The power of ECG in multimodal patient-specific seizure monitoring: Added value to an EEG-based detector using limited channels

Epileptic seizure detection using heart rate variability from ambulatory ECG: a pseudoprospective study

Objective.Seizure detection algorithms enable clinicians to accurately assess seizure burden for epilepsy diagnosis and long-term management. State-of-the-art algorithms rely on electroencephalography (EEG) data to identify electrographic seizures. Previous research that used non-EEG signals, such as electrocardiography (ECG) and wristband data, were collected in epilepsy monitoring units. We aimed to investigate the feasibility of ECG seizure detection in ambulatory settings.Approach.We developed a patient-independent, machine learning-based seizure detector using ambulatory long-term ECG monitoring data. The model was trained on long-term studies of 47 patients and evaluated pseudoprospectively using event detection on a hold-out test set of 18 patients.Main results.In the hold-out test set, the seizure detector performed better than chance for 14 out of 18 patients. The average sensitivity was 72% and the average specificity was 68% for the whole test cohort. Overall, across training and test sets, the performance was better for patients diagnosed with focal epilepsy and for patients who were identified as responders (had substantial heart rate changes during seizures).Significance.Key contributions of this study include the development of a patient-independent seizure detector using ambulatory data and the introduction of a pseudoprospective evaluation framework, which can benefit chronic ambulatory seizure monitoring.

Seizure Detection Devices

Goals of automated detection of epileptic seizures using wearable devices include objective documentation of seizures, prevention of sudden unexpected death in epilepsy (SUDEP) and seizure-related injuries, obviating both the unpredictability of seizures and potential social embarrassment, and finally to develop seizure-triggered on-demand therapies. Automated seizure detection devices are based on the analysis of EEG signals (scalp-EEG, subcutaneous EEG and intracranial EEG), of motor manifestations of seizures (surface EMG, accelerometry), and of physiologic autonomic changes caused by seizures (heart and respiration rate, oxygen saturation, sweat secretion, body temperature). While the detection of generalized tonic-clonic and of focal to bilateral tonic-clonic seizures can be achieved with high sensitivity and low false alarm rates, the detection of focal seizures is still suboptimal, especially in the everyday ambulatory setting. Multimodal seizure detection devices in general provide better performance than devices based on single measurement parameters. Long-term use of seizure detection devices in home environments helps to improve the accuracy of seizure diaries and to reduce seizure-related injuries, while evidence for prevention of SUDEP is still lacking. Automated seizure detection devices are generally well accepted by patients and caregivers.

Effects of epileptic seizures on the quality of biosignals recorded from wearables

OBJECTIVE

Wearable nonelectroencephalographic biosignal recordings captured from the wrist offer enormous potential for seizure monitoring. However, signal quality remains a challenging factor affecting data reliability. Models trained for seizure detection depend on the quality of recordings in peri-ictal periods in performing a feature-based separation of ictal periods from interictal periods. Thus, this study aims to investigate the effect of epileptic seizures on signal quality, ensuring accurate and reliable monitoring.

METHODS

This study assesses the signal quality of wearable data during peri-ictal phases of generalized tonic-clonic and focal to bilateral tonic-clonic seizures (TCS), focal motor seizures (FMS), and focal nonmotor seizures (FNMS). We evaluated accelerometer (ACC) activity and the signal quality of electrodermal activity (EDA) and blood volume pulse (BVP) data. Additionally, we analyzed the influence of peri-ictal movements as assessed by ACC (ACC activity) on signal quality and examined intraictal subphases of focal to bilateral TCS.

RESULTS

We analyzed 386 seizures from 111 individuals in three international epilepsy monitoring units. BVP signal quality and ACC activity levels differed between all seizure types. We found the largest decrease in BVP signal quality and increase in ACC activity when comparing the ictal phase to the pre- and postictal phases for TCS. Additionally, ACC activity was strongly negatively correlated with BVP signal quality for TCS and FMS, and weakly for FNMS. Intraictal analysis revealed that tonic and clonic subphases have the lowest BVP signal quality and the highest ACC activity.

