Performance Reassessment of a Real-time Seizure-detection Algorithm on Long ECoG Series

Purpose: Automated seizure detection and blockage requires highly sensitive and specific algorithms. This study reassessed the performance of an algorithm by using a more extensive database than that of a previous study and its suitability for safety/efficacy closed‐loop studies to block seizures in...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Epilepsia (Copenhagen) Jg. 43; H. 12; S. 1522 - 1535
Hauptverfasser: Osorio, Ivan, Frei, Mark G., Giftakis, Jon, Peters, Tom, Ingram, Jeff, Turnbull, Mary, Herzog, Michele, Rise, Mark T., Schaffner, Scott, Wennberg, Richard A., Walczak, Thaddeus S., Risinger, Michael W., Ajmone‐Marsan, Cosimo
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Boston, MA, USA Blackwell Science Inc 01.12.2002
Blackwell
Schlagworte:
Adolescent
Adult
Algorithm
Algorithms
Biological and medical sciences
Cerebral Cortex - physiopathology
Detection
Diagnosis, Computer-Assisted
Electrodes, Implanted
Electrodiagnosis. Electric activity recording
Electroencephalography
Epilepsies, Partial - diagnosis
Epilepsies, Partial - physiopathology
Epilepsy, Complex Partial - diagnosis
Epilepsy, Complex Partial - physiopathology
Epilepsy, Tonic-Clonic - diagnosis
Epilepsy, Tonic-Clonic - physiopathology
Evoked Potentials - physiology
Female
Fourier Analysis
Humans
Investigative techniques, diagnostic techniques (general aspects)
Male
Medical sciences
Middle Aged
Monitoring, Ambulatory
Nervous system
Observer Variation
Reaction Time - physiology
Real-time
Seizure
Sensitivity and Specificity
Signal Processing, Computer-Assisted
Warning
Human
Electrodiagnosis
Convulsion
Real-time-Seizure-Detection- Algorithm-Warning
Neurological disorder
Medical screening
Real time
Algorithm
Electrocorticography
ISSN:0013-9580, 1528-1167
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Purpose: Automated seizure detection and blockage requires highly sensitive and specific algorithms. This study reassessed the performance of an algorithm by using a more extensive database than that of a previous study and its suitability for safety/efficacy closed‐loop studies to block seizures in humans. Methods: Up to eight electrocorticography (EcoG) channels from 15 subjects were analyzed off‐line. Visual and computerized analyses of the data were performed by different (blinded) investigators. Independent visual analysis also was performed for clinical seizures and for detections identified only by the algorithm. The following were computed: FP rate, number of FNs, latency to automated detection, warning rate for clinical onset and warning times, seizure duration/intensity, and interrater agreement. Adaptations to improve performance were performed when indicated. Results: Fourteen subjects met inclusion criteria. Generic algorithm “relative sensitivity” for clinical seizures was 100%; two undetected subclinical seizures and two unclassified seizures were captured after adaptation. FPs/day were zero in seven and fewer than one in an additional three subjects. Adaptations for four subjects with greater than 1 FP/day (7.7–66.6/day) reduced the rate to 0 in one subject and to fewer than five FP/day (1.7–4.2/day) in the remainder. Generic latency to automated detection was <5 s in eight of 13 subjects, and in 12 of 13 after adaptation. Detections provided warning of clinical onset in three of four subjects in whom it always followed electrographic onset, and in four of four after adaptation. Interrater agreement was low for FPs and EDs. Conclusions: The generic algorithm demonstrated high sensitivity, specificity, and speed, characteristics further enhanced by adaptation. This algorithm is well suited for seizure detection/warning and use in safety/efficacy closed‐loop therapy studies.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0013-9580
1528-1167
DOI:10.1046/j.1528-1157.2002.11102.x