Discriminative and Generative Classification Techniques Applied to Automated Neonatal Seizure Detection

• Published in: IEEE journal of biomedical and health informatics Vol. 17; no. 2; pp. 297 - 304
• Main Authors: Thomas, E. M., Temko, A., Marnane, W. P., Boylan, G. B., Lightbody, G.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01-03-2013; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Automated; Automation; Classification; Classifier fusion; Classifiers; Databases, Factual; Detectors; Diagnosis, Computer-Assisted - methods; Electroencephalography; Electroencephalography - classification; Epilepsy - diagnosis; Epilepsy - physiopathology; Feature extraction; Frequency domain analysis; Humans; Infant, Newborn; Infant, Newborn, Diseases - diagnosis; Infant, Newborn, Diseases - physiopathology; machine learning; neonatal seizure detection; Nonlinearity; Pediatrics; Seizing; Studies; Support Vector Machine; Support vector machines; Tasks; Training data
• ISSN: 2168-2194; 2168-2208
• DOI: 10.1109/JBHI.2012.2237035

A number of automated neonatal seizure detectors have been proposed in recent years. However, there exists a large variability in the morphology of seizure and background patterns, both across patients and over time. This has resulted in relatively poor performance from systems which have been tested over large datasets. Here, the benefits of employing a pattern recognition approach are discussed. Such a system may use numerous features paired with nonlinear classifiers. In particular, two types of nonlinear classifiers are contrasted for the task. Additionally, it is shown that the proposed architecture allows for efficient classifier combination which improves the performance of the algorithm. The resulting automated detector is shown to achieve field leading performance. A particular strength of the proposed algorithm is the performance of the algorithm when very low false detections are required, at 0.25 false detections per hour, the system is able to detect 75.4% of the seizure events.