SIGNIFICANCE

Motor elements of seizures significantly impair BVP signal quality, but do not have significant effect on EDA signal quality, as assessed by wrist-worn wearables. The results underscore the importance of signal quality assessment methods and careful selection of robust modalities to ensure reliable seizure detection. Future research is needed to explain whether seizure detection models' decisions are based on signal responses induced by physiological processes as opposed to artifacts.

Cardiorespiratory disturbances in focal impaired awareness seizures: Insights from wearable ECG monitoring

PURPOSE

Seizures are characterized by periictal autonomic changes. Wearable devices could help improve our understanding of these phenomena through long-term monitoring. In this study, we used wearable electrocardiogram (ECG) data to evaluate differences between temporal and extratemporal focal impaired awareness (FIA) seizures monitored in the hospital and at home. We assessed periictal heart rate, respiratory rate, heart rate variability (HRV), and respiratory sinus arrhythmia (RSA).

METHODS

We extracted ECG signals across three time points - five minutes baseline and preictal, ten minutes postictal - and the seizure duration. After automatic Rpeak selection, we calculated the heart rate and estimated the respiratory rate using the ECG-derived respiration methodology. HRV was calculated in both time and frequency domains. To evaluate the influence of other modulators on the HRV after removing the respiratory influences, we recalculated the residual power in the high-frequency (HF) and low-frequency (LF) bands using orthogonal subspace projections. Finally, 5-minute and 30-second (ultra-short) ECG segments were used to calculate RSA using three different methods. Seizures from temporal and extratemporal origins were compared using mixed-effects models and estimated marginal means.

RESULTS

The mean preictal heart rate was 69.95 bpm (95 % CI 65.6 - 74.3), and it increased to 82 bpm, 95 % CI (77.51 - 86.47) and 84.11 bpm, 95 % CI (76.9 - 89.5) during the ictal and postictal periods. Preictal, ictal and postictal respiratory rates were 16.1 (95 % CI 15.2 - 17.1), 14.8 (95 % CI 13.4 - 16.2) and 15.1 (95 % CI 14 - 16.2), showing not statistically significant bradypnea. HRV analysis found a higher baseline power in the LF band, which was still significantly higher after removing the respiratory influences. Postictally, we found decreased power in the HF band and the respiratory influences in both frequency bands. The RSA analysis with the new methods confirmed the lower cardiorespiratory interaction during the postictal period. Additionally, using ultra-short ECG segments, we found that RSA decreases before the electroclinical seizure onset. No differences were observed in the studied parameters between temporal and extratemporal seizures.

CONCLUSIONS

We found significant increases in the ictal and postictal heart rates and lower respiratory rates. Isolating the respiratory influences on the HRV showed a postictal reduction of respiratory modulations on both LF and HF bands, suggesting a central role of respiratory influences in the periictal HRV, unlike the baseline measurements. We found a reduced cardiorespiratory interaction during the periictal period using other RSA methods, suggesting a blockade in vagal efferences before the electroclinical onset. These findings highlight the importance of respiratory influences in cardiac dynamics during seizures and emphasize the need to longitudinally assess HRV and RSA to gain insights into long-term autonomic dysregulation.

AI in ECG: Validating an ambulatory semiology labeller and predictor

OBJECTIVES

Early prediction of epileptic seizures can help reduce morbidity and mortality. In this work, we explore using electrocardiographic (ECG) signal as input to a seizure prediction system and note that the performance can be improved by using selected signal processing techniques.

METHODS

We used frequency domain analysis with a deep neural network backend for all our experiments in this work. We further analysed the effect of the proposed system for different seizure semiologies and prediction horizons. We explored refining the signal using signal processing to enhance the system's performance.

RESULTS

Our final system using the Temple University Hospital's Seizure (TUHSZ) corpus gave an overall prediction accuracy of 84.02 %, sensitivity of 87.59 %, specificity of 81.9 %, and an area under the receiver operating characteristic curve (AUROC) of 0.9112. Notably, these results surpassed the state-of-the-art outcomes reported using the TUHSZ database; all findings are statistically significant. We also validated our study using the Siena scalp EEG database. Using the frequency domain data, our baseline system gave a performance of 75.17 %, 79.17 %, 70.04 % and 0.82 for prediction accuracy, sensitivity, specificity and AUROC, respectively. After selecting the optimal frequency band of 0.8-15 Hz, we obtained a performance of 80.49 %, 89.51 %, 75.23 % and 0.89 for prediction accuracy, sensitivity, specificity and AUROC, respectively which is an improvement of 5.32 %, 10.34 %, 5.19 % and 0.08 for prediction accuracy, sensitivity, specificity and AUROC, respectively.

