Search

The electrocardiogram (ECG) is a powerful tool to measure the electrical activity of the heart, and the analysis of its data can be useful to assess the patient’s health. In particular, the computational analysis of electrocardiogram data, also called ECG signal processing, can reveal specific patterns or heart cycle trends which otherwise would be unnoticeable by medical experts. When performing ECG signal processing, however, it is easy to make mistakes and generate inflated, overoptimistic, or misleading results, which can lead to wrong diagnoses or prognoses and, in turn, could even contribute to bad medical decisions, damaging the health of the patient. Therefore, to avoid common mistakes and bad practices, we present here ten easy guidelines to follow when analyzing electrocardiogram data computationally. Our ten recommendations, written in a simple way, can be useful to anyone performing a computational study based on ECG data and eventually lead to better, more robust medical results.

The diagnosis of epilepsy can be confirmed in-hospital via video-electroencephalography (vEEG). Currently, long-term monitoring is limited to self-reporting seizure occurrences by the patients. In recent years, the development of wearable sensors has allowed monitoring patients outside of specialized environments. The application of wearable EEG devices for monitoring epileptic patients in ambulatory environments is still dampened by the low performance achieved by automated seizure detection frameworks. In this work, we present the results of a seizure detection grand challenge, organized as an attempt to stimulate the development of automated methodologies for detection of seizures on wearable EEG. The main drawbacks for developing wearable EEG seizure detection algorithms is the lack of data needed for training such frameworks. In this challenge, we provided participants with a large dataset of 42 patients with focal epilepsy, containing continuous recordings of behind-the-ear (bte) EEG. We challenged participants to develop a robust seizure classifier based on wearable EEG. Additionally, we proposed a subtask in order to motivate data-centric approaches to improve the training and performance of seizure detection models. An additional dataset, containing recordings with a bte-EEG wearable device, was employed to evaluate the work submitted by participants. In this paper, we present the five best scoring methodologies. The best performing approach was a feature-based decision tree ensemble algorithm with data augmentation via Fourier Transform surrogates. The organization of this challenge is of high importance for improving automated EEG analysis for epilepsy diagnosis, working towards implementing these technologies in clinical practice.

Sleep abnormalities can have severe health consequences. Automated sleep staging, i.e. labelling the sequence of sleep stages from the patient’s physiological recordings, could simplify the diagnostic process. Previous work on automated sleep staging has achieved great results, mainly relying on the EEG signal. However, often multiple sources of information are available beyond EEG. This can be particularly beneficial when the EEG recordings are noisy or even missing completely. In this paper, we propose CoRe-Sleep, a Coordinated Representation multimodal fusion network that is particularly focused on improving the robustness of signal analysis on imperfect data. We demonstrate how appropriately handling multimodal information can be the key to achieving such robustness. CoRe-Sleep tolerates noisy or missing modalities segments, allowing training on incomplete data. Additionally, it shows state-of-the-art performance when testing on both multimodal and unimodal data using a single model on SHHS-1, the largest publicly available study that includes sleep stage labels. The results indicate that training the model on multimodal data does positively influence performance when tested on unimodal data. This work aims at bridging the gap between automated analysis tools and their clinical utility.

ObjectivesThis study aimed to validate a sleep staging algorithm using in-hospital video-electroencephalogram (EEG) in children without epilepsy, with well-controlled epilepsy (WCE), and with drug-resistant epilepsy (DRE).MethodsOvernight video-EEG, along with electrooculogram (EOG) and chin electromyogram (EMG), was recorded in children between 4 and 18 years of age. Classical sleep staging was performed manually as a ground truth. An end-to-end hierarchical recurrent neural network for sequence-to-sequence automatic sleep staging (SeqSleepNet) was used to perform automated sleep staging using three channels: C4-A1, EOG, and chin EMG.ResultsIn 176 children sleep stages were manually scored: 47 children without epilepsy, 74 with WCE, and 55 with DRE. The 5-class sleep staging accuracy of the automatic sleep staging algorithm was 84.7% for the children without epilepsy, 83.5% for those with WCE, and 80.8% for those with DRE (Kappa of 0.79, 0.77, and 0.73 respectively). Performance per sleep stage was assessed with an F1 score of 0.91 for wake, 0.50 for N1, 0.83 for N2, 0.84 for N3, and 0.86 for rapid eye movement (REM) sleep.ConclusionWe concluded that the tested algorithm has a high accuracy in children without epilepsy and with WCE. Performance in children with DRE was acceptable, but significantly lower, which could be explained by a tendency of more time spent in N1, and by abundant interictal epileptiform discharges and intellectual disability leading to less recognizable sleep stages. REM sleep time, however, significantly affected in children with DRE, can be detected reliably by the algorithm.Clinical trial registration: ClinicalTrials.gov, identifier NCT04584385.

