Coupling between Regional Oxygen Saturation of the Brain and Vital Signs during Immediate Transition after Birth.

INTRODUCTION: The primary aim was to analyze any coupling of heart rate (HR)/arterial oxygen saturation (SpO2) and regional cerebral oxygen saturation (rScO2) and regional cerebral fractional tissue oxygen extraction (cFTOE) during immediate transition after birth in term and preterm neonates to gain more insight into interactions. METHODS: The present study is a post hoc analysis of data from 106 neonates, obtained from a prospective, observational study. Measurements of HR, SpO2, rScO2, and cFTOE were performed during the first 15 min after birth. The linear and nonlinear correlation were computed between these parameters in a sliding window. The resulting coupling curves were clustered. After clustering, demographic data of the clusters were de-blinded and compared. RESULTS: Due to missing data, 58 out of 106 eligible patients were excluded. Two clusters were obtained: cluster 1 (N = 39) and cluster 2 (N = 9). SpO2 had linear and nonlinear correlations with rScO2 and cFTOE, whereby the correlations with rScO2 were more pronounced in cluster 2. HR-rScO2 and HR-cFTOE demonstrated a nonlinear correlation in both clusters, again being more pronounced in cluster 2, whereby linear correlations were mainly absent. After de-blinding, the demographic data revealed that the neonates in cluster 2 had significantly lower gestational age (mainly preterm) compared to cluster 1 (mainly term). DISCUSSION: Besides SpO2, also HR demonstrated a nonlinear correlation with rScO2 and cFTOE in term and preterm neonates during immediate transition after birth. In addition, the coupling of SpO2 and HR with cerebral oxygenation was more pronounced in neonates with a lower gestational age.

A unified framework for multi-lead ECG characterization using Laplacian Eigenmaps.

Background.The analysis of multi-lead electrocardiographic (ECG) signals requires integrating the information derived from each lead to reach clinically relevant conclusions. This analysis could benefit from data-driven methods compacting the information in those leads into lower-dimensional representations (i.e. 2 or 3 dimensions instead of 12).Objective.We propose Laplacian Eigenmaps (LE) to create a unified framework where ECGs from different subjects can be compared and their abnormalities are enhanced.Approach.We conceive a normal reference ECG space based on LE, calculated using signals of healthy subjects in sinus rhythm. Signals from new subjects can be mapped onto this reference space creating a loop per heartbeat that captures ECG abnormalities. A set of parameters, based on distance metrics and on the shape of loops, are proposed to quantify the differences between subjects.Main results.This methodology was applied to find structural and arrhythmogenic changes in the ECG. The LE framework consistently captured the characteristics of healthy ECGs, confirming that normal signals behaved similarly in the LE space. Significant differences between normal signals, and those from patients with ischemic heart disease or dilated cardiomyopathy were detected. In contrast, LE biomarkers did not identify differences between patients with cardiomyopathy and a history of ventricular arrhythmia and their matched controls.Significance.This LE unified framework offers a new representation of multi-lead signals, reducing dimensionality while enhancing imperceptible abnormalities and enabling the comparison of signals of different subjects.

Regional beat-to-beat variability of repolarization increases during ischemia and predicts imminent arrhythmias in a pig model of myocardial infarction.

