Automated neonatal seizure detection mimicking a human observer reading EEG

• Published in: Clinical neurophysiology Vol. 119; no. 11; pp. 2447 - 2454
• Main Authors: Deburchgraeve, W, Cherian, P.J, De Vos, M, Swarte, R.M, Blok, J.H, Visser, G.H, Govaert, P, Van Huffel, S
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ireland Ltd 01.11.2008; Elsevier
• Subjects: Algorithm; Algorithms; Biological and medical sciences; Case-Control Studies; Diagnosis, Computer-Assisted - methods; Electrodiagnosis. Electric activity recording; Electroencephalography (EEG); Electroencephalography - methods; False Positive Reactions; Headache. Facial pains. Syncopes. Epilepsia. Intracranial hypertension. Brain oedema. Cerebral palsy; Humans; Infant; Infant, Newborn; Infant, Newborn, Diseases - diagnosis; Investigative techniques, diagnostic techniques (general aspects); Medical sciences; Nervous system; Nervous system (semeiology, syndromes); Neurology; Newborn; Predictive Value of Tests; Seizure detection; Seizures - classification; Seizures - diagnosis; Sensitivity and Specificity; Newborn; Electroencephalography (EEG); Seizure detection; Algorithm; Human; Evaluation; Nervous system diseases; Neonatal; Epilepsy; Electrophysiology; Infant; Electroencephalography; Low frequency; Cerebral disorder; Electrodiagnosis; Sensitivity; Convulsion; Central nervous system disease; Observer; Electroencephalography (EEC); Predictive value; Neurological disorder; Monitoring
• ISSN: 1388-2457; 1872-8952
• DOI: 10.1016/j.clinph.2008.07.281

Abstract Objective The description and evaluation of a novel patient-independent seizure detection for the EEG of the newborn term infant. Methods We identified characteristics of neonatal seizures by which a human observer is able to detect them. Neonatal seizures were divided into two types. For each type, a fully automated detection algorithm was developed based on the identified human observer characteristics. The first algorithm analyzes the correlation between high-energetic segments of the EEG. The second detects increases in low-frequency activity (<8 Hz) with high autocorrelation. Results The complete algorithm was tested on multi-channel EEG recordings of 21 patients with and 5 patients without electrographic seizures, totaling 217 h of EEG. Sensitivity of the combined algorithms was found to be 88%, Positive Predictive Value (PPV) 75% and the false positive rate 0.66 per hour. Conclusions Our approach to separate neonatal seizures into two types yields a high sensitivity combined with a good PPV and much lower false positive rate than previously published algorithms. Significance The proposed algorithm significantly improves neonatal seizure detection and monitoring.