Abstract Background Parameters from maximal expiratory flow-volume curves (MEFVC) have been linked to CT-based parameters of COPD. However, the association between MEFVC shape and phenotypes like emphysema, small airways disease (SAD) and bronchial wall thickening (BWT) has not been investigated. Research question We analyzed if the shape of MEFVC can be linked to CT-determined emphysema, SAD and BWT in a large cohort of COPDGene participants. Study design and methods In the COPDGene cohort, we used principal component analysis (PCA) to extract patterns from MEFVC shape and performed multiple linear regression to assess the association of these patterns with CT parameters over the COPD spectrum, in mild and moderate-severe COPD. Results Over the entire spectrum, in mild and moderate-severe COPD, principal components of MEFVC were important predictors for the continuous CT parameters. Their contribution to the prediction of emphysema diminished when classical pulmonary function test parameters were added. For SAD, the components remained very strong predictors. The adjusted R2 was higher in moderate-severe COPD, while in mild COPD, the adjusted R2 for all CT outcomes was low; 0.28 for emphysema, 0.21 for SAD and 0.19 for BWT. Interpretation The shape of the maximal expiratory flow-volume curve as analyzed with PCA is not an appropriate screening tool for early disease phenotypes identified by CT scan. However, it contributes to assessing emphysema and SAD in moderate-severe COPD.

Abstract 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.

Background and aims Pulmonary hypertension due to left heart disease (PH-LHD) is the most frequent form of PH. As differential diagnosis with pulmonary arterial hypertension (PAH) has therapeutic implications, it is important to accurately and noninvasively differentiate PH-LHD from PAH before referral to PH centres. The aim was to develop and validate a machine learning (ML) model to improve prediction of PH-LHD in a population of PAH and PH-LHD patients. Methods Noninvasive PH-LHD predictors from 172 PAH and 172 PH-LHD patients from the PH centre database at the University Hospitals of Leuven (Leuven, Belgium) were used to develop an ML model. The Jacobs score was used as performance benchmark. The dataset was split into a training and test set (70:30) and the best model was selected after 10-fold cross-validation on the training dataset (n=240). The final model was externally validated using 165 patients (91 PAH, 74 PH-LHD) from Erasme Hospital (Brussels, Belgium). Results In the internal test dataset (n=104), a random forest-based model correctly diagnosed 70% of PH-LHD patients (sensitivity: n=35/50), with 100% positive predicted value, 78% negative predicted value and 100% specificity. The model outperformed the Jacobs score, which identified 18% (n=9/50) of the patients with PH-LHD without false positives. In external validation, the model had 64% sensitivity at 100% specificity, while the Jacobs score had a sensitivity of 3% for no false positives. Conclusions ML significantly improves the sensitivity of PH-LHD prediction at 100% specificity. Such a model may substantially reduce the number of patients referred for invasive diagnostics without missing PAH diagnoses.

IntroductionAs our attention is becoming a commodity that an ever-increasing number of applications are competing for, investing in modern day tools and devices that can detect our mental states and protect them from outside interruptions holds great value. Mental fatigue and distractions are impacting our ability to focus and can cause workplace injuries. Electroencephalography (EEG) may reflect concentration, and if EEG equipment became wearable and inconspicuous, innovative brain-computer interfaces (BCI) could be developed to monitor mental load in daily life situations. The purpose of this study is to investigate the potential of EEG recorded inside and around the human ear to determine levels of attention and focus.MethodsIn this study, mobile and wireless ear-EEG were concurrently recorded with conventional EEG (cap) systems to collect data during tasks related to focus: an N-back task to assess working memory and a mental arithmetic task to assess cognitive workload. The power spectral density (PSD) of the EEG signal was analyzed to isolate consistent differences between mental load conditions and classify epochs using step-wise linear discriminant analysis (swLDA).Results and discussionResults revealed that spectral features differed statistically between levels of cognitive load for both tasks. Classification algorithms were tested on spectral features from twelve and two selected channels, for the cap and the ear-EEG. A two-channel ear-EEG model evaluated the performance of two dry in-ear electrodes specifically. Single-trial classification for both tasks revealed above chance-level accuracies for all subjects, with mean accuracies of: 96% (cap-EEG) and 95% (ear-EEG) for the twelve-channel models, 76% (cap-EEG) and 74% (in-ear-EEG) for the two-channel model for the N-back task; and 82% (cap-EEG) and 85% (ear-EEG) for the twelve-channel, 70% (cap-EEG) and 69% (in-ear-EEG) for the two-channel model for the arithmetic task. These results suggest that neural oscillations recorded with ear-EEG can be used to reliably differentiate between levels of cognitive workload and working memory, in particular when multi-channel recordings are available, and could, in the near future, be integrated into wearable devices.

