Deep learning model of fMRI connectivity predicts PTSD symptom trajectories in recent trauma survivors

Shelly Sheynin, Lior Wolf, Ziv Ben-Zion, Jony Sheynin, Shira Reznik, Jackob Nimrod Keynan, Roee Admon, Arieh Shalev, Talma Hendler, Israel Liberzon

Research output: Contribution to journalArticlepeer-review

Abstract

Early intervention following exposure to a traumatic life event could change the clinical path from the development of post traumatic stress disorder (PTSD) to recovery, hence the interest in early detection and underlying biological mechanisms involved in the development of post traumatic sequelae. We introduce a novel end-to-end neural network that employs resting-state and task-based functional MRI (fMRI) datasets, obtained one month after trauma exposure, to predict PTSD symptoms at one-, six- and fourteen-months after the exposure. FMRI data, as well as PTSD status and symptoms, were collected from adults at risk for PTSD development, after admission to emergency room following a traumatic event. Our computational method utilized a per-region encoder to extract brain regions embedding, which were subsequently updated by applying the algorithmic technique of pairwise attention. The affinities obtained between each pair of regions were combined to create a pairwise co-activation map used to perform multi-label classification. The results demonstrate that the novel method's performance in predicting PTSD symptoms, in a prospective manner, outperforms previous analytical techniques reported in the fMRI literature, all trained on the same dataset. We further show a high predictive ability for predicting PTSD symptom clusters and PTSD persistence. To the best of our knowledge, this is the first deep learning method applied on fMRI data with respect to prospective clinical outcomes, to predict PTSD status, severity and symptom clusters. Future work could further delineate the mechanisms that underlie such a prediction, and potentially improve single patient characterization.

Original languageEnglish
Article number118242
JournalNeuroImage
Volume238
DOIs
StatePublished - Sep 2021

Bibliographical note

Funding Information:
The work was supported by award number R01-MH-103287 from the National Institute of Mental Health (NIMH) given to A. Y.S. (PI), I.L. and T.H. (co-Investigators, subcontractors), and had undergone critical review by the NIMH Adult Psychopathology and Disorders of Aging study section. Additional funding was provided by the ISF Israel Precision Medicine Partnership (IPMP) Program (grant 2923/20). This project has also received funding from the European Research Council (ERC) under the European Unions Horizon 2020 research and innovation programme (grant ERC CoG 725974 ). Lastly, this work was additionally supported by a grant from the U.S. Department of Defense, award number W81XWH-16-C-0198 and also by the ISRAEL SCIENCE FOUNDATION (grant No. 2923/20), within the Israel Precision Medicine Partnership program. We would like to thank the research team at Tel-Aviv Sourasky Medical Center - including Nili Green, Mor Halevi, Sheli Luvton, Yael Shavit, Olga Nevenchannaya, Iris Rashap, Efrat Routledge, and Ophir Leshets for their major contribution in carrying out this research, including subjects recruitment and screening, and performing clinical, cognitive, and neural assessments. We also want to thank Naomi Fine and Michal Achituv for setting up the clinical aspect of the research. Last but not least, we extend our gratitude to all the participants of this study, who completed all the assessments at three different time-points after experiencing a traumatic event.

Publisher Copyright:
© 2021

Keywords

  • Attention mechanism
  • Deep learning
  • End-to-end neural network
  • PTSD symptom clusters
  • fMRI

ASJC Scopus subject areas

  • Neurology
  • Cognitive Neuroscience

Fingerprint

Dive into the research topics of 'Deep learning model of fMRI connectivity predicts PTSD symptom trajectories in recent trauma survivors'. Together they form a unique fingerprint.

Cite this