A perinatal stress calculator for the neonatal intensive care unit: an unobtrusive approach

A multi-task and multi-channel convolutional neural network for semi-supervised neonatal artefact detection

Objective. Automated artefact detection in the neonatal electroencephalogram (EEG) is crucial for reliable automated EEG analysis, but limited availability of expert artefact annotations challenges the development of deep learning models for artefact detection. This paper proposes a semi-supervised deep learning approach for artefact detection in neonatal EEG that requires few labelled data by training a multi-task convolutional neural network (CNN).Approach. An unsupervised and a supervised objective were jointly optimised by combining an autoencoder and an artefact classifier in one multi-output model that processes multi-channel EEG inputs. The proposed semi-supervised multi-task training strategy was compared to a classical supervised strategy and other existing state-of-the-art models. The models were trained and tested separately on two different datasets, which contained partially annotated multi-channel neonatal EEG. Models were evaluated using the F1-statistic and the relevance of the method was investigated in the context of a functional brain age (FBA) prediction model.Main results. The proposed multi-task and multi-channel CNN methods outperformed state-of-the-art methods, reaching F1 scores of 86.2% and 95.7% on two separate datasets. The proposed semi-supervised multi-task training strategy was shown to be superior to a classical supervised training strategy when the amount of labels in the dataset was artificially reduced. Finally, we found that the error of a brain age prediction model correlated with the amount of automatically detected artefacts in the EEG segment.Significance. Our results show that the proposed semi-supervised multi-task training strategy can train CNNs successfully even when the amount of labels in the dataset is limited. Therefore, this method is a promising semi-supervised technique for developing deep learning models with scarcely labelled data. Moreover, a correlation between the error of FBA estimates and the amount of detected artefacts in the corresponding EEG segments indicates the relevance of artefact detection for robust automated EEG analysis.

Automated detection and removal of flat line segments and large amplitude fluctuations in neonatal electroencephalography

Background

Artefact removal in neonatal electroencephalography (EEG) by visual inspection generally depends on the expertise of the operator, is time consuming and is not a consistent pre-processing step to the pipeline for the automated EEG analysis. Therefore, there is the need for the automated detection and removal of artefacts in neonatal EEG, especially of distinct and predominant artefacts such as flat line segments (mainly caused by instrumental error where contact between electrodes and head box is lost) and large amplitude fluctuations (related to neonatal movements).

Method

A threshold-based algorithm for the automated detection and removal of flat line segments and large amplitude fluctuations in neonatal EEG of infants at term-equivalent age is developed. The algorithm applies thresholds to the absolute second difference, absolute amplitude, absolute first difference and the ratio between the frequency content above 50 Hz and the frequency content across all frequencies.

Results

The algorithm reaches a median accuracy of 0.91, a median hit rate of 0.91 and a median false discovery rate of 0.37. Also, a significant improvement (≈10%) in the performance of a four-stage sleep classifier is observed after artefact removal with the proposed algorithm as compared to before its application.

Significance

An automated artefact removal method contributes to the pipeline of automated EEG analysis. The proposed algorithm has shown to have good performance and to be effective in neonatal EEG applications.

Neonatal heart rate variability: a contemporary scoping review of analysis methods and clinical applications

BACKGROUND

Neonatal heart rate variability (HRV) is widely used as a research tool. However, HRV calculation methods are highly variable making it difficult for comparisons between studies.

OBJECTIVES

To describe the different types of investigations where neonatal HRV was used, study characteristics, and types of analyses performed.

ELIGIBILITY CRITERIA

Human neonates ≤1 month of corrected age.

SOURCES OF EVIDENCE

A protocol and search strategy of the literature was developed in collaboration with the McGill University Health Center's librarians and articles were obtained from searches in the Biosis, Cochrane, Embase, Medline and Web of Science databases published between 1 January 2000 and 1 July 2020.

CHARTING METHODS

A single reviewer screened for eligibility and data were extracted from the included articles. Information collected included the study characteristics and population, type of HRV analysis used (time domain, frequency domain, non-linear, heart rate characteristics (HRC) parameters) and clinical applications (physiological and pathological conditions, responses to various stimuli and outcome prediction).

RESULTS

Of the 286 articles included, 171 (60%) were small single centre studies (sample size <50) performed on term infants (n=136). There were 138 different types of investigations reported: physiological investigations (n=162), responses to various stimuli (n=136), pathological conditions (n=109) and outcome predictor (n=30). Frequency domain analyses were used in 210 articles (73%), followed by time domain (n=139), non-linear methods (n=74) or HRC analyses (n=25). Additionally, over 60 different measures of HRV were reported; in the frequency domain analyses alone there were 29 different ranges used for the low frequency band and 46 for the high frequency band.

CONCLUSIONS

Neonatal HRV has been used in diverse types of investigations with significant lack of consistency in analysis methods applied. Specific guidelines for HRV analyses in neonates are needed to allow for comparisons between studies.