Although medication use during pregnancy is common, most available products lack sufficient safety information. As prospective data collection and perinatal pharmacoepidemiologic research on medication safety in pregnancy did not exist in Belgium yet, the BELpREG data registration system was developed. BELpREG enables comprehensive “real-world” data collection on perinatal medication use and mother-infant outcomes via online questionnaires that are completed by pregnant women every 4 weeks during pregnancy and in the first 8 weeks after childbirth. This paper describes the development and current design of the BELpREG system, including the list of BELpREG variables. To compile this list of variables, relevant documents were explored, followed by consultation of an interdisciplinary expert panel. The included variables were structured in seven categories: 1) Sociodemographic characteristics; 2) Information on the current pregnancy and health status; 3) Maternal-obstetric history; 4) Use of medicines, folic acid/pregnancy vitamins and other health products; 5) Substance use; 6) Pregnancy outcomes; and 7) Neonatal outcomes. An electronic informed consent and linkage to medication databases, with images of drug packages and underlying structured data fields, are built into the system. Data collection has officially started in November 2022. Based on its rigorous design, BELpREG holds the potential to be a successful and sustainable research tool, enabling perinatal pharmacoepidemiologic research in Belgium and beyond.

Background and objectiveSpirometry patterns can suggest that a patient has a restrictive ventilatory impairment; however, lung volume measurements such as total lung capacity (TLC) are required to confirm the diagnosis. The aim of the study was to train a supervised machine learning model that can accurately estimate TLC values from spirometry and subsequently identify which patients would most benefit from undergoing a complete pulmonary function test.MethodsWe trained three tree-based machine learning models on 51,761 spirometry data points with corresponding TLC measurements. We then compared model performance using an independent test set consisting of 1,402 patients. The best-performing model was used to retrospectively identify restrictive ventilatory impairment in the same test set. The algorithm was compared against different spirometry patterns commonly used to predict restriction.ResultsThe prevalence of restrictive ventilatory impairment in the test set is 16.7% (234/1402). CatBoost was the best-performing machine learning model. It predicted TLC with a mean squared error (MSE) of 560.1 mL. The sensitivity, specificity, and F1-score of the optimal algorithm for predicting restrictive ventilatory impairment was 83, 92, and 75%, respectively.ConclusionA machine learning model trained on spirometry data can estimate TLC to a high degree of accuracy. This approach could be used to develop future smart home-based spirometry solutions, which could aid decision making and self-monitoring in patients with restrictive lung diseases.

Goal: Smartphone and wearable devices may act as powerful tools to remotely monitor physical function in people with neurodegenerative and autoimmune diseases from out-of-clinic environments. Detection of progression onset or worsening of symptoms is especially important in people living with multiple sclerosis (PwMS) in order to enable optimally adapted therapeutic strategies. MS symptoms typically follow subtle and fluctuating disease courses, patient-to-patient, and over time. Current in-clinic assessments are often too infrequently administered to reflect longitudinal changes in MS impairment that impact daily life. This work, therefore, explores how smartphones can administer daily two-minute walking assessments to monitor PwMS physical function at home. Methods: Remotely collected smartphone inertial sensor data was transformed through state-of-the-art Deep Convolutional Neural Networks, to estimate a participant's daily ambulatory-related disease severity, longitudinally over a 24-week study. Results: This study demonstrated that smartphone-based ambulatory severity outcomes could accurately estimate MS level of disability, as measured by the EDSS score ($r^{2}$: 0.56,$p< $0.001). Furthermore, longitudinal severity outcomes were shown to accurately reflect individual participants' level of disability over the study duration. Conclusion: Smartphone-based assessments, that can be performed by patients from their home environments, could greatly augment standard in-clinic outcomes for neurodegenerative diseases. The ability to understand the impact of disease on daily-life between clinical visits, through objective digital outcomes, paves the way forward to better measure and identify signs of disease progression that may be occurring out-of-clinic, to monitor how different patients respond to various treatments, and to ultimately enable the development of better, and more personalised care.