Ventricular arrhythmia (VT/VF) can complicate acute myocardial ischemia (AMI). Regional instability of repolarization during AMI contributes to the substrate for VT/VF. Beat-to-beat variability of repolarization (BVR), a measure of repolarization lability increases during AMI. We hypothesized that its surge precedes VT/VF. We studied the spatial and temporal changes in BVR in relation to VT/VF during AMI. In 24 pigs, BVR was quantified on 12-lead electrocardiogram recorded at a sampling rate of 1 kHz. AMI was induced in 16 pigs by percutaneous coronary artery occlusion (MI), whereas 8 underwent sham operation (sham). Changes in BVR were assessed at 5 min after occlusion, 5 and 1 min pre-VF in animals that developed VF, and matched time points in pigs without VF. Serum troponin and ST deviation were measured. After 1 mo, magnetic resonance imaging and VT induction by programmed electrical stimulation were performed. During AMI, BVR increased significantly in inferior-lateral leads correlating with ST deviation and troponin increase. BVR was maximal 1 min pre-VF (3.78 ± 1.36 vs. 5 min pre-VF, 1.67 ± 1.56, P < 0.0001). After 1 mo, BVR was higher in MI than in sham and correlated with the infarct size (1.43 ± 0.50 vs. 0.57 ± 0.30, P = 0.009). VT was inducible in all MI animals and the ease of induction correlated with BVR. BVR increased during AMI and temporal BVR changes predicted imminent VT/VF, supporting a possible role in monitoring and early warning systems. BVR correlated to arrhythmia vulnerability suggesting utility in risk stratification post-AMI.NEW & NOTEWORTHY The key finding of this study is that BVR increases during AMI and surges before ventricular arrhythmia onset. This suggests that monitoring BVR may be useful for monitoring the risk of VF during and after AMI in the coronary care unit settings. Beyond this, monitoring BVR may have value in cardiac implantable devices or wearables.

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.

Partial wavelet coherence as a robust method for assessment of neurovascular coupling in neonates with hypoxic ischemic encephalopathy.

In neonates with hypoxic ischemic encephalopathy, the computation of wavelet coherence between electroencephalogram (EEG) power and regional cerebral oxygen saturation (rSO2) is a promising method for the assessment of neurovascular coupling (NVC), which in turn is a promising marker for brain injury. However, instabilities in arterial oxygen saturation (SpO2) limit the robustness of previously proposed methods. Therefore, we propose the use of partial wavelet coherence, which can eliminate the influence of SpO2. Furthermore, we study the added value of the novel NVC biomarkers for identification of brain injury compared to traditional EEG and NIRS biomarkers. 18 neonates with HIE were monitored for 72 h and classified into three groups based on short-term MRI outcome. Partial wavelet coherence was used to quantify the coupling between C3-C4 EEG bandpower (2-16 Hz) and rSO2, eliminating confounding effects of SpO2. NVC was defined as the amount of significant coherence in a frequency range of 0.25-1 mHz. Partial wavelet coherence successfully removed confounding influences of SpO2 when studying the coupling between EEG and rSO2. Decreased NVC was related to worse MRI outcome. Furthermore, the combination of NVC and EEG spectral edge frequency (SEF) improved the identification of neonates with mild vs moderate and severe MRI outcome compared to using EEG SEF alone. Partial wavelet coherence is an effective method for removing confounding effects of SpO2, improving the robustness of automated assessment of NVC in long-term EEG-NIRS recordings. The obtained NVC biomarkers are more sensitive to MRI outcome than traditional rSO2 biomarkers and provide complementary information to EEG biomarkers.

Factorizer: A scalable interpretable approach to context modeling for medical image segmentation.

Convolutional Neural Networks (CNNs) with U-shaped architectures have dominated medical image segmentation, which is crucial for various clinical purposes. However, the inherent locality of convolution makes CNNs fail to fully exploit global context, essential for better recognition of some structures, e.g., brain lesions. Transformers have recently proven promising performance on vision tasks, including semantic segmentation, mainly due to their capability of modeling long-range dependencies. Nevertheless, the quadratic complexity of attention makes existing Transformer-based models use self-attention layers only after somehow reducing the image resolution, which limits the ability to capture global contexts present at higher resolutions. Therefore, this work introduces a family of models, dubbed Factorizer, which leverages the power of low-rank matrix factorization for constructing an end-to-end segmentation model. Specifically, we propose a linearly scalable approach to context modeling, formulating Nonnegative Matrix Factorization (NMF) as a differentiable layer integrated into a U-shaped architecture. The shifted window technique is also utilized in combination with NMF to effectively aggregate local information. Factorizers compete favorably with CNNs and Transformers in terms of accuracy, scalability, and interpretability, achieving state-of-the-art results on the BraTS dataset for brain tumor segmentation and ISLES'22 dataset for stroke lesion segmentation. Highly meaningful NMF components give an additional interpretability advantage to Factorizers over CNNs and Transformers. Moreover, our ablation studies reveal a distinctive feature of Factorizers that enables a significant speed-up in inference for a trained Factorizer without any extra steps and without sacrificing much accuracy. The code and models are publicly available at https://github.com/pashtari/factorizer.