CONCLUSIONS

The seizure information in ECG is concentrated in a narrow frequency band. Identifying and selecting that band can help improve the performance of seizure detection and prediction.

SIGNIFICANCE

EEG is susceptible to artefacts and is not preferred in a low-cost ambulatory device. ECG can be used in wearable devices (like chest bands) and is feasible for developing a low-cost ambulatory device for seizure prediction. Early seizure prediction can provide patients and clinicians with the required alert to take necessary precautions and prevent a fatality, significantly improving the patient's quality of life.

Exploring the potential of pretrained CNNs and time-frequency methods for accurate epileptic EEG classification: a comparative study

Prompt diagnosis of epilepsy relies on accurate classification of automated electroencephalogram (EEG) signals. Several approaches have been developed to characterize epileptic EEG data; however, none of them have exploited time-frequency data to evaluate the effect of tweaking parameters in pretrained frameworks for EEG data classification. This study compares the performance of several pretrained convolutional neural networks (CNNs) namely, AlexNet, GoogLeNet, MobileNetV2, ResNet-18 and SqueezeNet for the localization of epilepsy EEG data using various time-frequency data representation algorithms. Continuous wavelet transform (CWT), empirical Fourier decomposition (EFD), empirical mode decomposition (EMD), empirical wavelet transform (EWT), and variational mode decomposition (VMD) were exploited for the acquisition of 2D scalograms from 1D data. The research evaluates the effect of multiple factors, including noisy versus denoised scalograms, different optimizers, learning rates, single versus dual channels, model size, and computational time consumption. The benchmark Bern-Barcelona EEG dataset is used for testing purpose. Results obtained show that the combination of MobileNetV2, Continuous Wavelet Transform (CWT) and Adam optimizer at a learning rate of 10-4, coupled with dual-data channels, provides the best performance metrics. Specifically, these parameters result in optimal sensitivity, specificity, f1-score, and classification accuracy, with respective values of 96.06%, 96.15%, 96.08%, and 96.10%. To further corroborate the efficacy of opted pretrained models on exploited Signal Decomposition (SD) algorithms, the classifiers are also being simulated on Temple University database at pinnacle modeling composition. A similar pattern in the outcome readily validate the findings of our study and robustness of deep learning models on epilepsy EEG scalograms.The conclusions drawn emphasize the potential of pretrained CNN-based models to create a robust, automated system for diagnosing epileptiform. Furthermore, the study offers insights into the effectiveness of varying time-frequency techniques and classifier parameters for classifying epileptic EEG data.

A personalized earbud for non-invasive long-term EEG monitoring

Objective. The primary objective of this study was to evaluate the reliability, comfort, and performance of a custom-fit, non-invasive long-term electrophysiologic headphone, known as Aware Hearable, for the ambulatory recording of brain activities. These recordings play a crucial role in diagnosing neurological disorders such as epilepsy and in studying neural dynamics during daily activities.Approach.The study uses commercial manufacturing processes common to the hearing aid industry, such as 3D scanning, computer-aided design modeling, and 3D printing. These processes enable the creation of the Aware Hearable with a personalized, custom-fit, thereby ensuring complete and consistent contact with the inner surfaces of the ear for high-quality data recordings. Additionally, the study employs a machine learning data analysis approach to validate the recordings produced by Aware Hearable, by comparing them to the gold standard intracranial electroencephalography recordings in epilepsy patients.Main results.The results indicate the potential of Aware Hearable to expedite the diagnosis of epilepsy by enabling extended periods of ambulatory recording.Significance.This offers significant reductions in burden to patients and their families. Furthermore, the device's utility may extend to a broader spectrum, making it suitable for other applications involving neurophysiological recordings in real-world settings.

