Publication details

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

Authors

ZHU Xi KIM Yoojean RAVID Orren HE Xiaofu SUAREZ-JIMENEZ Benjamin ZILCHA-MANO Sigal LAZAROV Amit LEE Seonjoo ABDALLAH Chadi G ANGSTADT Michael AVERILL Christopher L BAIRD C Lexi BAUGH Lee A BLACKFORD Jennifer U BOMYEA Jessica BRUCE Steven E BRYANT Richard A CAO Zhihong CHOI Kyle CISLER Josh COTTON Andrew S DANIELS Judith K DAVENPORT Nicholas D DAVIDSON Richard J DEBELLIS Michael D DENNIS Emily L DENSMORE Maria DEROON-CASSINI Terri DISNER Seth G WISSAM El Hage ETKIN Amit FANI Negar FERCHO Kelene A FITZGERALD Jacklynn FORSTER Gina L FRIJLING Jessie L GEUZE Elbert GONENC Atilla GORDON Evan M GRUBER Staci GRUPE Daniel GUENETTE Jeffrey P HASWELL Courtney C HERRINGA Ryan J HERZOG Julia HOFMANN David Bernd HOSSEINI Bobak HUDSON Anna R HUGGINS Ashley A IPSER Jonathan C JAHANSHAD Neda JIA-RICHARDS Meilin JOVANOVIC Tanja KAUFMAN Milissa L KENNIS Mitzy KING Anthony KINZEL Philipp KOCH Saskia B J KOERTE Inga K KOOPOWITZ Sheri M KORGAONKAR Mayuresh S KRYSTAL John H LANIUS Ruth LARSON Christine L LEBOIS Lauren A M LI Gen LIBERZON Israel LU Guang Ming LUO Yifeng MAGNOTTA Vincent A MANTHEY Antje MARON-KATZ Adi MAY Geoffery MCLAUGHLIN Katie MUELLER Sven C NAWIJN Laura NELSON Steven M NEUFELD Richard W J NITSCHKE Jack B LEARY Erin M OLATUNJI Bunmi O OLFF Miranda PEVERILL Matthew PHAN K Luan QI Rongfeng QUIDE Yann REKTOR Ivan RESSLER Kerry ŘÍHA Pavel ROSS Marisa ROSSO Isabelle M SALMINEN Lauren E SAMBROOK Kelly SCHMAHL Christian SHENTON Martha E SHERIDAN Margaret SHIH Chiahao SICORELLO Maurizio SIERK Anika SIMMONS Alan N SIMONS Raluca M SIMONS Jeffrey S SPONHEIM Scott R STEIN Murray B STEIN Dan J STEVENS Jennifer S STRAUBE Thomas SUN Delin THEBERGE Jean THOMPSON Paul M THOMOPOULOS Sophia I VAN DER WEE Nic J A VAN DER WERFF Steven J A VAN ERP Theo G M VAN ROOIJ Sanne J H MIRJAM van Zuiden VARKEVISSER Tim VELTMAN Dick J VERMEIREN Robert R J M WALTER Henrik WANG Li WANG Xin WEIS Carissa WINTERNITZ Sherry XIE Hong ZHU Ye WALL Melanie NERIA Yuval MOREY Rajendra A

Year of publication 2023
Type Article in Periodical
Magazine / Source Neuroimage
MU Faculty or unit

Faculty of Medicine

Citation
Web https://www.sciencedirect.com/science/article/pii/S1053811923005633?via%3Dihub
Doi http://dx.doi.org/10.1016/j.neuroimage.2023.120412
Keywords Posttraumatic stress disorder; Multimodal MRI; Machine learning; Deep learning; Classification
Description 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.

You are running an old browser version. We recommend updating your browser to its latest version.

More info