Post-acquisition water-signal removal in 3D water-unsuppressed 1 H-MR spectroscopic imaging of the prostate.

PURPOSE: To develop a robust processing procedure of raw signals from water-unsuppressed MRSI of the prostate for the mapping of absolute tissue concentrations of metabolites. METHODS: Water-unsuppressed 3D MRSI data were acquired from a phantom, from healthy volunteers, and a patient with prostate cancer. Signal processing included sequential computation of the modulus of the FID to remove water sidebands, a Hilbert transformation, and k-space Hamming filtering. For the removal of the water signal, we compared Löwner tensor-based blind source separation (BSS) and Hankel Lanczos singular value decomposition techniques. Absolute metabolite levels were quantified with LCModel and the results were statistically analyzed to compare the water removal methods and conventional water-suppressed MRSI. RESULTS: The post-processing algorithms successfully removed the water signal and its sidebands without affecting metabolite signals. The best water removal performance was achieved by Löwner tensor-based BSS. Absolute tissue concentrations of citrate in the peripheral zone derived from water-suppressed and unsuppressed 1 H MRSI were the same and as expected from the known physiology of the healthy prostate. Maps for citrate and choline from water-unsuppressed 3D 1 H-MRSI of the prostate showed expected spatial variations in metabolite levels. CONCLUSION: We developed a robust relatively simple post-processing method of water-unsuppressed MRSI of the prostate to remove the water signal. Absolute quantification using the water signal, originating from the same location as the metabolite signals, avoids the acquisition of additional reference data.

Relating QRS voltages to left ventricular mass and body composition in elite endurance athletes.

PURPOSE: Electrocardiogram (ECG) QRS voltages correlate poorly with left ventricular mass (LVM). Body composition explains some of the QRS voltage variability. The relation between QRS voltages, LVM and body composition in endurance athletes is unknown. METHODS: Elite endurance athletes from the Pro@Heart trial were evaluated with 12-lead ECG for Cornell and Sokolow-Lyon voltage and product. Cardiac magnetic resonance imaging assessed LVM. Dual energy x-ray absorptiometry assessed fat mass (FM) and lean mass of the trunk and whole body (LBM). The determinants of QRS voltages and LVM were identified by multivariable linear regression. Models combining ECG, demographics, DEXA and exercise capacity to predict LVM were developed. RESULTS: In 122 athletes (19 years, 71.3% male) LVM was a determinant of the Sokolow-Lyon voltage and product (ß = 0.334 and 0.477, p < 0.001) but not of the Cornell criteria. FM of the trunk (ß = - 0.186 and - 0.180, p < 0.05) negatively influenced the Cornell voltage and product but not the Sokolow-Lyon criteria. DEXA marginally improved the prediction of LVM by ECG (r = 0.773 vs 0.510, p < 0.001; RMSE = 18.9 ± 13.8 vs 25.5 ± 18.7 g, p > 0.05) with LBM as the strongest predictor (ß = 0.664, p < 0.001). DEXA did not improve the prediction of LVM by ECG and demographics combined and LVM was best predicted by including VO2max (r = 0.845, RMSE = 15.9 ± 11.6 g). CONCLUSION: LVM correlates poorly with QRS voltages with adipose tissue as a minor determinant in elite endurance athletes. LBM is the strongest single predictor of LVM but only marginally improves LVM prediction beyond ECG variables. In endurance athletes, LVM is best predicted by combining ECG, demographics and VO2max.

Assessing Neurovascular Coupling Using Wavelet Coherence in Neonates with Asphyxia.

