Epileptic seizure onset detection based on EEG and ECG data fusion

Heart Rate Variability as a Tool for Seizure Prediction: A Scoping Review

The most critical burden for People with Epilepsy (PwE) is represented by seizures, the unpredictability of which severely impacts quality of life. The design of real-time warning systems that can detect or even predict ictal events would enhance seizure management, leading to high benefits for PwE and their caregivers. In the past, various research works highlighted that seizure onset is anticipated by significant changes in autonomic cardiac control, which can be assessed through heart rate variability (HRV). This manuscript conducted a scoping review of the literature analyzing HRV-based methods for detecting or predicting ictal events. An initial search on the PubMed database returned 402 papers, 72 of which met the inclusion criteria and were included in the review. These results suggest that seizure detection is more accurate in neonatal and pediatric patients due to more significant autonomic modifications during the ictal transitions. In addition, conventional metrics are often incapable of capturing cardiac autonomic variations and should be replaced with more advanced methodologies, considering non-linear HRV features and machine learning tools for processing them. Finally, studies investigating wearable systems for heart monitoring denoted how HRV constitutes an efficient biomarker for seizure detection in patients presenting significant alterations in autonomic cardiac control during ictal events.

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.

Neonatal Seizure Detection Using a Wearable Multi-Sensor System

Neonatal seizure is an important clinical symptom of brain dysfunction, which is more common in infancy than in childhood. At present, video electroencephalogram (VEEG) technology is widely used in clinical practice. However, video electroencephalogram technology has several disadvantages. For example, the wires connecting the medical instruments may interfere with the infant's movement and the gel patch electrode or disk electrode commonly used to monitor EEG may cause skin allergies or even tears. For the above reasons, we developed a wearable multi-sensor platform for newborns to collect physiological and movement signals. In this study, we designed a second-generation multi-sensor platform and developed an automatic detection algorithm for neonatal seizures based on ECG, respiration and acceleration. Data for 38 neonates were recorded at the Children's Hospital of Fudan University in Shanghai. The total recording time was approximately 300 h. Four of the patients had seizures during data collection. The total recording time for the four patients was approximately 34 h, with 30 seizure episodes recorded. These data were evaluated by the algorithm. To evaluate the effectiveness of combining ECG, respiration and movement, we compared the performance of three types of seizure detectors. The first detector included features from ECG, respiration and acceleration records; the second detector incorporated features based on respiratory movement from respiration and acceleration records; and the third detector used only ECG-based features from ECG records. Our study illustrated that, compared with the detector utilizing individual modal features, multi-modal feature detectors could achieve favorable overall performance, reduce false alarm rates and give higher F-measures.

Longitudinally tracking personal physiomes for precision management of childhood epilepsy

Our current understanding of human physiology and activities is largely derived from sparse and discrete individual clinical measurements. To achieve precise, proactive, and effective health management of an individual, longitudinal, and dense tracking of personal physiomes and activities is required, which is only feasible by utilizing wearable biosensors. As a pilot study, we implemented a cloud computing infrastructure to integrate wearable sensors, mobile computing, digital signal processing, and machine learning to improve early detection of seizure onsets in children. We recruited 99 children diagnosed with epilepsy and longitudinally tracked them at single-second resolution using a wearable wristband, and prospectively acquired more than one billion data points. This unique dataset offered us an opportunity to quantify physiological dynamics (e.g., heart rate, stress response) across age groups and to identify physiological irregularities upon epilepsy onset. The high-dimensional personal physiome and activity profiles displayed a clustering pattern anchored by patient age groups. These signatory patterns included strong age and sex-specific effects on varying circadian rhythms and stress responses across major childhood developmental stages. For each patient, we further compared the physiological and activity profiles associated with seizure onsets with the personal baseline and developed a machine learning framework to accurately capture these onset moments. The performance of this framework was further replicated in another independent patient cohort. We next referenced our predictions with the electroencephalogram (EEG) signals on selected patients and demonstrated that our approach could detect subtle seizures not recognized by humans and could detect seizures prior to clinical onset. Our work demonstrated the feasibility of a real-time mobile infrastructure in a clinical setting, which has the potential to be valuable in caring for epileptic patients. Extension of such a system has the potential to be leveraged as a health management device or longitudinal phenotyping tool in clinical cohort studies.