Heart disease is the leading cause of mortality worldwide, and it is of utmost importance that clinicians and researchers understand the dynamics of the heart. As an electrical measure of the heart’s activity, the electrocardiogram, or ECG, is the gold standard for recording the cardiac state, whether monitoring the structure of the traces that make up the ECG or indicating key metrics such as heart rate variability. Long-term monitoring of ECG is often required to identify cardiovascular issues but proves impractical; therefore, patients will remotely collect their data. However, ECG signals can become contaminated with various noise sources during data collection. This paper proposes a custom loss function capable of denoising electrode motion artefact in ECG data to a higher standard than other, more common loss functions. We implement our custom loss function with a convolutional neural network to return high-quality ECG, suitable for calculating the aforementioned key metrics from a previously unobtainable state. The proposed model improves ECG signals overall signal-to-noise ratio and preserves the R waves structure. The model outperforms a standard mean squared error loss function with an improvement of 0.5 dB in terms of signal to noise ratio and improves the heart rate estimation by 25%.

Introduction Objective cough frequency is a key clinical end-point but existing wearable monitors are limited to 24-h recordings. Albus Home uses contactless motion, acoustic and environmental sensors to monitor multiple metrics, including respiratory rate and cough without encroaching on patient lifestyle. The aim of this study was to evaluate measurement characteristics of nocturnal cough monitoring by Albus Home compared to manual counts. Methods Adults with respiratory conditions underwent overnight monitoring using Albus Home in their usual bedroom environments. Participants set-up the plug-and-play device themselves. For reference counts, each audio recording was counted by two annotators, and cough defined as explosive phases audio-visually labelled by both. In parallel, recordings were processed by a proprietary Albus system, comprising a deep-learning algorithm with a human screening step for verifying or excluding occasional events that mimic cough. Performance of the Albus system in detecting individual cough events and reporting hourly cough counts was compared against reference counts. Results 30 nights from 10 subjects comprised 375 hours of recording. Mean±sd coughs per night were 90±76. Coughs per hour ranged from 0 to 129. Albus counts were accurate across hours with high and low cough frequencies, with median sensitivity, specificity, positive predictive value and negative predictive values of 94.8, 100.0, 99.1 and 100.0%, respectively. Agreement between Albus and reference was strong (intra-class correlation coefficient (ICC) 0.99; 95% CI 0.99–0.99; p

Having previously seen an item helps uncover the item another time, given a perceptual or cognitive cue. Oftentimes, however, it may be difficult to quantify or test the existence and size of a perceptual or cognitive effect, in general, and a priming effect, in particular. This is because to examine the existence of and quantify the effect, one needs to compare two outcomes: the outcome had one previously seen the item vs. the outcome had one not seen the item. But only one of the two outcomes is observable. Here, we argue that the potential outcomes framework is useful to define, quantify, and test the causal priming effect. To demonstrate its efficacy, we apply the framework to study the priming effect using data from a between-subjects study involving English word identification. In addition, we show that what has been used intuitively by experimentalists to assess the priming effect in the past has a sound mathematical foundation. Finally, we examine the links between the proposed method in studying priming and the multinomial processing tree (MPT) model, and how to extend the method to study experimental paradigms involving exclusion and inclusion instructional conditions.

Patients with absence epilepsy fail to report almost 90% of their seizures. The clinical gold standard to assess absence seizures is video-electroencephalography (vEEG) recorded in the hospital, an expensive and obtrusive procedure which requires also extended reviewing time. Wearable sensors, which allow the recording of electroencephalography (EEG), accelerometer and gyroscope have been used to monitor epileptic patients in their home environment for the first time. We developed a pipeline for accurate and robust absence seizure detection while reducing the review time of the long recordings. Our results show that multimodal analysis of absence seizures can improve the robustness to false alarms, while retaining a high sensitivity in seizure detection.

Abstract The emergence of digital technologies such as smartphones in healthcare applications have demonstrated the possibility of developing rich, continuous, and objective measures of multiple sclerosis (MS) disability that can be administered remotely and out-of-clinic. Deep Convolutional Neural Networks (DCNN) may capture a richer representation of healthy and MS-related ambulatory characteristics from the raw smartphone-based inertial sensor data than standard feature-based methodologies. To overcome the typical limitations associated with remotely generated health data, such as low subject numbers, sparsity, and heterogeneous data, a transfer learning (TL) model from similar large open-source datasets was proposed. Our TL framework leveraged the ambulatory information learned on human activity recognition (HAR) tasks collected from wearable smartphone sensor data. It was demonstrated that fine-tuning TL DCNN HAR models towards MS disease recognition tasks outperformed previous Support Vector Machine (SVM) feature-based methods, as well as DCNN models trained end-to-end, by upwards of 8–15%. A lack of transparency of “black-box” deep networks remains one of the largest stumbling blocks to the wider acceptance of deep learning for clinical applications. Ensuing work therefore aimed to visualise DCNN decisions attributed by relevance heatmaps using Layer-Wise Relevance Propagation (LRP). Through the LRP framework, the patterns captured from smartphone-based inertial sensor data that were reflective of those who are healthy versus people with MS (PwMS) could begin to be established and understood. Interpretations suggested that cadence-based measures, gait speed, and ambulation-related signal perturbations were distinct characteristics that distinguished MS disability from healthy participants. Robust and interpretable outcomes, generated from high-frequency out-of-clinic assessments, could greatly augment the current in-clinic assessment picture for PwMS, to inform better disease management techniques, and enable the development of better therapeutic interventions.

