Automatic Detection of Childhood Absence Epilepsy Seizures: Toward a Monitoring Device

• Published in: Pediatric neurology Vol. 46; no. 5; pp. 287 - 292
• Main Authors: Duun-Henriksen, Jonas, MSc, Madsen, Rasmus E., PhD, Remvig, Line S., MSc, Thomsen, Carsten E., PhD, Sorensen, Helge B.D., PhD, Kjaer, Troels W., MD, PhD
• Format: Journal Article
• Language: English
• Published: New York, NY Elsevier Inc 01.05.2012; Elsevier
• Subjects: Algorithms; Antiepileptic agents; Biological and medical sciences; Brain Mapping; Brain Waves - physiology; Child; Child, Preschool; Children; Diagnosis, Computer-Assisted; EEG; Electroencephalography; Epilepsy; Epilepsy, Absence - diagnosis; Epilepsy, Absence - physiopathology; Female; Headache. Facial pains. Syncopes. Epilepsia. Intracranial hypertension. Brain oedema. Cerebral palsy; Humans; Male; Medical sciences; Monitoring, Physiologic; Nervous system (semeiology, syndromes); Neurology; Pediatrics; Scalp; Seizures; Sensitivity and Specificity; Side effects; Time Factors; Human; Nervous system diseases; Convulsion; Epilepsy; Central nervous system disease; Neurological disorder; Medical screening; Child; Monitoring; Cerebral disorder
• ISSN: 0887-8994; 1873-5150
• DOI: 10.1016/j.pediatrneurol.2012.02.018

Abstract Automatic detections of paroxysms in patients with childhood absence epilepsy have been neglected for several years. We acquire reliable detections using only a single-channel brainwave monitor, allowing for unobtrusive monitoring of antiepileptic drug effects. Ultimately we seek to obtain optimal long-term prognoses, balancing antiepileptic effects and side effects. The electroencephalographic appearance of paroxysms in childhood absence epilepsy is fairly homogeneous, making it feasible to develop patient-independent automatic detection. We implemented a state-of-the-art algorithm to investigate the performance of paroxysm detection. Using only a single scalp electroencephalogram channel from 20 patients with a total of 125 paroxysms >2 seconds, 97.2% of paroxysms could be detected with no false detections. This result leads us to recommend further investigations of tiny, one-channel electroencephalogram systems in an ambulatory setting.