Seizure Detection, Prediction, and Forecasting

SUMMARY

Among the many fears associated with seizures, patients with epilepsy are greatly frustrated and distressed over seizure's apparent unpredictable occurrence. However, increasing evidence have emerged over the years to support that seizure occurrence is not a random phenomenon as previously presumed; it has a cyclic rhythm that oscillates over multiple timescales. The pattern in rises and falls of seizure rate that varies over 24 hours, weeks, months, and years has become a target for the development of innovative devices that intend to detect, predict, and forecast seizures. This article will review the different tools and devices available or that have been previously studied for seizure detection, prediction, and forecasting, as well as the associated challenges and limitations with the utilization of these devices. Although there is strong evidence for rhythmicity in seizure occurrence, very little is known about the mechanism behind this oscillation. This article concludes with early insights into the regulations that may potentially drive this cyclical variability and future directions.

Differentiation of subclinical and clinical electrographic events in long-term electroencephalographic recordings

OBJECTIVE

With the advent of ultra-long-term recordings for monitoring of epilepsies, the interpretation of results of isolated electroencephalographic (EEG) recordings covering only selected brain regions attracts considerable interest. In this context, the question arises of whether detected ictal EEG patterns correspond to clinically manifest seizures or rather to purely electrographic events, that is, subclinical events.

METHODS

EEG patterns from 268 clinical seizures and 252 subclinical electrographic events from 50 patients undergoing video-EEG monitoring were analyzed. Features extracted included predominant frequency band, duration, association with rhythmic muscle artifacts, spatial extent, and propagation patterns. Classification using logistic regression was performed based on data from the whole dataset of 10-20 system EEG recordings and from a subset of two temporal electrode contacts.

RESULTS

Correct separation of clinically manifest and purely electrographic events based on 10-20 system EEG recordings was possible in up to 83.8% of events, depending on the combination of features included. Correct classification based on two-channel recordings was only slightly inferior, achieving 78.6% accuracy; 74.4% and 74.8%, respectively, of events could be correctly classified when using duration alone with either electrode set, although classification accuracies were lower for some subgroups of seizures, particularly focal aware seizures and epileptic arousals.

SIGNIFICANCE

A correct classification of subclinical versus clinical EEG events was possible in 74%-83% of events based on full EEG recordings, and in 74%-78% when considering only a subset of two electrodes, matching the channel number available from new implantable diagnostic devices. This is a promising outcome, suggesting that ultra-long-term low-channel EEG recordings may provide sufficient information for objective seizure diaries. Intraindividual optimization using high numbers of ictal events may further improve separation, provided that supervised learning with external validation is feasible.

Wearable detection of tonic seizures in childhood epilepsy: An exploratory cohort study

OBJECTIVE

To investigate the performance of a multimodal wearable device for the offline detection of tonic seizures (TS) in a pediatric childhood epilepsy cohort, with a focus on patients with Lennox-Gastaut syndrome.

METHODS

Parallel with prolonged video-electroencephalography (EEG), the Plug 'n Patch system, a multimodal wearable device using the Sensor Dot and replaceable electrode adhesives, was used to detect TS. Multiple biosignals were recorded: behind-the-ear EEG, surface electromyography, electrocardiography, and accelerometer/gyroscope. Biosignals were annotated blindly by a neurologist. Seizure characteristics were described, and performance was assessed by sensitivity, positive predictive value (PPV), F1 score, and false alarm rate (FAR) per hour. Performance was compared to seizure diaries kept by the caretaker.

RESULTS

Ninety-nine TS were detected in 13 patients. Seven patients (54%) had Lennox-Gastaut syndrome and six patients (46%) had other forms of (developmental) epileptic encephalopathies or drug-resistant epilepsy. All but one patient had intellectual disability. Overall sensitivity was 41%, with a PPV of 9%, an F1 score of 14%, and a median FAR per hour of 0.75. Performance increased to an F1 score of 66% for nightly seizures lasting at least 10 s (sensitivity 66%, PPV 66%) and 71% for nightly seizures lasting at least 20 s (sensitivity 62%, PPV 82%). For these seizures there were no false alarms in 10 of 13 patients. Sensitivity of seizure diaries reached a maximum of 52% for prolonged (≥20 s) nightly seizures, even though caretakers slept in the same room.

