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

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.

The suppression curve as a quantitative approach for measuring brain maturation in preterm infants.

OBJECTIVES: We apply the suppression curve (SC) as an automated approach to describe the maturational change in EEG discontinuity in preterm infants. This method allows to define normative values of interburst intervals (IBIs) at different postmenstrual ages (PMA). METHODS: Ninety-two multichannel EEG recordings from 25 preterm infants (born ⩽32weeks) with normal developmental outcome at 9months, were first analysed using the Line Length method, an established method for burst detection. Subsequently, the SC was defined as the 'level of EEG discontinuity'. The mean and the standard deviation of the SC, as well as the IBIs from each recording were calculated and correlated with PMA. RESULTS: Over the course of development, there is a decrease in EEG discontinuity with a strong linear correlation between the mean SC and PMA till 34weeks. From 30weeks PMA, differences between discontinuous and continuous EEG become smaller, which is reflected by the decrease of the standard deviation of the SC. IBIs are found to have a significant correlation with PMA. CONCLUSIONS: Automated detection of individual maturational changes in EEG discontinuity is possible with the SC. These changes include more continuous tracing, less amplitude differences and shorter suppression periods, reflecting development of the vigilance states. SIGNIFICANCE: The suppression curve facilitates automated assessment of EEG maturation. Clinical applicability is straight forward since values for IBIs according to PMA are generated automatically.

Early development of synchrony in cortical activations in the human.

Early intermittent cortical activity is thought to play a crucial role in the growth of neuronal network development, and large scale brain networks are known to provide the basis for higher brain functions. Yet, the early development of the large scale synchrony in cortical activations is unknown. Here, we tested the hypothesis that the early intermittent cortical activations seen in the human scalp EEG show a clear developmental course during the last trimester of pregnancy, the period of intensive growth of cortico-cortical connections. We recorded scalp EEG from altogether 22 premature infants at post-menstrual age between 30 and 44 weeks, and the early cortical synchrony was quantified using recently introduced activation synchrony index (ASI). The developmental correlations of ASI were computed for individual EEG signals as well as anatomically and mathematically defined spatial subgroups. We report two main findings. First, we observed a robust and statistically significant increase in ASI in all cortical areas. Second, there were significant spatial gradients in the synchrony in fronto-occipital and left-to-right directions. These findings provide evidence that early cortical activity is increasingly synchronized across the neocortex. The ASI-based metrics introduced in our work allow direct translational comparison to in vivo animal models, as well as hold promise for implementation as a functional developmental biomarker in future research on human neonates.

Event related potentials during attention tasks in VLBW children with and without attention deficit disorder.

OBJECTIVE: Children born prematurely have a higher incidence of attention deficit disorder with or without hyperactivity. We have used visual event related potentials to study possible brain dysfunctions that could explain this higher incidence. METHODS: Very low birth weight (VLBW) children with and without AD/HD and term born children with and without AD/HD, were matched for IQ, age and socio-economic status (n=41, mean age 104 months). A visual oddball paradigm, consisting of target and non-target stimuli, was used with analysis of response times, error scores, N200, P300 and a P500 component. RESULTS: AD/HD children responded slower (F (1,38)=11.20, p<0.002); more varied (F (1,38)=21.77, p<0.000) and made more commission and omission errors (Kruskal-Wallis p<0.000). Non-target N200 was increased in amplitude (F (1.39)=4.01, p=0.05) with a wide anterior topography in children with AD/HD. The late positivity (P500) was decreased over central leads in children with AD/HD during the non-target stimuli (F (3,75)=3.00, p<0.036). No differences could be found in latency, amplitude or topography between VLBW children with AD/HD and term born children with AD/HD. CONCLUSIONS: Prematurity does not induce specific attentional brain dysfunction or maturation delays in stimulus processing during cognitive tasks. Other factors should be investigated to explain the higher incidence of AD/HD in VLBW children.