Improved multi-stage neonatal seizure detection using a heuristic classifier and a data-driven post-processor

Abstract

Objective: After identifying the most seizure-relevant characteristics by a previously developed heuristic classifier, a data-driven post-processor using a novel set of features is applied to improve the performance.

Methods: The main characteristics of the outputs of the heuristic algorithm are extracted by five sets of features including synchronization, evolution, retention, segment, and signal features. Then, a support vector machine and a decision making layer remove the falsely detected segments.

Results: Four datasets including 71 neonates (1023h, 3493 seizures) recorded in two different university hospitals, are used to train and test the algorithm without removing the dubious seizures. The heuristic method resulted in a false alarm rate of 3.81 per hour and good detection rate of 88% on the entire test databases. The post-processor, effectively reduces the false alarm rate by 34% while the good detection rate decreases by 2%.

Conclusion: This post-processing technique improves the performance of the heuristic algorithm. The structure of this post-processor is generic, improves our understanding of the core visually determined EEG features of neonatal seizures and is applicable for other neonatal seizure detectors.

Significance: The post-processor significantly decreases the false alarm rate at the expense of a small reduction of the good detection rate.

Keywords: Automated neonatal seizure detection; Hypoxic-ischemic encephalopathy; Machine learning; Support vector machines.