Brain monitoring is important in neonates with asphyxia in order to assess the severity of hypoxic ischaemic encephalopathy (HIE) and identify neonates at risk of adverse neurodevelopmental outcome. Previous studies suggest that neurovascular coupling (NVC), quantified as the interaction between electroencephalography (EEG) and near-infrared spectroscopy (NIRS)-derived regional cerebral oxygen saturation (rSO2) is a promising biomarker for HIE severity and outcome. In this study, we explore how wavelet coherence can be used to assess NVC. Wavelet coherence was computed in 18 neonates undergoing therapeutic hypothermia in the first 3 days of life, with varying HIE severities (mild, moderate, severe). We compared two pre-processing methods of the EEG prior to wavelet computation: amplitude integrated EEG (aEEG) and EEG bandpower. Furthermore, we proposed average real coherence as a biomarker for NVC. Our results indicate that NVC as assessed by wavelet coherence between EEG bandpower and rSO2 can be a valuable biomarker for HIE severity in neonates with peripartal asphyxia. More specifically, average real coherence in a very low frequency range (0.21-0.83 mHz) tends to be high (positive) in neonates with mild HIE, low (positive) in neonates with moderate HIE, and negative in neonates with severe HIE. Further investigation in a larger patient cohort is needed to validate our findings.

New multiple sclerosis lesion segmentation and detection using pre-activation U-Net.

Automated segmentation of new multiple sclerosis (MS) lesions in 3D MRI data is an essential prerequisite for monitoring and quantifying MS progression. Manual delineation of such lesions is time-consuming and expensive, especially because raters need to deal with 3D images and several modalities. In this paper, we propose Pre-U-Net, a 3D encoder-decoder architecture with pre-activation residual blocks, for the segmentation and detection of new MS lesions. Due to the limited training set and the class imbalance problem, we apply intensive data augmentation and use deep supervision to train our models effectively. Following the same U-shaped architecture but different blocks, Pre-U-Net outperforms U-Net and Res-U-Net on the MSSEG-2 dataset, achieving a Dice score of 40.3% on new lesion segmentation and an F1 score of 48.1% on new lesion detection. The codes and trained models are publicly available at https://github.com/pashtari/xunet.

Classification of multiple sclerosis clinical profiles using machine learning and grey matter connectome.

Purpose: The main goal of this study is to investigate the discrimination power of Grey Matter (GM) thickness connectome data between Multiple Sclerosis (MS) clinical profiles using statistical and Machine Learning (ML) methods. Materials and Methods: A dataset composed of 90 MS patients acquired at the MS clinic of Lyon Neurological Hospital was used for the analysis. Four MS profiles were considered, corresponding to Clinical Isolated Syndrome (CIS), Relapsing-Remitting MS (RRMS), Secondary Progressive MS (SPMS), and Primary Progressive MS (PPMS). Each patient was classified in one of these profiles by our neurologist and underwent longitudinal MRI examinations including T1-weighted image acquisition at each examination, from which the GM tissue was segmented and the cortical GM thickness measured. Following the GM parcellation using two different atlases (FSAverage and Glasser 2016), the morphological connectome was built and six global metrics (Betweenness Centrality (BC), Assortativity (r), Transitivity (T), Efficiency (E g ), Modularity (Q) and Density (D)) were extracted. Based on their connectivity metrics, MS profiles were first statistically compared and second, classified using four different learning machines (Logistic Regression, Random Forest, Support Vector Machine and AdaBoost), combined in a higher level ensemble model by majority voting. Finally, the impact of the GM spatial resolution on the MS clinical profiles classification was analyzed. Results: Using binary comparisons between the four MS clinical profiles, statistical differences and classification performances higher than 0.7 were observed. Good performances were obtained when comparing the two early clinical forms, RRMS and PPMS (F1 score of 0.86), and the two neurodegenerative profiles, PPMS and SPMS (F1 score of 0.72). When comparing the two atlases, slightly better performances were obtained with the Glasser 2016 atlas, especially between RRMS with PPMS (F1 score of 0.83), compared to the FSAverage atlas (F1 score of 0.69). Also, the thresholding value for graph binarization was investigated suggesting more informative graph properties in the percentile range between 0.6 and 0.8. Conclusion: An automated pipeline was proposed for the classification of MS clinical profiles using six global graph metrics extracted from the GM morphological connectome of MS patients. This work demonstrated that GM morphological connectivity data could provide good classification performances by combining four simple ML models, without the cost of long and complex MR techniques, such as MR diffusion, and/or deep learning architectures.

Machine learning to support triage of children at risk for epileptic seizures in the pediatric intensive care unit.

