Neuroimaging-based classification of PTSD using data-driven computational approaches: A multisite big data study from the ENIGMA-PGC PTSD consortium
文献类型:期刊论文
作者 | Zhu, Xi74,75; Kim, Yoojean74; Ravid, Orren74; He, Xiaofu75; Suarez-Jimenez, Benjamin73; Zilcha-Mano, Sigal72; Lazarov, Amit71; Lee, Seonjoo74,75; Abdallah, Chadi G.69,70; Angstadt, Michael68 |
刊名 | NEUROIMAGE |
出版日期 | 2023-12-01 |
卷号 | 283页码:13 |
通讯作者邮箱 | yuval neria |
ISSN号 | 1053-8119 |
关键词 | Posttraumatic stress disorder Multimodal MRI Machine learning Deep learning Classification |
DOI | 10.1016/j.neuroimage.2023.120412 |
文献子类 | 实证研究 |
英文摘要 | 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. |
收录类别 | SCI |
WOS关键词 | POSTTRAUMATIC-STRESS-DISORDER ; RESTING-STATE FMRI ; TRAUMA SURVIVORS ; NETWORK ; BIOMARKERS ; MODELS |
资助项目 | NIH[K01MH122774] ; NIH[R01MH117601] ; NIH[U54 EB020403] ; NIH[AT011267] ; NIH[MH111671] ; NIH[R61MH127005] ; NIH[CX001600] ; NIH[K01MH118467] ; NIH[K23 MH090366] ; NIH[T32GM007507] ; NIH[DA 1222/4-1] ; NIH[IK2RX002922] ; NIH[1073041] ; NARSAD Young Investigator Grant from the Brain & Behavior Research Foundation[R61NS120249] ; German Research Foundation[T32MH018931] ; VA RRD Award[F31MH122047] ; National Health and Medical Research Council[27040] ; NIMH[MH111671] ; NIMH[MH119132] ; NIMH[MH097784] ; NIMH[MH129832] |
WOS研究方向 | Neurosciences & Neurology ; Radiology, Nuclear Medicine & Medical Imaging |
语种 | 英语 |
出版者 | ACADEMIC PRESS INC ELSEVIER SCIENCE |
WOS记录号 | WOS:001109390600001 |
资助机构 | NIH ; NARSAD Young Investigator Grant from the Brain & Behavior Research Foundation ; German Research Foundation ; VA RRD Award ; National Health and Medical Research Council ; NIMH |
源URL | [http://ir.psych.ac.cn/handle/311026/46735] |
专题 | 心理研究所_健康与遗传心理学研究室 |
通讯作者 | Neria, Yuval; Morey, Rajendra A. |
作者单位 | 1.Univ Wisconsin, Milwaukee, WI 53201 USA 2.McLean Hosp, 115 Mill St, Belmont, MA 02178 USA 3.Univ Chinese Acad Sci, Dept Psychol, Beijing, Peoples R China 4.Univ Calif Irvine, Irvine, CA USA 5.Leiden Univ, Med Ctr, Leiden, Netherlands 6.Univ Minnesota, Minneapolis, MN USA 7.Univ South Dakota, Vermillion, SD USA 8.VA San Diego Healthcare Syst, Ctr Excellence Stress & Mental Hlth, San Diego, CA USA 9.Univ N Carolina, Chapel Hill, NC 27515 USA 10.Northwestern Univ, Inst Policy Res, Northwestern Neighborhood & Networks Initiat, Evanston, IL USA |
推荐引用方式 GB/T 7714 | Zhu, Xi,Kim, Yoojean,Ravid, Orren,et al. Neuroimaging-based classification of PTSD using data-driven computational approaches: A multisite big data study from the ENIGMA-PGC PTSD consortium[J]. NEUROIMAGE,2023,283:13. |
APA | Zhu, Xi.,Kim, Yoojean.,Ravid, Orren.,He, Xiaofu.,Suarez-Jimenez, Benjamin.,...&Morey, Rajendra A..(2023).Neuroimaging-based classification of PTSD using data-driven computational approaches: A multisite big data study from the ENIGMA-PGC PTSD consortium.NEUROIMAGE,283,13. |
MLA | Zhu, Xi,et al."Neuroimaging-based classification of PTSD using data-driven computational approaches: A multisite big data study from the ENIGMA-PGC PTSD consortium".NEUROIMAGE 283(2023):13. |
入库方式: OAI收割
来源:心理研究所
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。