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.
There is a growing body of evidence that stressful events may affect the brain not only as a whole, but also in multiple laterality aspects. The present review is aimed at discussing the effect of stress and stress hormones on structural brain asymmetry. Differences and crossroads of functional and structural asymmetry are briefly mentioned throughout the document. The first part of this review summarizes major findings in the field of structural brain asymmetries in animals and humans from the evolutionary perspective. Additionally, effect of stress on animals is discussed generally. The second part then explores asymmetrical effects of stress on structural changes of principal brain areas - amygdala, hippocampus, neocortex, diencephalon, basal forebrain and basal ganglia from the point of normal lateralization, steroids, trauma and genetic factors. At the end we present hypothesis why stress appears to have asymmetrical effects on lateralized brain structures.
- MeSH
- amygdala diagnostické zobrazování metabolismus MeSH
- bazální ganglia diagnostické zobrazování metabolismus MeSH
- biologická evoluce MeSH
- diencefalon diagnostické zobrazování metabolismus MeSH
- funkční lateralita MeSH
- glukokortikoidy metabolismus MeSH
- hipokampus diagnostické zobrazování metabolismus MeSH
- lidé MeSH
- magnetická rezonanční tomografie MeSH
- mozek diagnostické zobrazování metabolismus MeSH
- neokortex diagnostické zobrazování metabolismus MeSH
- pars basalis telencephali diagnostické zobrazování metabolismus MeSH
- posttraumatická stresová porucha diagnostické zobrazování MeSH
- psychický stres metabolismus MeSH
- systém hypofýza - nadledviny metabolismus MeSH
- systém hypotalamus-hypofýza metabolismus MeSH
- zvířata MeSH
- Check Tag
- lidé MeSH
- zvířata MeSH
- Publikační typ
- časopisecké články MeSH
- přehledy MeSH