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.

Long-term home monitoring of people living with epilepsy cannot be achieved using the standard full-scalp electroencephalography (EEG) coupled with video. Wearable seizure detection devices, such as behind-the-ear EEG (bte-EEG), offer an unobtrusive method for ambulatory follow-up of this population. Combining bte-EEG with electrocardiography (ECG) can enhance automated seizure detection performance. However, such frameworks produce high false alarm rates, making visual review necessary. This study aimed to evaluate a semi-automated multimodal wearable seizure detection framework using bte-EEG and ECG. Using the SeizeIT1 dataset of 42 patients with focal epilepsy, an automated multimodal seizure detection algorithm was used to produce seizure alarms. Two reviewers evaluated the algorithm’s detections twice: (1) using only bte-EEG data and (2) using bte-EEG, ECG, and heart rate signals. The readers achieved a mean sensitivity of 59.1% in the bte-EEG visual experiment, with a false detection rate of 6.5 false detections per day. Adding ECG resulted in a higher mean sensitivity (62.2%) and a largely reduced false detection rate (mean of 2.4 false detections per day), as well as an increased inter-rater agreement. The multimodal framework allows for efficient review time, making it beneficial for both clinicians and patients.

Background: Mild cognitive impairment (MCI) is a condition that entails a slight yet noticeable decline in cognition that exceeds normal age-related changes. Older adults living with MCI have a higher chance of progressing to dementia, which warrants regular cognitive follow-up at memory clinics. However, due to time and resource constraints, this follow-up is conducted at separate moments in time with large intervals in between. Casual games, embedded into the daily life of older adults, may prove to be a less resource-intensive medium that yields continuous and rich data on a patient’s cognition. Objective: To explore whether digital biomarkers of cognitive performance, found in the casual card game Klondike Solitaire, can be used to train machine-learning models to discern games played by older adults living with MCI from their healthy counterparts. Methods: Digital biomarkers of cognitive performance were captured from 23 healthy older adults and 23 older adults living with MCI, each playing 3 games of Solitaire with 3 different deck shuffles. These 3 deck shuffles were identical for each participant. Using a supervised stratified, 5-fold, cross-validated, machine-learning procedure, 19 different models were trained and optimized for F1 score. Results: The 3 best performing models, an Extra Trees model, a Gradient Boosting model, and a Nu-Support Vector Model, had a cross-validated F1 training score on the validation set of ≥0.792. The F1 score and AUC of the test set were, respectively, >0.811 and >0.877 for each of these models. These results indicate psychometric properties comparative to common cognitive screening tests. Conclusion: The results suggest that commercial card games, not developed to address specific mental processes, may be used for measuring cognition. The digital biomarkers derived from Klondike Solitaire show promise and may prove useful to fill the current blind spot between consultations.

Access to medical data is highly regulated due to its sensitive nature, which can constrain communities’ ability to utilize these data for research or clinical purposes. Common de-identification techniques to enable the sharing of data may not provide adequate privacy in every circumstance. We investigate the ability of Generative Adversarial Networks (GANs) to generate synthetic, and more significantly, multichannel electrocardiogram signals that are representative of waveforms observed in patients to address these privacy concerns. Successful generation of high-quality synthetic time series data has the potential to act as an effective substitute for actual patient data. For the first time, we demonstrate a range of novel loss functions using our multivariate GAN architecture and analyse their effect on data quality and privacy. We also present the application of multivariate dynamic time warping as a means of evaluating generated time series. Quantitative evidence demonstrates that the inclusion of a penalisation coefficient (Dynamic Time Warping) in the loss function enables our GAN to outperform the other generative models and loss functions explored by 4.9% according to our metrics. This allows for the generation of data that is more representative of the training set and diverse across generated samples, all whilst ensuring sufficient privacy.

