Search

Neonatal brain monitoring in the neonatal intensive care units (NICU) requires a continuous review of the spontaneous cortical activity, i.e., the electroencephalograph (EEG) background activity. This needs development of bedside methods for an automated assessment of the EEG background activity. In this paper, we present development of the key components of a neonatal EEG background classifier, starting from the visual background scoring to classifier design, and finally to possible bedside visualization of the classifier results. A dataset with 13,200 5-minute EEG epochs (8–16 channels) from 27 infants with birth asphyxia was used for classifier training after scoring by two independent experts. We tested three classifier designs based on 98 computational features, and their performance was assessed with respect to scoring system, pre- and post-processing of labels and outputs, choice of channels, and visualization in monitor displays. The optimal solution achieved an overall classification accuracy of 97% with a range across subjects of 81–100%. We identified a set of 23 features that make the classifier highly robust to the choice of channels and missing data due to artefact rejection. Our results showed that an automated bedside classifier of EEG background is achievable, and we publish the full classifier algorithm to allow further clinical replication and validation studies.

Objective: To evaluate the reliability of recording cortical somatosensory evoked potentials (SEPs) in asphyxiated newborns using the 4-electrode setup applied in routine long-term amplitude-integrated EEG (aEEG) brain monitoring and to assess the number of averages needed for reliably detecting the cortical responses. Methods: We evaluated median nerve SEPs in 50 asphyxiated full-term newborns. The SEP interpretation (present or absent) from the original recordings with 21-electrodes and approximately 600 trials served as the reference. This was compared to SEP classification (absent, present, or unreliable) based on a reduced (300 or 150) number of averages, and to classification based on only four electrodes (F3, P3, F4, P4). Results: Compared to the original classification, cortical SEPs were uniformly interpreted as present or absent in all 50 newborns with the 4-electrode setup and 600 averages. Reducing number of averages to 300 still resulted in correct SEP interpretation in 49/50 newborns with 21-electrode setup, and 46/50 newborns with 4-electrode setup. Conclusions: Evaluation of early cortical neonatal SEPs is reliable from the 4-electrode setup commonly used in aEEG monitoring. SEP is discernible in most newborns with 300 averages. Significance: Adding SEP into routine aEEG monitoring offers an additional tool for early neonatal neurophysiological evaluation. Keywords: Amplitude-integrated electroencephalography (aEEG), Asphyxia, Brain monitoring, Electroencephalography (EEG), Newborn, Somatosensory evoked potentials (SEPs)

Objective: Sharing medical data between institutions is difficult in practice due to data protection laws and official procedures within institutions. Therefore, most existing algorithms are trained on relatively small electroencephalogram (EEG) data sets which is likely to be detrimental to prediction accuracy. In this work, we simulate a case when the data can not be shared by splitting the publicly available data set into disjoint sets representing data in individual institutions. Methods and procedures: We propose to train a (local) detector in each institution and aggregate their individual predictions into one final prediction. Four aggregation schemes are compared, namely, the majority vote, the mean, the weighted mean and the Dawid-Skene method. The method was validated on an independent data set using only a subset of EEG channels. Results: The ensemble reaches accuracy comparable to a single detector trained on all the data when sufficient amount of data is available in each institution. Conclusion: The weighted mean aggregation scheme showed best performance, it was only marginally outperformed by the Dawid–Skene method when local detectors approach performance of a single detector trained on all available data. Clinical impact: Ensemble learning allows training of reliable algorithms for neonatal EEG analysis without a need to share the potentially sensitive EEG data between institutions.