SIGNIFICANCE

We showed that it is feasible to use a multimodal wearable device with multiple adhesive sites in children with epilepsy and intellectual disability. For prolonged nightly seizures, offline manual detection of TS outperformed seizure diaries. The recognition of seizure-specific signatures using multiple modalities can help in the development of automated TS detection algorithms.

Non-electroencephalogram-based seizure detection devices: State of the art and future perspectives

INTRODUCTION AND PURPOSE

The continuously expanding research and development of wearable devices for automated seizure detection in epilepsy uses mostly non-invasive technology. Real-time alarms, triggered by seizure detection devices, are needed for safety and prevention to decrease seizure-related morbidity and mortality, as well as objective quantification of seizure frequency and severity. Our review strives to provide a state-of-the-art on automated seizure detection using non-invasive wearable devices in an ambulatory (home) environment and to highlight the prospects for future research.

METHODS

A joint working group of the International League Against Epilepsy (ILAE) and the International Federation of Clinical Neurophysiology (IFCN) recently published a clinical practice guideline on automated seizure detection using wearable devices. We updated the systematic literature search for the period since the last search by the joint working group. We selected studies qualifying minimally as phase-2 clinical validation trials, in accordance with standards for testing and validation of seizure detection devices.

RESULTS

High-level evidence (phases 3 and 4) is available only for the detection of tonic-clonic seizures and major motor seizures when using wearable devices based on accelerometry, surface electromyography (EMG), or a multimodal device combining accelerometry and heart rate. The reported sensitivity of these devices is 79.4-96%, with a false alarm rate of 0.20-1.92 per 24 hours (0-0.03 per night). A single phase-3 study validated the detection of absence seizures using a single-channel wearable EEG device. Two phase-4 studies showed overall user satisfaction with wearable seizure detection devices, which helped decrease injuries related to tonic-clonic seizures. Overall satisfaction, perceived sensitivity, and improvement in quality-of-life were significantly higher for validated devices.

CONCLUSIONS

Among the vast number of studies published on seizure detection devices, most are strongly affected by potential bias, providing a too-optimistic perspective. By applying the standards for clinical validation studies, potential bias can be reduced, and the quality of a continuously growing number of studies in this field can be assessed and compared. The ILAE-IFCN clinical practice guideline on automated seizure detection using wearable devices recommends using clinically validated wearable devices for automated detection of tonic-clonic seizures when significant safety concerns exist. The studies published after the guideline was issued only provide incremental knowledge and would not change the current recommendations.

Mapping of Neuro-Cardiac Electrophysiology: Interlinking Epilepsy and Arrhythmia

The interplay between neurology and cardiology has gained significant attention in recent years, particularly regarding the shared pathophysiological mechanisms and clinical comorbidities observed in epilepsy and arrhythmias. Neuro-cardiac electrophysiology mapping involves the comprehensive assessment of both neural and cardiac electrical activity, aiming to unravel the intricate connections and potential cross-talk between the brain and the heart. The emergence of artificial intelligence (AI) has revolutionized the field by enabling the analysis of large-scale data sets, complex signal processing, and predictive modeling. AI algorithms have been applied to neuroimaging, electroencephalography (EEG), electrocardiography (ECG), and other diagnostic modalities to identify subtle patterns, classify disease subtypes, predict outcomes, and guide personalized treatment strategies. In this review, we highlight the potential clinical implications of neuro-cardiac mapping and AI in the management of epilepsy and arrhythmias. We address the challenges and limitations associated with these approaches, including data quality, interpretability, and ethical considerations. Further research and collaboration between neurologists, cardiologists, and AI experts are needed to fully unlock the potential of this interdisciplinary field.

The future of wearable EEG: a review of ear-EEG technology and its applications

Objective.This review paper provides a comprehensive overview of ear-electroencephalogram (EEG) technology, which involves recording EEG signals from electrodes placed in or around the ear, and its applications in the field of neural engineering.Approach.We conducted a thorough literature search using multiple databases to identify relevant studies related to ear-EEG technology and its various applications. We selected 123 publications and synthesized the information to highlight the main findings and trends in this field.Main results.Our review highlights the potential of ear-EEG technology as the future of wearable EEG technology. We discuss the advantages and limitations of ear-EEG compared to traditional scalp-based EEG and methods to overcome those limitations. Through our review, we found that ear-EEG is a promising method that produces comparable results to conventional scalp-based methods. We review the development of ear-EEG sensing devices, including the design, types of sensors, and materials. We also review the current state of research on ear-EEG in different application areas such as brain-computer interfaces, and clinical monitoring.Significance.This review paper is the first to focus solely on reviewing ear-EEG research articles. As such, it serves as a valuable resource for researchers, clinicians, and engineers working in the field of neural engineering. Our review sheds light on the exciting future prospects of ear-EEG, and its potential to advance neural engineering research and become the future of wearable EEG technology.