As a measure of the brain's electrical activity, electroencephalography (EEG) is the primary signal of interest for brain-computer-interfaces (BCI). BCIs offer a communication pathway between a brain and an external device, translating thought into action with suitable processing. EEG data is the most common signal source for such technologies. However, artefacts induced in BCIs in the real-world context can severely degrade their performance relative to their in-laboratory performance. In most cases, the recorded signals are so heavily corrupted by noise that they are unusable and restrict BCI's broader applicability. To realise the use of portable BCIs capable of high-quality performance in a real-world setting, we use Generative Adversarial Networks (GANs) that can adopt both supervised and unsupervised learning approaches. Although our approach is supervised, the same model can be used for unsupervised tasks such as data augmentation/imputation in the low resource setting. Exploiting recent advancements in Generative Adversarial Networks (GAN), we construct a pipeline capable of denoising artefacts from EEG time series data. In the case of denoising data, it maps noisy EEG signals to clean EEG signals, given the nature of the respective artefact. We demonstrate the capability of our network on a toy dataset and a benchmark EEG dataset developed explicitly for deep learning denoising techniques. Our datasets consist of an artificially added mains noise (50/60 Hz) artefact dataset and an open-source EEG benchmark dataset with two artificially added artefacts. Artificially inducing myogenic and ocular artefacts for the benchmark dataset allows us to present qualitative and quantitative evidence of the GANs denoising capabilities and rank it among the current gold standard deep learning EEG denoising techniques. We show the power spectral density (PSD), signal-to-noise ratio (SNR), and other classical time series similarity measures for quantitative metrics and compare our model to those previously used in the literature. To our knowledge, this framework is the first example of a GAN capable of EEG artefact removal and generalisable to more than one artefact type. Our model has provided a competitive performance in advancing the state-of-the-art deep learning EEG denoising techniques. Furthermore, given the integration of AI into wearable technology, our method would allow for portable EEG devices with less noisy and more stable brain signals.

Abstract Background Avoidance to look others in the eye is a characteristic symptom of Autism Spectrum Disorders (ASD), and it has been hypothesised that quantitative monitoring of gaze patterns could be useful to objectively evaluate treatments. However, tools to measure gaze behaviour on a regular basis at a manageable cost are missing. In this paper, we investigated whether a smartphone-based tool could address this problem. Specifically, we assessed the accuracy with which the phone-based, state-of-the-art eye-tracking algorithm iTracker can distinguish between gaze towards the eyes and the mouth of a face displayed on the smartphone screen. This might allow mobile, longitudinal monitoring of gaze aversion behaviour in ASD patients in the future. Results We simulated a smartphone application in which subjects were shown an image on the screen and their gaze was analysed using iTracker. We evaluated the accuracy of our set-up across three tasks in a cohort of 17 healthy volunteers. In the first two tasks, subjects were shown different-sized images of a face and asked to alternate their gaze focus between the eyes and the mouth. In the last task, participants were asked to trace out a circle on the screen with their eyes. We confirm that iTracker can recapitulate the true gaze patterns, and capture relative position of gaze correctly, even on a different phone system to what it was trained on. Subject-specific bias can be corrected using an error model informed from the calibration data. We compare two calibration methods and observe that a linear model performs better than a previously proposed support vector regression-based method. Conclusions Under controlled conditions it is possible to reliably distinguish between gaze towards the eyes and the mouth with a smartphone-based set-up. However, future research will be required to improve the robustness of the system to roll angle of the phone and distance between the user and the screen to allow deployment in a home setting. We conclude that a smartphone-based gaze-monitoring tool provides promising opportunities for more quantitative monitoring of ASD.

Background: To improve the objective assessment of continuous video-EEG (cEEG) monitoring of neonatal brain function, the aim was to relate automated derived amplitude and duration parameters of the suppressed periods in the EEG background (dynamic Interburst Interval= dIBIs) after neonatal hypoxic-ischemic encephalopathy (HIE) to favourable or adverse neurodevelopmental outcome. Methods: Nineteen neonates (gestational age 36–41 weeks) with HIE underwent therapeutic hypothermia and had cEEG-monitoring. EEGs were retrospectively analyzed with a previously developed algorithm to detect the dynamic Interburst Intervals. Median duration and amplitude of the dIBIs were calculated at 1 h-intervals. Sensitivity and specificity of automated EEG background grading for favorable and adverse outcomes were assessed at 6 h-intervals. Results: Dynamic IBI values reached the best prognostic value between 18 and 24 h (AUC of 0.93). EEGs with dIBI amplitude ≥15 μV and duration 10 s were specific for adverse outcome (89–100%) at 18–24 h (n = 10). Extremely low voltage and invariant EEG patterns were indicative of adverse outcome at all time points. Conclusions: Automated analysis of the suppressed periods in EEG of neonates with HIE undergoing TH provides objective and early prognostic information. This objective tool can be used in a multimodal strategy for outcome assessment. Implementation of this method can facilitate clinical practice, improve risk stratification and aid therapeutic decision-making. A multicenter trial with a quantifiable outcome measure is warranted to confirm the predictive value of this method in a more heterogeneous dataset. Keywords: hypoxic-ischemic encephalopathy, automated EEG analysis, dynamic Interburst Interval, outcome prediction