Objective.Epileptic seizures are relatively common in critically-ill children admitted to the pediatric intensive care unit (PICU) and thus serve as an important target for identification and treatment. Most of these seizures have no discernible clinical manifestation but still have a significant impact on morbidity and mortality. Children that are deemed at risk for seizures within the PICU are monitored using continuous-electroencephalogram (cEEG). cEEG monitoring cost is considerable and as the number of available machines is always limited, clinicians need to resort to triaging patients according to perceived risk in order to allocate resources. This research aims to develop a computer aided tool to improve seizures risk assessment in critically-ill children, using an ubiquitously recorded signal in the PICU, namely the electrocardiogram (ECG).Approach.A novel data-driven model was developed at a patient-level approach, based on features extracted from the first hour of ECG recording and the clinical data of the patient.Main results.The most predictive features were the age of the patient, the brain injury as coma etiology and the QRS area. For patients without any prior clinical data, using one hour of ECG recording, the classification performance of the random forest classifier reached an area under the receiver operating characteristic curve (AUROC) score of 0.84. When combining ECG features with the patients clinical history, the AUROC reached 0.87.Significance.Taking a real clinical scenario, we estimated that our clinical decision support triage tool can improve the positive predictive value by more than 59% over the clinical standard.

Temporal Changes in Beat-to-Beat Variability of Repolarization Predict Imminent Nonsustained Ventricular Tachycardia in Patients With Ischemic and Nonischemic Dilated Cardiomyopathy.

Background An increase in beat-to-beat variability of repolarization (BVR) predicts arrhythmia onset in experimental models, but its clinical translation is not well established. We investigated the temporal changes in BVR before nonsustained ventricular tachycardia (nsVT) in patients with implantable cardioverter defibrillator (ICD). Methods and Results Patients with nsVT on 24-hour Holter before ICD implantation for ischemic cardiomyopathy (ischemic cardiomyopathy+nsVT, n=43) or dilated cardiomyopathy (dilated cardiomyopathy+nsVT, n=37), matched ICD candidates without nsVT (ischemic cardiomyopathy-nsVT, n=29 and dilated cardiomyopathy-nsVT, n=26), and patients without ICD without structural heart disease (n=50) were studied. Digital Holter recordings from these patients were analyzed using a modified fiducial segment averaging technique to detect the QT interval. The nsVT episodes were semi-automatically identified and QT-BVR was assessed 1-, 5-, and 30-minutes before nsVT, and at rest (at 3:00 am). Resting BVR was higher in ICD patients compared with controls without structural heart disease. In ICD patients with nsVT, BVR increased significantly 1-minute pre-nsVT in ischemic cardiomyopathy (2.21±0.59 ms, versus 5 minutes pre-nsVT: 1.78±0.50 ms, P<0.001) and dilated cardiomyopathy (2.09±0.57 ms, versus 5-minutes pre-nsVT: 1.58±0.51 ms, P<0.001), but not in patients without nsVT. In multivariable Cox regression analysis, pre-nsVT BVR was a significant predictor for appropriate therapy during follow-up. Conclusions Baseline BVR is elevated and temporal changes in BVR predict imminent nsVT events in patients with ICD independent of underlying cause. Real-time BVR monitoring could be used to predict impending ventricular arrhythmia and allow preventive therapy to be incorporated into ICDs.

Corrigendum: Artificial Intelligence Based Patient-Specific Preoperative Planning Algorithm for Total Knee Arthroplasty.

[This corrects the article DOI: 10.3389/frobt.2022.840282.].

A machine learning algorithm for electrocardiographic fQRS quantification validated on multi-center data.

