Automatic Detection of Epileptic Seizures in Neonatal Intensive Care Units Through EEG, ECG and Video Recordings: A Survey

Abstract

In Neonatal Intensive Care Units (NICUs), the early detection of neonatal seizures is of utmost importance for a timely, effective and efficient clinical intervention. The continuous video electroencephalogram (v-EEG) is the gold standard for monitoring neonatal seizures, but it requires specialized equipment and expert staff available 24/24h. The purpose of this study is to present an overview of the main Neonatal Seizure Detection (NSD) systems developed during the last ten years that implement Artificial Intelligence techniques to detect and report the temporal occurrence of neonatal seizures. Expert systems based on the analysis of EEG, ECG and video recordings are investigated, and their usefulness as support tools for the medical staff in detecting and diagnosing neonatal seizures in NICUs is evaluated. EEGbased NSD systems show better performance than systems based on other signals. Recently ECG analysis, particularly the related HRV analysis, seems to be a promising marker of brain damage. Moreover, video analysis could be helpful to identify inconspicuous but pathological movements. This study highlights possible future developments of the NSD systems: a multimodal approach that exploits and combines the results of the EEG, ECG and video approaches and a system able to automatically characterize etiologies might provide additional support to clinicians in seizures diagnosis.

Analysis of Brain-Heart Interactions in newborns with and without seizures using the Convergent Cross Mapping approach

“…Thus, our results suggest that in patients with seizure events, the heart dynamics could be altered by the CNS activity but not the opposite. It agrees with [7,9,13]: seizures may alter the ANS dynamics and not only the CNS one. The CCM approach seems to catch differences in BHIs in newborns with and without seizures.…”

“…However, our findings suggest that ANS and HRV analysis are strictly related to seizure events in newborns. This information could better understand these pathological events and support neonatal seizure detection methods [9,10,19].…”

“…They could focus on differences between interictal and ictal periods [20] or between pre-ictal and post-ictal periods [8]. Others could investigate BHIs among different aetiologies [7,9]; or how BHI varies after pharmacological treatments [6].…”

“…However, there is still a lack of information about the interactions between CNS and ANS during or close to several seizure events [6], such as neonatal seizures, the most common neurological emergency in the first days of life of the newborn [7]. According to a recent ILAE position paper [7], neonatal seizures deserve a particular classification among seizure events, both for the intrinsic electroclinical characteristics of the newborn (when compared to the adult [8]), and their aetiologies [9]. Seizure detection is tricky and timeconsuming, and delayed treatment can negatively affect neurodevelopment [7,10].…”