Respiratory rate (RR) is a clinically important predictor of cardio-respiratory deteriorations. The mainstay of clinical measurement comprises the manual counting of chest movements, which is variable between clinicians and limited to sporadic readings. Emerging solutions are limited by poor adherence and acceptability or are not clinically validated. Albus HomeTM is a contactless and automated bedside system for nocturnal respiratory monitoring that overcomes these limitations. This study aimed to validate the accuracy of Albus Home compared to gold standards in real-world sleeping environments. Participants undertook overnight monitoring simultaneously using Albus Home and gold-standard polygraphy with thoraco-abdominal respiratory effort belts (SomnomedicsEU). Reference RR readings were obtained by clinician-count of polygraphy data. For both the Albus system and reference, RRs were measured in 30-s segments, reported as breaths/minute, and compared. Accuracy was defined as the percentage of RRs from the Albus system within ±2 breaths/minute of reference counts. Across a diverse validation set of 32 participants, the mean accuracy exceeded 98% and was maintained across different participant characteristics. In a Bland–Altman analysis, Albus RRs had strong agreement with reference mean differences and the limits of agreement of −0.4 and ±1.2 breaths/minute, respectively. Albus Home is a contactless yet accurate system for automated respiratory monitoring. Validated against gold –standard methods, it enables long-term, reliable nocturnal monitoring without patient burden.

Along the pathway from behavioral symptoms to the development of psychotic disorders sits the multivariate mediating brain. The functional organization and structural topography of large-scale multivariate neural mediators among patients with brain disorders, however, are not well understood. Here, we design a high-dimensional brain-wide functional mediation framework to investigate brain regions that intermediate between baseline behavioral symptoms and future conversion to full psychosis among individuals at clinical high risk (CHR). Using resting-state functional magnetic resonance imaging (fMRI) data from 263 CHR subjects, we extract an α brain atlas and a β brain atlas: the former underlines brain areas associated with prodromal symptoms and the latter highlights brain areas associated with disease onset. In parallel, we identify and separate mediators that potentially positively and negatively mediate symptoms and psychosis, respectively, and quantify the effect of each neural mediator on disease development. Taken together, these results paint a brain-wide picture of neural markers that are potentially mediating behavioral symptoms and the development of psychotic disorders; additionally, they underscore a statistical framework that is useful to uncover large-scale intermediating variables in a regulatory biological system.

Ischemic heart disease is the highest cause of mortality globally each year. This puts a massive strain not only on the lives of those affected, but also on the public healthcare systems. To understand the dynamics of the healthy and unhealthy heart, doctors commonly use an electrocardiogram (ECG) and blood pressure (BP) readings. These methods are often quite invasive, particularly when continuous arterial blood pressure (ABP) readings are taken, and not to mention very costly. Using machine learning methods, we develop a framework capable of inferring ABP from a single optical photoplethysmogram (PPG) sensor alone. We train our framework across distributed models and data sources to mimic a large-scale distributed collaborative learning experiment that could be implemented across low-cost wearables. Our time-series-to-time-series generative adversarial network (T2TGAN) is capable of high-quality continuous ABP generation from a PPG signal with a mean error of 2.95 mmHg and a standard deviation of 19.33 mmHg when estimating mean arterial pressure on a previously unseen, noisy, independent dataset. To our knowledge, this framework is the first example of a GAN capable of continuous ABP generation from an input PPG signal that also uses a federated learning methodology.