Fragmented QRS (fQRS) is an electrocardiographic (ECG) marker of myocardial conduction abnormality, characterized by additional notches in the QRS complex. The presence of fQRS has been associated with an increased risk of all-cause mortality and arrhythmia in patients with cardiovascular disease. However, current binary visual analysis is prone to intra- and inter-observer variability and different definitions are problematic in clinical practice. Therefore, objective quantification of fQRS is needed and could further improve risk stratification of these patients. We present an automated method for fQRS detection and quantification. First, a novel robust QRS complex segmentation strategy is proposed, which combines multi-lead information and excludes abnormal heartbeats automatically. Afterwards extracted features, based on variational mode decomposition (VMD), phase-rectified signal averaging (PRSA) and the number of baseline-crossings of the ECG, were used to train a machine learning classifier (Support Vector Machine) to discriminate fragmented from non-fragmented ECG-traces using multi-center data and combining different fQRS criteria used in clinical settings. The best model was trained on the combination of two independent previously annotated datasets and, compared to these visual fQRS annotations, achieved Kappa scores of 0.68 and 0.44, respectively. We also show that the algorithm might be used in both regular sinus rhythm and irregular beats during atrial fibrillation. These results demonstrate that the proposed approach could be relevant for clinical practice by objectively assessing and quantifying fQRS. The study sets the path for further clinical application of the developed automated fQRS algorithm.

Artificial Intelligence Based Patient-Specific Preoperative Planning Algorithm for Total Knee Arthroplasty.

Previous studies have shown that the manufacturer's default preoperative plans for total knee arthroplasty with patient-specific guides require frequent, time-consuming changes by the surgeon. Currently, no research has been done on predicting preoperative plans for orthopedic surgery using machine learning. Therefore, this study aims to evaluate whether artificial intelligence (AI) driven planning tools can create surgeon and patient-specific preoperative plans that require fewer changes by the surgeon. A dataset of 5409 preoperative plans, including the manufacturer's default and the plans corrected by 39 surgeons, was collected. Features were extracted from the preoperative plans that describe the implant sizes, position, and orientation in a surgeon- and patient-specific manner. Based on these features, non-linear regression models were employed to predict the surgeon's corrected preoperative plan. The average number of corrections a surgeon has to make to the preoperative plan generated using AI was reduced by 39.7% compared to the manufacturer's default plan. The femoral and tibial implant size in the manufacturer's plan was correct in 68.4% and 73.1% of the cases, respectively, while the AI-based plan was correct in 82.2% and 85.0% of the cases, respectively, compared to the surgeon approved plan. Our method successfully demonstrated the use of machine learning to create preoperative plans in a surgeon- and patient-specific manner for total knee arthroplasty.

Data Augmentation and Transfer Learning for Data Quality Assessment in Respiratory Monitoring.

Changes in respiratory rate have been found to be one of the early signs of health deterioration in patients. In remote environments where diagnostic tools and medical attention are scarce, such as deep space exploration, the monitoring of the respiratory signal becomes crucial to timely detect life-threatening conditions. Nowadays, this signal can be measured using wearable technology; however, the use of such technology is often hampered by the low quality of the recordings, which leads more often to wrong diagnosis and conclusions. Therefore, to apply these data in diagnosis analysis, it is important to determine which parts of the signal are of sufficient quality. In this context, this study aims to evaluate the performance of a signal quality assessment framework, where two machine learning algorithms (support vector machine-SVM, and convolutional neural network-CNN) were used. The models were pre-trained using data of patients suffering from chronic obstructive pulmonary disease. The generalization capability of the models was evaluated by testing them on data from a different patient population, presenting normal and pathological breathing. The new patients underwent bariatric surgery and performed a controlled breathing protocol, displaying six different breathing patterns. Data augmentation (DA) and transfer learning (TL) were used to increase the size of the training set and to optimize the models for the new dataset. The effect of the different breathing patterns on the performance of the classifiers was also studied. The SVM did not improve when using DA, however, when using TL, the performance improved significantly (p < 0.05) compared to DA. The opposite effect was observed for CNN, where the biggest improvement was obtained using DA, while TL did not show a significant change. The models presented a low performance for shallow, slow and fast breathing patterns. These results suggest that it is possible to classify respiratory signals obtained with wearable technologies using pre-trained machine learning models. This will allow focusing on the relevant data and avoid misleading conclusions because of the noise, when designing bio-monitoring systems.

A Deep Shared Multi-Scale Inception Network Enables Accurate Neonatal Quiet Sleep Detection With Limited EEG Channels.

