Automated analysis and detection of epileptic seizures in video recordings using artificial intelligence

Pragya Rai; Andrew Knight; Matias Hiillos; Csaba Kertész; Elizabeth Morales; Daniella Terney; Sidsel Armand Larsen; Tim Østerkjerhuus; Jukka Peltola; Sándor Beniczky

doi:10.3389/fninf.2024.1324981

Automated analysis and detection of epileptic seizures in video recordings using artificial intelligence

Front Neuroinform. 2024 Mar 15:18:1324981. doi: 10.3389/fninf.2024.1324981. eCollection 2024.

Authors

Pragya Rai¹, Andrew Knight^{1

2}, Matias Hiillos¹, Csaba Kertész¹, Elizabeth Morales¹, Daniella Terney³, Sidsel Armand Larsen³, Tim Østerkjerhuus⁴, Jukka Peltola^{2

5}, Sándor Beniczky^{3

4

6}

Affiliations

¹ Neuro Event Labs, Tampere, Finland.
² Department of Medicine and Health Technology, Tampere University, Tampere, Finland.
³ Department of Clinical Neurophysiology, Danish Epilepsy Centre, Dianalund, Denmark.
⁴ Department of Clinical Neurophysiology, Aarhus University Hospital, Aarhus, Denmark.
⁵ Department of Neurology, Tampere University Hospital, Tampere, Finland.
⁶ Department of Clinical Medicine, Aarhus University, Aarhus, Denmark.

Abstract

Introduction: Automated seizure detection promises to aid in the prevention of SUDEP and improve the quality of care by assisting in epilepsy diagnosis and treatment adjustment.

Methods: In this phase 2 exploratory study, the performance of a contactless, marker-free, video-based motor seizure detection system is assessed, considering video recordings of patients (age 0-80 years), in terms of sensitivity, specificity, and Receiver Operating Characteristic (ROC) curves, with respect to video-electroencephalographic monitoring (VEM) as the medical gold standard. Detection performances of five categories of motor epileptic seizures (tonic-clonic, hyperkinetic, tonic, unclassified motor, automatisms) and psychogenic non-epileptic seizures (PNES) with a motor behavioral component lasting for >10 s were assessed independently at different detection thresholds (rather than as a categorical classification problem). A total of 230 patients were recruited in the study, of which 334 in-scope (>10 s) motor seizures (out of 1,114 total seizures) were identified by VEM reported from 81 patients. We analyzed both daytime and nocturnal recordings. The control threshold was evaluated at a range of values to compare the sensitivity (n = 81 subjects with seizures) and false detection rate (FDR) (n = all 230 subjects).

Results: At optimal thresholds, the performance of seizure groups in terms of sensitivity (CI) and FDR/h (CI): tonic-clonic- 95.2% (82.4, 100%); 0.09 (0.077, 0.103), hyperkinetic- 92.9% (68.5, 98.7%); 0.64 (0.59, 0.69), tonic- 78.3% (64.4, 87.7%); 5.87 (5.51, 6.23), automatism- 86.7% (73.5, 97.7%); 3.34 (3.12, 3.58), unclassified motor seizures- 78% (65.4, 90.4%); 4.81 (4.50, 5.14), and PNES- 97.7% (97.7, 100%); 1.73 (1.61, 1.86). A generic threshold recommended for all motor seizures under study asserted 88% sensitivity and 6.48 FDR/h.

Discussion: These results indicate an achievable performance for major motor seizure detection that is clinically applicable for use as a seizure screening solution in diagnostic workflows.

Keywords: artificial intelligence; biomarkers; epilepsy; motor seizures; seizure detection; signal processing.

Grants and funding

The author(s) declare that financial support was received for the research, authorship, and/or publication of this article. Neuro Event Labs, the company that provided the equipment and technology used in the study, is the funder of the research. It will also be covering the article publishing charges for the manuscript.