Out-of-hospital multimodal seizure detection: a pilot study

Background

Out-of-hospital seizure detection aims to provide clinicians and patients with objective seizure documentation in efforts to improve the clinical management of epilepsy. In-patient studies have found that combining different modalities helps improve the seizure detection accuracy. In this study, the objective was to evaluate the viability of out-of-hospital seizure detection using wearable ECG, accelerometry and behind-the-ear electroencephalography (EEG). Furthermore, we examined the signal quality of out-of-hospital EEG recordings.

Methods

Seventeen patients were monitored for up to 5 days. A support vector machine based seizure detection algorithm was applied using both in-patient seizures and out-of-hospital electrographic seizures in one patient. To assess the content of noise in the EEG signal, we compared the root-mean-square (RMS) of the recordings to a reference threshold derived from manually categorised segments of EEG recordings.

Results

In total 1427 hours of continuous EEG was recorded. In one patient, we identified 15 electrographic focal impaired awareness seizures with a motor component. After training our algorithm on in-patient data, we found a sensitivity of 91% and a false alarm rate (FAR) of 18/24 hours for the detection of out-of-hospital seizures using a combination of EEG and ECG recordings. We estimated that 30.1% of the recorded EEG signal was physiological EEG, with an RMS value within the reference threshold.

Conclusion

We found that detection of out-of-hospital focal impaired awareness seizures with a motor component is possible and that applying multiple modalities improves the diagnostic accuracy compared with unimodal EEG. However, significant challenges remain regarding a high FAR and that only 30.1% of the EEG data represented usable signal.

Electrocardiogram Changes in the Postictal Phase of Epileptic Seizure: Results from a Prospective Study

BACKGROUND

The brain and heart are strictly linked and the electrical physiologies of these organs share common pathways and genes. Epilepsy patients have a higher prevalence of electrocardiogram (ECG) abnormalities compared to healthy people. Furthermore, the relationship between epilepsy, genetic arrhythmic diseases and sudden death is well known. The association between epilepsy and myocardial channelopathies, although already proposed, has not yet been fully demonstrated. The aim of this prospective observational study is to assess the role of the ECG after a seizure.

MATERIALS AND METHODS

From September 2018 to August 2019, all patients admitted to the emergency department of San Raffaele Hospital with a seizure were enrolled in the study; for each patient, neurological, cardiological and ECG data were collected. The ECG was performed at the time of the admission (post-ictal ECG) and 48 h later (basal ECG) and analyzed by two blinded expert cardiologists looking for abnormalities known to indicate channelopathies or arrhythmic cardiomyopathies. In all patients with abnormal post-ictal ECG, next generation sequencing (NGS) analysis was performed.

RESULTS

One hundred and seventeen patients were enrolled (females: 45, median age: 48 ± 12 years). There were 52 abnormal post-ictal ECGs and 28 abnormal basal ECGs. All patients with an abnormal basal ECG also had an abnormal post-ictal ECG. In abnormal post-ictal ECG, a Brugada ECG pattern (BEP) was found in eight patients (of which two had BEP type I) and confirmed in two basal ECGs (of which zero had BEP type I). An abnormal QTc interval was identified in 20 patients (17%), an early repolarization pattern was found in 4 patients (3%) and right precordial abnormalities were found in 5 patients (4%). Any kind modification of post-ictal ECG was significantly more pronounced in comparison with an ECG recorded far from the seizure (p = 0.003). A 10:1 higher prevalence of a BEP of any type (particularly in post-ictal ECG, p = 0.04) was found in our population compared to general population. In three patients with post-ictal ECG alterations diagnostic for myocardial channelopathy (BrS and ERP), not confirmed at basal ECG, a pathogenic gene variant was identified (KCNJ8, PKP2 and TRMP4).

