Name: DDESVSFS: a screening tool for the differential diagnosis of epileptic versus functional seizures
Published: July 9, 2026
License: https://github.com/bdsp-core/bdsp-license-and-dua

Software Credentialed Access

Nicholas J. Janocko , Jin Jing , Ziwei Fan , Diane L. Teagarden , Hannah K. Villarreal , Matthew L. Morton , Olivia Groover , David W. Loring , Daniel L. Drane , M. Brandon Westover , Ioannis Karakis

Published: July 9, 2026. Version: 1.0.0

When using this resource, please cite: (show more options)
Janocko, N. J., Jing, J., Fan, Z., Teagarden, D. L., Villarreal, H. K., Morton, M. L., Groover, O., Loring, D. W., Drane, D. L., Westover, M. B., & Karakis, I. (2026). DDESVSFS: a screening tool for the differential diagnosis of epileptic versus functional seizures (version 1.0.0). Brain Data Science Platform. https://doi.org/10.60508/yyev-cx22.

MLA	Janocko, Nicholas J., et al. "DDESVSFS: a screening tool for the differential diagnosis of epileptic versus functional seizures" (version 1.0.0). Brain Data Science Platform (2026), https://doi.org/10.60508/yyev-cx22.
APA	Janocko, N. J., Jing, J., Fan, Z., Teagarden, D. L., Villarreal, H. K., Morton, M. L., Groover, O., Loring, D. W., Drane, D. L., Westover, M. B., & Karakis, I. (2026). DDESVSFS: a screening tool for the differential diagnosis of epileptic versus functional seizures (version 1.0.0). Brain Data Science Platform. https://doi.org/10.60508/yyev-cx22.
Chicago	Janocko, Nicholas J., Jing, Jin, Fan, Ziwei, Teagarden, Diane L., Villarreal, Hannah K., Morton, Matthew L., Groover, Olivia, Loring, David W., Drane, Daniel L., Westover, M. Brandon, and Ioannis Karakis. "DDESVSFS: a screening tool for the differential diagnosis of epileptic versus functional seizures" (version 1.0.0). Brain Data Science Platform (2026). https://doi.org/10.60508/yyev-cx22.
Harvard	Janocko, N. J., Jing, J., Fan, Z., Teagarden, D. L., Villarreal, H. K., Morton, M. L., Groover, O., Loring, D. W., Drane, D. L., Westover, M. B., and Karakis, I. (2026) 'DDESVSFS: a screening tool for the differential diagnosis of epileptic versus functional seizures' (version 1.0.0), Brain Data Science Platform. Available at: https://doi.org/10.60508/yyev-cx22.
Vancouver	Janocko N J, Jing J, Fan Z, Teagarden D L, Villarreal H K, Morton M L, Groover O, Loring D W, Drane D L, Westover M B, Karakis I. DDESVSFS: a screening tool for the differential diagnosis of epileptic versus functional seizures (version 1.0.0). Brain Data Science Platform. 2026. Available from: https://doi.org/10.60508/yyev-cx22.

Abstract

Objective. To develop a simple, rapid questionnaire-based screening tool to help differentiate epileptic seizures from functional (psychogenic non-epileptic) seizures.

Methods. In 208 patients with a confirmed diagnosis, structured intake questionnaire and clinical variables were related to the epileptic-vs-functional outcome using multivariable logistic regression with nested cross-validated LASSO feature selection; an integer point score (DDESVSFS) was derived.

Results. The model discriminated epileptic from functional seizures with AUC 0.93 (95% CI 0.87-0.96), with an operating point of ~95% sensitivity and ~70% specificity and good calibration.

Conclusion. DDESVSFS is a simple, well-calibrated screening tool. This project releases the code and de-identified data to reproduce the analysis.

Background

Distinguishing epileptic from functional (psychogenic non-epileptic) seizures is clinically challenging and often delayed. A simple validated screening tool from a rapid structured questionnaire can aid triage.

Software Description

MATLAB scripts (feature selection, ROC/calibration, score system, odds-ratio tables) and the de-identified feature table pnespredictiondeidentified.xlsx (208 x 24; ptid + questionnaire/clinical features; no PHI), plus the fitted model featureSelected.mat.

Technical Implementation

In 208 patients with a confirmed diagnosis, questionnaire and clinical variables were related to the epileptic-vs-functional outcome using multivariable logistic regression with nested cross-validated LASSO feature selection; an integer DDESVSFS point score was derived, and ROC/calibration assessed.

Installation and Requirements

MATLAB R2016+ with the Statistics and Machine Learning Toolbox. Run main_ROC_and_Calibration from the repo root. See REPRODUCE.md and DATA_SOURCE.md.

Usage Notes

main_ROC_and_Calibration reproduces AUC 0.929 [0.875-0.961]; step1_nestedCVlasso re-runs feature selection; main_ScoreSystem builds the integer DDESVSFS score.

Release Notes

First public release: code + de-identified data + reproduction docs.

Ethics

De-identified data collected under IRB approval at Emory University.

Acknowledgements

Emory University epilepsy program (I. Karakis) and MGH (J. Jing, M.B. Westover).

Conflicts of Interest

See the associated publication (Epilepsy Res 2021;171:106563).

Access

Access Policy:
Only credentialed users who sign the DUA can access the files.

License (for files):
BDSP Credentialed Health Data License 1.5.0

Data Use Agreement:
BDSP Credentialed Health Data Use Agreement

Required training:

Discovery

DOI:
https://doi.org/10.60508/yyev-cx22

Corresponding Author

You must be logged in to view the contact information.

Files

This is a restricted-access resource. To access the files, you must fulfill all of the following requirements:

be a credentialed user
sign the data use agreement for the project

DDESVSFS: a screening tool for the differential diagnosis of epileptic versus functional seizures

Cite