You are here

  • Home
  • Online First
  • Machine learning classification of functional neurological disorder using structural brain MRI features

Article Text

Article menu
Download PDFPDF
Neuropsychiatry
Original research
Machine learning classification of functional neurological disorder using structural brain MRI features
  1. Christiana Westlin1,2,3,
  2. Andrew J Guthrie1,2,
  3. Sara Paredes-Echeverri1,2,
  4. Julie Maggio1,4,
  5. Sara Finkelstein1,
  6. Ellen Godena1,
  7. Daniel Millstein1,3,
  8. Julie MacLean1,5,
  9. Jessica Ranford1,5,
  10. Jennifer Freeburn1,6,
  11. Caitlin Adams1,3,
  12. Christopher Stephen1,7,
  13. Ibai Diez1,2,8,
  14. David L Perez1,2,3
  1. 1Functional Neurological Disorder Research Group, Division of Behavioral Neurology & Integrated Brain Medicine, Department of Neurology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
  2. 2Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
  3. 3Department of Psychiatry, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
  4. 4Department of Physical Therapy, Massachusetts General Hospital, Boston, Massachusetts, USA
  5. 5Department of Occupational Therapy, Massachusetts General Hospital, Boston, Massachusetts, USA
  6. 6Department of Speech, Language, and Swallowing Disorders, Massachusetts General Hospital, Boston, Massachusetts, USA
  7. 7Movement Disorders Division, Department of Neurology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
  8. 8Gordon Center for Medical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
  1. Correspondence to Dr David L Perez; dlperez{at}nmr.mgh.harvard.edu; Dr Christiana Westlin; cwestlin{at}mgh.harvard.edu

Abstract

Background Brain imaging studies investigating grey matter in functional neurological disorder (FND) have used univariate approaches to report group-level differences compared with healthy controls (HCs). However, these findings have limited translatability because they do not differentiate patients from controls at the individual-level.

Methods 183 participants were prospectively recruited across three groups: 61 patients with mixed FND (FND-mixed), 61 age-matched and sex-matched HCs and 61 age, sex, depression and anxiety-matched psychiatric controls (PCs). Radial basis function support vector machine classifiers with cross-validation were used to distinguish individuals with FND from HCs and PCs using 134 FreeSurfer-derived grey matter MRI features.

Results Patients with FND-mixed were differentiated from HCs with an accuracy of 0.66 (p=0.005; area under the receiving operating characteristic (AUROC)=0.74); this sample was also distinguished from PCs with an accuracy of 0.60 (p=0.038; AUROC=0.56). When focusing on the functional motor disorder subtype (FND-motor, n=46), a classifier robustly differentiated these patients from HCs (accuracy=0.72; p=0.002; AUROC=0.80). FND-motor could not be distinguished from PCs, and the functional seizures subtype (n=23) could not be classified against either control group. Important regions contributing to statistically significant multivariate classifications included the cingulate gyrus, hippocampal subfields and amygdalar nuclei. Correctly versus incorrectly classified participants did not differ across a range of tested psychometric variables.

Conclusions These findings underscore the interconnection of brain structure and function in the pathophysiology of FND and demonstrate the feasibility of using structural MRI to classify the disorder. Out-of-sample replication and larger-scale classifier efforts incorporating psychiatric and neurological controls are needed.

  • functional neurological disorder
  • MRI
  • movement disorders

Data availability statement

Data are available on reasonable request.

https://doi.org/10.1136/jnnp-2024-333499

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    Data availability statement

    Data are available on reasonable request.

    View Full Text

    Footnotes

    • CW and AJG contributed equally.

    • Contributors CW, AJG, ID and DLP designed the study. All authors were involved in data collection. CW, AJG, ID and DLP conceptualised the analyses. CW and AJG performed the analyses. ID and DLP supervised the analyses. CW, AJG and DLP drafted the manuscript. All authors critically appraised and interpreted the results and revised the manuscript. DLP is the guarantor of the study and accepts full responsibility for the work and the conduct of the study, had access to the data and controlled the decision to publish.

    • Funding This project was supported by NIMH R01MH125802 and K23MH111983 grants.

    • Competing interests DLP has received honoraria for continuing medical education lectures in FND; royalties from Springer for a functional movement disorder textbook and honoraria from Elsevier for a functional neurological disorder textbook; is on the editorial boards of Brain and Behavior (paid), Epilepsy & Behavior, The Journal of Neuropsychiatry and Clinical Neurosciences and Cognitive and Behavioral Neurology; has previously received funding from the Sidney R. Baer Jr. Foundation unrelated to this work and is on the FND Society Board, American Neuropsychiatric Association Advisory Council and the FND Hope International Medical Advisory Board. All other authors report no conflicts of interest/disclosures.

    • Provenance and peer review Not commissioned; externally peer reviewed.

    • Supplemental material This content has been supplied by the author(s). It has not been vetted by BMJ Publishing Group Limited (BMJ) and may not have been peer-reviewed. Any opinions or recommendations discussed are solely those of the author(s) and are not endorsed by BMJ. BMJ disclaims all liability and responsibility arising from any reliance placed on the content. Where the content includes any translated material, BMJ does not warrant the accuracy and reliability of the translations (including but not limited to local regulations, clinical guidelines, terminology, drug names and drug dosages), and is not responsible for any error and/or omissions arising from translation and adaptation or otherwise.