGMA-PGC PTSD Working group. METHODS: We analyzed brain MRI data from 3,477 structural-MRI; 2,495 resting state-fMRI; and 1,952 diffusion-MRI. First, we identified the brain features that best distinguish individuals with PTSD from controls using traditional machine learning methods. Second, we assessed the utility of the denoising variational autoencoder (DVAE) and evaluated its classification performance. Third, we assessed the generalizability and reproducibility of both models using leave-one-site-out cross-validation procedure for each modality. RESULTS: We found lower performance in classifying PTSD vs. controls with data from over 20 sites (60 % test AUC for s-MRI, 59 % for rs-fMRI and 56 % for d-MRI), as compared to other studies run on single-site data. The performance increased when classifying PTSD from HC without trauma history in each modality (75 % AUC). The classification performance remained intact when applying the DVAE framework, which reduced the number of features. Finally, we found that the DVAE framework achieved better generalization to unseen datasets compared with the traditional machine learning frameworks, albeit performance was slightly above chance. CONCLUSION: These results have the potential to provide a baseline classification performance for PTSD when using large scale neuroimaging datasets. Our findings show that the control group used can heavily affect classification performance. The DVAE framework provided better generalizability for the multi-site data. This may be more significant in clinical practice since the neuroimaging-based diagnostic DVAE classification models are much less site-specific, rendering them more generalizable.

Post-traumatic factors are involved in the evolution of the number of seizures in patients with PNES.

OBJECTIVE: The purpose of this prospective study was to identify predictive factors of the evolution of the number of seizures. METHODS: We included 85 individuals with a diagnosis of Psychogenic Nonepileptic Seizure (PNES) who completed at least two clinical interviews spaced by 6 months during a 24-month follow-up. Participants underwent a structured interview with an experimented clinician in PNES to complete standardized evaluation and validated scales. We collected sociodemographic and clinical data on PNES (number of seizures, duration of the disease), anxiety, depression, history of traumas, alexithymia, dissociation, and post-traumatic stress disorder (PTSD). We used a multivariate linear regression analysis to predict the characteristics independently associated with the evolution of the number of seizures in percentage. RESULTS: Dissociation score was significantly associated with a negative evolution of the number of seizures (p < 0.002). Conversely, the diagnosis of PTSD at inclusion was correlated to a positive evolution of the number of seizures (p < 0.029). CONCLUSION: Dissociation was related to a more pejorative evolution of the number of seizures while PTSD diagnosis was associated with a decreased number of seizures. It is therefore essential to improve detection and treatment of post-traumatic dissociation. Further studies are required to understand the impact of PTSD on the evolution of the number of seizures.