Neuroimaging-based classification of PTSD using data-driven computational approaches: A multisite big data study from the ENIGMA-PGC PTSD consortium.
Date
2023-12
Journal Title
Journal ISSN
Volume Title
Repository Usage Stats
views
downloads
Citation Stats
Abstract
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.Type
Department
Description
Provenance
Citation
Permalink
Published Version (Please cite this version)
Publication Info
Zhu, Xi, Yoojean Kim, Orren Ravid, Xiaofu He, Benjamin Suarez-Jimenez, Sigal Zilcha-Mano, Amit Lazarov, Seonjoo Lee, et al. (2023). Neuroimaging-based classification of PTSD using data-driven computational approaches: A multisite big data study from the ENIGMA-PGC PTSD consortium. NeuroImage, 283. p. 120412. 10.1016/j.neuroimage.2023.120412 Retrieved from https://hdl.handle.net/10161/31283.
This is constructed from limited available data and may be imprecise. To cite this article, please review & use the official citation provided by the journal.
Collections
Scholars@Duke
Delin Sun
I am interested in the neuropsychological and behavioral correlates of posttraumatic stress disorder (PTSD) and adolescent trauma. With a multidisciplinary background in psychology, physics, and biology, I have specific training and expertise in neuroimaging methods and secondary data analysis of neural changes in PTSD and childhood trauma. I systematically study PTSD-related structural and functional brain images using methods that focus on different levels including regional changes, connectivity, and brain networks, respectively, to build a complete behavioral-brain map. I also study the relationship between adolescent brain development and trauma as well as alcohol by using brain structure network graphs, longitudinal studies, and machine learning research methods. Besides, I utilize neuroimaging and neurophysiological techniques to investigate the neural underpinnings of social cognitive and affective functions in both healthy volunteers and patients with mental disorders including excessive internet usage, smoking addiction, Alzheimer’s Disease, and depression. I have successfully collaborated with researchers locally or from other institutions and have had several peer-reviewed publications in each project.
Rajendra A. Morey
Research in my lab is focused on brain changes associated with posttraumatic stress disorder (PTSD), traumatic brain injury (TBI), and other neuropsychiatric disorders. We apply several advanced methods for understanding brain function including functional MRI, structural MRI, diffusion tensor imaging, and genetic effects.
Unless otherwise indicated, scholarly articles published by Duke faculty members are made available here with a CC-BY-NC (Creative Commons Attribution Non-Commercial) license, as enabled by the Duke Open Access Policy. If you wish to use the materials in ways not already permitted under CC-BY-NC, please consult the copyright owner. Other materials are made available here through the author’s grant of a non-exclusive license to make their work openly accessible.