CONCLUSION

The 12-lead ECG after an epileptic seizure may show disease-related alterations otherwise concealed in a population at a higher incidence of sudden death and channelopathies. Post-ictal BEP incidence was higher in cases of nocturnal seizure.

Electrocardiogram Monitoring Wearable Devices and Artificial-Intelligence-Enabled Diagnostic Capabilities: A Review

Worldwide, population aging and unhealthy lifestyles have increased the incidence of high-risk health conditions such as cardiovascular diseases, sleep apnea, and other conditions. Recently, to facilitate early identification and diagnosis, efforts have been made in the research and development of new wearable devices to make them smaller, more comfortable, more accurate, and increasingly compatible with artificial intelligence technologies. These efforts can pave the way to the longer and continuous health monitoring of different biosignals, including the real-time detection of diseases, thus providing more timely and accurate predictions of health events that can drastically improve the healthcare management of patients. Most recent reviews focus on a specific category of disease, the use of artificial intelligence in 12-lead electrocardiograms, or on wearable technology. However, we present recent advances in the use of electrocardiogram signals acquired with wearable devices or from publicly available databases and the analysis of such signals with artificial intelligence methods to detect and predict diseases. As expected, most of the available research focuses on heart diseases, sleep apnea, and other emerging areas, such as mental stress. From a methodological point of view, although traditional statistical methods and machine learning are still widely used, we observe an increasing use of more advanced deep learning methods, specifically architectures that can handle the complexity of biosignal data. These deep learning methods typically include convolutional and recurrent neural networks. Moreover, when proposing new artificial intelligence methods, we observe that the prevalent choice is to use publicly available databases rather than collecting new data.

Seizure detection with reduced electroencephalogram channels: research trends and outlook

Epilepsy is a prevalent condition characterized by recurrent, unpredictable seizures. Monitoring with surface electroencephalography (EEG) is the gold standard for diagnosing epilepsy, but a time-consuming, uncomfortable and sometimes ineffective process for patients. Further, using EEG over a brief monitoring period has variable success, dependent on patient tolerance and seizure frequency. The availability of hospital resources and hardware and software specifications inherently restrict the options for comfortable, long-term data collection, resulting in limited data for training machine-learning models. This mini-review examines the current patient journey, providing an overview of the current state of EEG monitoring with reduced electrodes and automated channel reduction methods. Opportunities for improving data reliability through multi-modal data fusion are suggested. We assert the need for further research in electrode reduction to advance brain monitoring solutions towards portable, reliable devices that simultaneously offer patient comfort, perform ultra-long-term monitoring and expedite the diagnosis process.

The Power of ECG in Semi-Automated Seizure Detection in Addition to Two-Channel behind-the-Ear EEG

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.

Seizure detection based on wearable devices: A review of device, mechanism, and algorithm

With sudden and unpredictable nature, seizures lead to great risk of the secondary damage, status epilepticus, and sudden unexpected death in epilepsy. Thus, it is essential to use a wearable device to detect seizure and inform patients' caregivers for assistant to prevent or relieve adverse consequence. In this review, we gave an account of the current state of the field of seizure detection based on wearable devices from three parts: devices, physiological activities, and algorithms. Firstly, seizure monitoring devices available in the market primarily involve wristband-type devices, patch-type devices, and armband-type devices, which are able to detect motor seizures, focal autonomic seizures, or absence seizures. Secondly, seizure-related physiological activities involve the discharge of brain neurons presented, autonomous nervous activities, and motor. Plenty of studies focus on features from one signal, while it is a lack of evidences about the change of signal coupling along with seizures. Thirdly, the seizure detection algorithms developed from simple threshold method to complicated machine learning and deep learning, aiming at distinguish seizures from normal events. After understanding of some preliminary studies, we will propose our own thought for future development in this field.

