Corrigendum: Building an open source classifier for the neonatal EEG background: a systematic feature-based approach from expert scoring to clinical visualization.

[This corrects the article DOI: 10.3389/fnhum.2021.675154.].

Validating an SVM-based neonatal seizure detection algorithm for generalizability, non-inferiority and clinical efficacy.

Neonatal seizure detection algorithms (SDA) are approaching the benchmark of human expert annotation. Measures of algorithm generalizability and non-inferiority as well as measures of clinical efficacy are needed to assess the full scope of neonatal SDA performance. We validated our neonatal SDA on an independent data set of 28 neonates. Generalizability was tested by comparing the performance of the original training set (cross-validation) to its performance on the validation set. Non-inferiority was tested by assessing inter-observer agreement between combinations of SDA and two human expert annotations. Clinical efficacy was tested by comparing how the SDA and human experts quantified seizure burden and identified clinically significant periods of seizure activity in the EEG. Algorithm performance was consistent between training and validation sets with no significant worsening in AUC (p > 0.05, n = 28). SDA output was inferior to the annotation of the human expert, however, re-training with an increased diversity of data resulted in non-inferior performance (Δκ = 0.077, 95% CI: -0.002-0.232, n = 18). The SDA assessment of seizure burden had an accuracy ranging from 89 to 93%, and 87% for identifying periods of clinical interest. The proposed SDA is approaching human equivalence and provides a clinically relevant interpretation of the EEG.

Building an Open Source Classifier for the Neonatal EEG Background: A Systematic Feature-Based Approach From Expert Scoring to Clinical Visualization.

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.

Hybrid neonatal EEG seizure detection algorithms achieve the benchmark of visual interpretation of the human expert.

Neonatal EEG seizure detection algorithms (NSDAs) have an upper bound of performance related to the agreement between visual interpretation of human experts. No published algorithms have reported performance that has reached this upper bound. In this paper, we combined two recently developed NSDAs in order to improve detection performance. An outlier detection stage was also added to improve robustness in the presence of unseen data. A large database of EEG from 79 term infants labeled by three independent human experts was used to develop and test the sufficiency of the hybrid NSDA. The inter-observer agreement (IOA) between experts was high (κ = 0.757, 95%CI: 0.665-0.836, n=79). The area under the receiver operator characteristic of the NSDA compared to the consensus annotation of the human experts was 0.952 (95%CI: 0.0927-0.971). The IOA of seizure detection between the NSDA and human experts was not significantly less than the IOA among human experts (Δκ = 0.022, 95%CI: -0.20 to 0.072) and was further improved by increasing the minimum seizure duration from 10s to 30s (Δκ = -0.002, 95%CI: -0.073 to 0.055). Automated methods of neonatal EEG seizure detection have sufficient accuracy to replace human interpretation, potentially, providing reliable interpretations for clinicians in the neonatal intensive care unit.

Time-Varying EEG Correlations Improve Automated Neonatal Seizure Detection.

The aim of this study was to develop methods for detecting the nonstationary periodic characteristics of neonatal electroencephalographic (EEG) seizures by adapting estimates of the correlation both in the time (spike correlation; SC) and time-frequency domain (time-frequency correlation; TFC). These measures were incorporated into a seizure detection algorithm (SDA) based on a support vector machine to detect periods of seizure and nonseizure. The performance of these nonstationary correlation measures was evaluated using EEG recordings from 79 term neonates annotated by three human experts. The proposed measures were highly discriminative for seizure detection (median AUCSC : 0.933 IQR: 0.821-0.975, median AUCTFC : 0.883 IQR: 0.707-0.931). The resultant SDA applied to multi-channel recordings had a median AUC of 0.988 (IQR: 0.931-0.998) when compared to consensus annotations, outperformed two state-of-the-art SDAs (p < 0.001) and was noninferior to the human expert for 73/79 of neonates.

Neural mechanisms supporting evaluation of others' errors in real-life like conditions.

The ability to evaluate others' errors makes it possible to learn from their mistakes without the need for first-hand trial-and-error experiences. Here, we compared functional magnetic resonance imaging activation to self-committed errors during a computer game to a variety of errors committed by others during movie clips (e.g., figure skaters falling down and persons behaving inappropriately). While viewing errors by others there was activation in lateral and medial temporal lobe structures, posterior cingulate cortex, precuneus, and medial prefrontal cortex possibly reflecting simulation and storing for future use alternative action sequences that could have led to successful behaviors. During both self- and other-committed errors activation was seen in the striatum, temporoparietal junction, and inferior frontal gyrus. These areas may be components of a generic error processing mechanism. The ecological validity of the stimuli seemed to matter, since we largely failed to see activations when subjects observed errors by another player in the computer game, as opposed to observing errors in the rich real-life like human behaviors depicted in the movie clips.