A Comparison of Two Deep Learning Approaches to Distinguish Functional Dissociative from Epileptic Seizures Using Event Videos
Our findings demonstrate the superiority of CNN over pose-estimation models to differentiate between motor ES and FDS using video alone. Although future studies are needed, these models hold potential as adjunct diagnostic tools by enabling rapid, objective seizure evaluations without immediate neurologist involvement.
Authors
- Madeline Fields (ORCID: https://orcid.org/0000-0003-0661-4153)
- Benjamin Scott Glicksberg (ORCID: https://orcid.org/0000-0003-4515-8090)
- Girish N. Nadkarni (ORCID: https://orcid.org/0000-0001-6319-4314)
- Ilana Lefkovitz (ORCID: https://orcid.org/0000-0002-8724-3798)
- Andy Ho Wing Chan (ORCID: https://orcid.org/0009-0002-5055-9470)
- Felix Richter (ORCID: https://orcid.org/0000-0003-3429-9621)
- Lara Marcuse (ORCID: https://orcid.org/0000-0002-1494-7241)
- Benjamin R. Kummer (ORCID: https://orcid.org/0000-0002-1413-8014)
- Nathalie Jetté (ORCID: https://orcid.org/0000-0003-1351-5866)
- Megan MacKenzie
- Stefano Malerba
- Alec Gleason
- Mark Dakov
- Jacky Cheung
- Jiyoon Hwang
- Asala N Erekat
Institutions
- Albert Einstein College of Medicine (US)
- Children's Hospital of Philadelphia (US)
- University of Calgary (CA)
- Columbia University Irving Medical Center (US)
- O'Brien Institute (AU)
- Icahn School of Medicine at Mount Sinai (US)
Publication Details
- Journal
- medRxiv
- Published
- 2025-12-19
- DOI
- https://doi.org/10.64898/2025.12.18.25342568
- Primary Topic
- Psychosomatic Disorders and Their Treatments
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Regeneron Pharmaceuticals