BHI-Net: Brain-Heart Interaction-Based Deep Architectures for Epileptic Seizures and Firing Location Detection

Automatic detection of epileptic seizures is still a challenging problem due to the intolerance of EEG. Introducing ECG can help with EEG for detecting seizures. However, the existing methods depended on fusing either the extracted features or the classification results of EEG-only and ECG-only with ignoring the interaction between them, so the detection rate did not improve much. Also, all EEG channels were considered in a complex manner. Moreover, the detection of epilepsy firing location, which is an important issue for diagnosing epilepsy, is not considered before. Therefore, we propose a new method based on the brain-heart interaction (BHI) for detecting the seizure onset and its firing location in the brain with lower complexity and better performance. BHI allows us to study the nonlinear coupling and variation of phase-synchronization between brain regions and heart activity, which are effective for distinguishing seizures. In our method, the EEG channels are mapped into two surrogate channels to reduce the computational complexity. Moreover, the firing location detector is triggered only once the seizure is detected to save the system's power. Evaluation using different proposed classification networks based on the TUSZ, the largest available EEG/ECG dataset with 315 subjects and 7 seizure types, showed that our BHI method improves the sensitivity by 48% with only 4 false alarms/24h compared to using only EEG. Moreover, it outperforms the performance of the average human detector based on the quantitative EEG tools by achieving a sensitivity of 68.2% with 11.9 false alarms/ 24h and a latency of 11.94 sec.

A Comparison of Energy-Efficient Seizure Detectors for Implantable Neurostimulation Devices

Introduction

About 30% of epilepsy patients are resistant to treatment with antiepileptic drugs, and only a minority of these are surgical candidates. A recent therapeutic approach is the application of electrical stimulation in the early phases of a seizure to interrupt its spread across the brain. To accomplish this, energy-efficient seizure detectors are required that are able to detect a seizure in its early stages.

Methods

Three patient-specific, energy-efficient seizure detectors are proposed in this study: (i) random forest (RF); (ii) long short-term memory (LSTM) recurrent neural network (RNN); and (iii) convolutional neural network (CNN). Performance evaluation was based on EEG data (n = 40 patients) derived from a selected set of surface EEG electrodes, which mimic the electrode layout of an implantable neurostimulation system. As for the RF input, 16 features in the time- and frequency-domains were selected. Raw EEG data were used for both CNN and RNN. Energy consumption was estimated by a platform-independent model based on the number of arithmetic operations (AOs) and memory accesses (MAs). To validate the estimated energy consumption, the RNN classifier was implemented on an ultra-low-power microcontroller.

Results

The RNN seizure detector achieved a slightly better level of performance, with a median area under the precision-recall curve score of 0.49, compared to 0.47 for CNN and 0.46 for RF. In terms of energy consumption, RF was the most efficient algorithm, with a total of 67k AOs and 67k MAs per classification. This was followed by CNN (488k AOs and 963k MAs) and RNN (772k AOs and 978k MAs), whereby MAs contributed more to total energy consumption. Measurements derived from the hardware implementation of the RNN algorithm demonstrated a significant correlation between estimations and actual measurements.

Discussion

All three proposed seizure detection algorithms were shown to be suitable for application in implantable devices. The applied methodology for a platform-independent energy estimation was proven to be accurate by way of hardware implementation of the RNN algorithm. These findings show that seizure detection can be achieved using just a few channels with limited spatial distribution. The methodology proposed in this study can therefore be applied when designing new models for responsive neurostimulation.

The Individual Ictal Fingerprint: Combining Movement Measures With Ultra Long-Term Subcutaneous EEG in People With Epilepsy

Background: Epileptic seizures are caused by abnormal brain wave hypersynchronization leading to a range of signs and symptoms. Tools for detecting seizures in everyday life typically focus on cardiac rhythm, electrodermal activity, or movement (EMG, accelerometry); however, these modalities are not very effective for non-motor seizures. Ultra long-term subcutaneous EEG-devices can detect the electrographic changes that do not depend on clinical changes. Nonetheless, this also means that it is not possible to assess whether a seizure is clinical or subclinical based on an EEG signal alone. Therefore, we combine EEG and movement-related modalities in this work. We focus on whether it is possible to define an individual “multimodal ictal fingerprint” which can be exploited in different epilepsy management purposes.