Sleep in children with refractory epilepsy and epileptic encephalopathies: A systematic review of literature

Children with epilepsy have more sleep disorders compared to healthy children. The bidirectional interaction between epilepsy and sleep is not completely understood. However, disruption of sleep architecture during childhood may have consequences for cognitive development. As children with drug-refractory epilepsy often have intellectual disability, sleep disruption could be an important contributing factor in severity of their cognitive impairment. To better understand these interactions, sleep architecture in children with drug-refractory epilepsy and epileptic encephalopathies should be investigated. In this review, we conducted a systematic literature search on this topic. Articles that investigated sleep macro- and/or microstructure by means of electroencephalogram/polysomnography were included, as well as articles that used validated questionnaires. Sixteen articles were reviewed, eight of which used polysomnography. Only 2 articles examined sleep in children with epileptic encephalopathies. Consistent findings on measures of sleep architecture were a reduction in REM percentage and an increase in sleep fragmentation when comparing drug-refractory patients with non-refractory and healthy subjects. The findings on slow wave sleep were less clear. Studies with questionnaires unambiguously confirmed subjectively more sleep problems in children with drug-refractory epilepsy. This is the first review of literature in this patient population. More good quality sleep studies in children with drug-refractory epilepsy are warranted. The use of wearables in the home setting together with automatic sleep staging could provide more insights.

A multimodal AI system for out-of-distribution generalization of seizure identification

Artificial intelligence (AI) and health sensory data-fusion hold the potential to automate many laborious and time-consuming processes in hospitals or ambulatory settings, e.g. home monitoring and telehealth. One such unmet challenge is rapid and accurate epileptic seizure annotation. An accurate and automatic approach can provide an alternative way to label seizures in epilepsy or deliver a substitute for inaccurate patient self-reports. Multimodal sensory fusion is believed to provide an avenue to improve the performance of AI systems in seizure identification. We propose a state-of-the-art performing AI system that combines electroencephalogram (EEG) and electrocardiogram (ECG) for seizure identification, tested on clinical data with early evidence demonstrating generalization across hospitals. The model was trained and validated on the publicly available Temple University Hospital (TUH) dataset. To evaluate performance in a clinical setting, we conducted non-patient-specific pseudo-prospective inference tests on three out-of-distribution datasets, including EPILEPSIAE (30 patients) and the Royal Prince Alfred Hospital (RPAH) in Sydney, Australia (31 neurologists-shortlisted patients and 30 randomly selected). Our multimodal approach improves the area under the receiver operating characteristic curve (AUC-ROC) by an average margin of 6.71% and 14.42% for deep learning techniques using EEG-only and ECG-only, respectively. Our model's state-of-the-art performance and robustness to out-of-distribution datasets show the accuracy and efficiency necessary to improve epilepsy diagnoses. To the best of our knowledge, this is the first pseudo-prospective study of an AI system combining EEG and ECG modalities for automatic seizure annotation achieved with fusion of two deep learning networks.

Automatic annotation correction for wearable EEG based epileptic seizure detection

OBJECTIVE

Video-electroencephalography (vEEG), which defines the ground truth for the detection of epileptic seizures, is inadequate for long-term home monitoring. Thanks to their advantages in comfort and unobtrusiveness, wearable EEG devices have been suggested as a solution for home monitoring. However, one of the challenges in data-driven automated seizure detection with wearable EEG data is to have reliable seizure annotations. Seizure annotations on the gold-standard 25-channel vEEG recordings may not be optimal to delineate seizure activity on the concomitantly recorded wearable EEG, due to artifacts or absence of ictal activity on the limited set of electrodes of the wearable EEG. This paper aims to develop an automatic approach to correct the imperfect annotations of seizure activity on wearable EEG, which can be used to train seizure detection algorithms.

APPROACH

This paper first investigates the effectiveness of correcting the seizure annotations for the training set with a visual annotation correction. Then a novel approach has been proposed to automatically remove non-seizure data from wearable EEG in epochs annotated as seizures in gold-standard video-EEG recordings. The performance of the automatic annotation correction approach was evaluated by comparing the seizure detection models trained with 1. original vEEG seizure annotations, 2. visually corrected seizure annotations, and 3. automatically corrected seizure annotations.

RESULTS

The automatic seizure detection approach trained with automatically corrected seizure annotations was more sensitive and had fewer false-positive detections compared to the approach trained with visually corrected seizure annotations, and the approach trained with the original seizure annotations from gold-standard vEEG.

SIGNIFICANCE

The wearable EEG seizure detection approach performs better when trained with automatic seizure annotation correction.