Wearable technology will become available and allow prolonged electroencephalography (EEG) monitoring in the home environment of patients with epilepsy. Neurologists analyse the EEG visually and annotate all seizures, which patients often under-report. Visual analysis of a 24-h EEG recording typically takes one to two hours. Reliable automated seizure detection algorithms will be crucial to reduce this analysis. We investigated such algorithms on a dataset of behind-the-ear EEG measurements. Our first aim was to develop a methodology where part of the data is deferred to a human expert, who performs perfectly, with the goal of obtaining an (almost) perfect detection sensitivity (DS). Prediction confidences are determined by temperature scaling of the classification model outputs and trust scores. A DS of approximately 90% (99%) can be achieved when deferring around 10% (40%) of the data. Perfect DS can be achieved when deferring 50% of the data. Our second contribution demonstrates that a common modelling strategy, where predictions from several short EEG segments are combined to obtain a final prediction, can be improved by filtering out untrustworthy segments with low trust scores. The false detection rate shows a relative decrease between 21% and 43%, and the DS shows a small increase or decrease.

Heart rate variability (HRV) in psychiatric disorders has become an increasing area of interest in recent years following technological advances that enable non-invasive monitoring of autonomic nervous system regulation. However, the clinical interpretation of HRV features remain widely debated or unknown. Standardisation within studies of HRV in psychiatric disorders is poor, making it difficult to reproduce or build on previous work. Recently, a Guidelines for Reporting Articles on Psychiatry and Heart rate variability checklist has been proposed to address this issue. Here we assess studies of HRV in bipolar disorder and borderline personality disorder against this checklist and discuss the implication for ongoing research in this area.

Target speaker identification is essential for speech enhancement algorithms in assistive devices aimed towards helping the hearing impaired. Several recent studies have reported that target speaker identification is possible through electroencephalography (EEG) recordings. If the EEG system could be reduced to acceptable size while retaining the signal quality, hearing aids could benefit from the integration with concealed EEG. To compare the performance of a multichannel around-the-ear EEG system with high-density cap EEG recordings an envelope tracking algorithm was applied in a competitive speaker paradigm. The data from 20 normal hearing listeners were concurrently collected from the traditional state-of-the-art laboratory wired EEG system and a wireless mobile EEG system with two bilaterally-placed around-the-ear electrode arrays (cEEGrids). The results show that the cEEGrid ear-EEG technology captured neural signals that allowed the identification of the attended speaker above chance-level, with 69.3% accuracy, while cap-EEG signals resulted in the accuracy of 84.8%. Further analyses investigated the influence of ear-EEG signal quality and revealed that the envelope tracking procedure was unaffected by variability in channel impedances. We conclude that the quality of concealed ear-EEG recordings as acquired with the cEEGrid array has potential to be used in the brain-computer interface steering of hearing aids.

Simultaneous EEG-fMRI has proven to be useful in localizing interictal epileptic activity. However, the applicability of traditional GLM-based analysis is limited as interictal spikes are often not seen on the EEG inside the scanner. Therefore, we aim at extracting epileptic activity purely from the fMRI time series using independent component analysis (ICA). To our knowledge, we show for the first time that ICA can find sources related to epileptic activity in patients where no interictal spikes were recorded in the EEG. The epileptic components were identified retrospectively based on the known localization of the ictal onset zone (IOZ). We demonstrate that the selected components truly correspond to epileptic activity, as sources extracted from patients resemble significantly better the IOZ than sources found in healthy controls. Furthermore, we show that the epileptic components in patients with and without spikes recorded inside the scanner resemble the IOZ in the same degree. We conclude that ICA of fMRI has the potential to extend the applicability of EEG-fMRI for presurgical evaluation in epilepsy.

Cognitive task demands in one sensory modality (T1) can have beneficial effects on a secondary task (T2) in a different modality, due to reduced top-down control needed to inhibit the secondary task, as well as crossmodal spread of attention. This contrasts findings of cognitive load compromising a secondary modality's processing. We manipulated cognitive load within one modality (visual) and studied the consequences of cognitive demands on secondary (auditory) processing. 15 healthy participants underwent a simultaneous EEG-fMRI experiment. Data from 8 participants were obtained outside the scanner for validation purposes. The primary task (T1) was to respond to a visual working memory (WM) task with four conditions, while the secondary task (T2) consisted of an auditory oddball stream, which participants were asked to ignore. The fMRI results revealed fronto-parietal WM network activations in response to T1 task manipulation. This was accompanied by significantly higher reaction times and lower hit rates with increasing task difficulty which confirmed successful manipulation of WM load. Amplitudes of auditory evoked potentials, representing fundamental auditory processing showed a continuous augmentation which demonstrated a systematic relation to cross-modal cognitive load. With increasing WM load, primary auditory cortices were increasingly deactivated while psychophysiological interaction results suggested the emergence of auditory cortices connectivity with visual WM regions. These results suggest differential effects of crossmodal attention on fundamental auditory processing. We suggest a continuous allocation of resources to brain regions processing primary tasks when challenging the central executive under high cognitive load.