Methods: This study used ultra long-term data from an outpatient monitoring trial of persons with temporal lobe epilepsy obtained with a subcutaneous EEG recording system. Subcutaneous EEG, an EMG estimate and chest-mounted accelerometry were extracted from four persons showing more than 10 well-defined electrographic seizures each. Numerous features were computed from all three modalities. Based on these, the Gini impurity measure of a Random Forest classifier was used to select the most discriminative features for the ictal fingerprint. A total of 74 electrographic seizures were analyzed.

Results: The optimal individual ictal fingerprints included features extracted from all three tested modalities: an acceleration component; the power of the estimated EMG activity; and the relative power in the delta (0.5–4 Hz), low theta (4–6 Hz), and high theta (6–8 Hz) bands of the subcutaneous EEG. Multimodal ictal fingerprints were established for all persons, clustering seizures within persons, while separating seizures across persons.

Conclusion: The existence of multimodal ictal fingerprints illustrates the benefits of combining multiple modalities such as EEG, EMG, and accelerometry in future epilepsy management. Multimodal ictal fingerprints could be used by doctors to get a better understanding of the individual seizure semiology of people with epilepsy. Furthermore, the multimodal ictal fingerprint gives a better understanding of how seizures manifest simultaneously in different modalities. A knowledge that could be used to improve seizure acknowledgment when reviewing EEG without video.

A Robust Bimodal Index Reflecting Relative Dynamics of EEG and HRV With Application in Monitoring Depth of Anesthesia

Supplemental information captured from HRV can provide deeper insight into nervous system function and consequently improve evaluation of brain function. Therefore, it is of interest to combine both EEG and HRV. However, irregular nature of time spans between adjacent heartbeats makes the HRV hard to be directly fused with EEG timeseries. Current study performed a pioneering work in integrating EEG-HRV information in a single marker called cumulant ratio, quantifying how far EEG dynamics deviate from self-similarity compared to HRV dynamics. Experimental data recorded using BrainStatus device with single ECG and 10 EEG channels from healthy-brain patients undergoing operation (N = 20) were used for the validation of the proposed method. Our analyses show that the EEG to HRV ratio of first, second and third cumulants gets systematically closer to zero with increase in depth of anesthesia, respectively 29.09%, 65.0% and 98.41%. Furthermore, extracting multifractality properties of both heart and brain activities and encoding them into a 3-sample numeric code of relative cumulants does not only encapsulates the comparison of two evenly and unevenly spaced variables of EEG and HRV into a concise unitless quantity, but also reduces the impact of outlying data points.

The Challenging Path to Developing a Mobile Health Device for Epilepsy: The Current Landscape and Where We Go From Here

Seizure detection, and more recently seizure forecasting, represent important avenues of clinical development in epilepsy, promoted by progress in wearable devices and mobile health (mHealth), which might help optimizing seizure control and prevention of seizure-related mortality and morbidity in persons with epilepsy. Yet, very long-term continuous monitoring of seizure-sensitive biosignals in the ambulatory setting presents a number of challenges. We herein provide an overview of these challenges and current technological landscape of mHealth devices for seizure detection. Specifically, we display, which types of sensor modalities and analytical methods are available, and give insight into current clinical practice guidelines, main outcomes of clinical validation studies, and discuss how to evaluate device performance at point-of-care facilities. We then address pitfalls which may arise in patient compliance and the need to design solutions adapted to user experience.

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

Objective

Wearable seizure detection devices could provide more reliable seizure documentation outside the hospital compared to seizure self‐reporting by patients, which is the current standard. Previously, during the SeizeIT1 project, we studied seizure detection based on behind‐the‐ear electroencephalography (EEG). However, the obtained sensitivities were too low for practical use, because not all seizures are associated with typical ictal EEG patterns. Therefore, in this paper, we aim to develop a multimodal automated seizure detection algorithm integrating behind‐the‐ear EEG and electrocardiography (ECG) for detecting focal seizures. In this framework, we quantified the added value of ECG to behind‐the‐ear EEG.

Methods

This study analyzed three multicenter databases consisting of 135 patients having focal epilepsy and a total of 896 seizures. A patient‐specific multimodal automated seizure detection algorithm was developed using behind‐the‐ear/temporal EEG and single‐lead ECG. The EEG and ECG data were processed separately using machine learning methods. A late integration approach was applied for fusing those predictions.