In this paper, we introduce a new variation of the Convolutional Neural Network Inception block, called Sinc, for sleep stage classification in premature newborn babies using electroencephalogram (EEG). In practice, there are many medical centres where only a limited number of EEG channels are recorded. Existing automated algorithms mainly use multi-channel EEGs which perform poorly when fewer numbers of channels are available. The proposed Sinc utilizes multi-scale analysis to place emphasis on the temporal EEG information to be less dependent on the number of EEG channels. In Sinc, we increase the receptive fields through Inception while by additionally sharing the filters that have similar receptive fields, overfitting is controlled and the number of trainable parameters dramatically reduced. To train and test this model, 96 longitudinal EEG recordings from 26 premature infants are used. The Sinc-based model significantly outperforms state-of-the-art neonatal quiet sleep detection algorithms, with mean Kappa 0.77 ± 0.01 (with 8-channel EEG) and 0.75 ± 0.01 (with a single bipolar channel EEG). This is the first study using Inception-based networks for EEG analysis that utilizes filter sharing to improve efficiency and trainability. The suggested network can successfully detect quiet sleep stages with even a single EEG channel making it more practical especially in the hospital setting where cerebral function monitoring is predominantly used.

Early soft and flexible fusion of electroencephalography and functional magnetic resonance imaging via double coupled matrix tensor factorization for multisubject group analysis.

Data fusion refers to the joint analysis of multiple datasets that provide different (e.g., complementary) views of the same task. In general, it can extract more information than separate analyses can. Jointly analyzing electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) measurements has been proved to be highly beneficial to the study of the brain function, mainly because these neuroimaging modalities have complementary spatiotemporal resolution: EEG offers good temporal resolution while fMRI is better in its spatial resolution. The EEG-fMRI fusion methods that have been reported so far ignore the underlying multiway nature of the data in at least one of the modalities and/or rely on very strong assumptions concerning the relation of the respective datasets. For example, in multisubject analysis, it is commonly assumed that the hemodynamic response function is a priori known for all subjects and/or the coupling across corresponding modes is assumed to be exact (hard). In this article, these two limitations are overcome by adopting tensor models for both modalities and by following soft and flexible coupling approaches to implement the multimodal fusion. The obtained results are compared against those of parallel independent component analysis and hard coupling alternatives, with both synthetic and real data (epilepsy and visual oddball paradigm). Our results demonstrate the clear advantage of using soft and flexible coupled tensor decompositions in scenarios that do not conform with the hard coupling assumption.

Functional brain maturation and sleep organisation in neonates with congenital heart disease.

OBJECTIVE: Neonates with Congenital Heart Disease (CHD) have structural delays in brain development. To evaluate whether functional brain maturation and sleep-wake physiology is also disturbed, the Functional Brain Age (FBA) and sleep organisation on EEG during the neonatal period is investigated. METHODS: We compared 15 neonates with CHD who underwent multichannel EEG with healthy term newborns of the same postmenstrual age, including subgroup analysis for d-Transposition of the Great Arteries (d-TGA) (n = 8). To estimate FBA, a prediction tool using quantitative EEG features as input, was applied. Second, the EEG was automatically classified into the 4 neonatal sleep stages. Neonates with CHD underwent neurodevelopmental testing using the Bayley Scale of Infant Development-III at 24 months. RESULTS: Preoperatively, the FBA was delayed in CHD infants and more so in d-TGA infants. The FBA was positively correlated with motor scores. Sleep organisation was significantly altered in neonates with CHD. The duration of the sleep cycle and the proportion of Active Sleep Stage 1 was decreased, again more marked in the d-TGA infants. Neonates with d-TGA spent less time in High Voltage Slow Wave Sleep and more in Tracé Alternant compared to healthy terms. Both FBA and sleep organisation normalised postoperatively. The duration of High Voltage Slow Wave Sleep remained positively correlated with motor scores in d-TGA infants. INTERPRETATION: Altered early brain function and sleep is present in neonates with CHD. These results are intruiging, as inefficient neonatal sleep has been linked with adverse long-term outcome. Identifying how these rapid alterations in brain function are mitigated through improvements in cerebral oxygenation, surgery, drugs and nutrition may have relevance for clinical practice and outcome.