Results

The multimodal algorithm outperformed the EEG‐based algorithm in two of three databases, with an increase of 11% and 8% in sensitivity for the same false alarm rate.

Significance

ECG can be of added value to an EEG‐based seizure detection algorithm using only behind‐the‐ear/temporal lobe electrodes for patients with focal epilepsy.

Classification with a Deferral Option and Low-Trust Filtering for Automated Seizure Detection

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.

Noninvasive detection of focal seizures in ambulatory patients

Reliably detecting focal seizures without secondary generalization during daily life activities, chronically, using convenient portable or wearable devices, would offer patients with active epilepsy a number of potential benefits, such as providing more reliable seizure count to optimize treatment and seizure forecasting, and triggering alarms to promote safeguarding interventions. However, no generic solution is currently available to reach these objectives. A number of biosignals are sensitive to specific forms of focal seizures, in particular heart rate and its variability for seizures affecting the neurovegetative system, and accelerometry for those responsible for prominent motor activity. However, most studies demonstrate high rates of false detection or poor sensitivity, with only a minority of patients benefiting from acceptable levels of accuracy. To tackle this challenging issue, several lines of technological progress are envisioned, including multimodal biosensing with cross‐modal analytics, a combination of embedded and distributed self‐aware machine learning, and ultra–low‐power design to enable appropriate autonomy of such sophisticated portable solutions.

Resource-Aware Distributed Epilepsy Monitoring Using Self-Awareness From Edge to Cloud

The integration of wearable devices in humans' daily lives has grown significantly in recent years and still continues to affect different aspects of high-quality life. Thus, ensuring the reliability of the decisions becomes essential in biomedical applications, while representing a major challenge considering battery-powered wearable technologies. Transferring the complex and energy-consuming computations to fogs or clouds can significantly reduce the energy consumption of wearable devices and result in a longer lifetime of these systems with a single battery charge. In this work, we aim to distribute the complex and energy-consuming machine-learning computations between the edge, fog, and cloud, based on the notion of self-awareness that takes into account the complexity and reliability of the algorithm. We also model and analyze the trade-offs in terms of energy consumption, latency, and performance of different Internet of Things (IoT) solutions. We consider the epileptic seizure detection problem as our real-world case study to demonstrate the importance of our proposed self-aware methodology.

Neural stimulation systems for the control of refractory epilepsy: a review

Epilepsy affects nearly 1% of the world's population. A third of epilepsy patients suffer from a kind of epilepsy that cannot be controlled by current medications. For those where surgery is not an option, neurostimulation may be the only alternative to bring relief, improve quality of life, and avoid secondary injury to these patients. Until recently, open loop neurostimulation was the only alternative for these patients. However, for those whose epilepsy is applicable, the medical approval of the responsive neural stimulation and the closed loop vagal nerve stimulation systems have been a step forward in the battle against uncontrolled epilepsy. Nonetheless, improvements can be made to the existing systems and alternative systems can be developed to further improve the quality of life of sufferers of the debilitating condition. In this paper, we first present a brief overview of epilepsy as a disease. Next, we look at the current state of biomarker research in respect to sensing and predicting epileptic seizures. Then, we present the current state of open loop neural stimulation systems. We follow this by investigating the currently approved, and some of the recent experimental, closed loop systems documented in the literature. Finally, we provide discussions on the current state of neural stimulation systems for controlling epilepsy, and directions for future studies.

Ictal autonomic changes as a tool for seizure detection: a systematic review

Purpose

Adequate epileptic seizure detection may have the potential to minimize seizure-related complications and improve treatment evaluation. Autonomic changes often precede ictal electroencephalographic discharges and therefore provide a promising tool for timely seizure detection. We reviewed the literature for seizure detection algorithms using autonomic nervous system parameters.

Methods

The PubMed and Embase databases were systematically searched for original human studies that validate an algorithm for automatic seizure detection based on autonomic function alterations. Studies on neonates only and pilot studies without performance data were excluded. Algorithm performance was compared for studies with a similar design (retrospective vs. prospective) reporting both sensitivity and false alarm rate (FAR). Quality assessment was performed using QUADAS-2 and recently reported quality standards on reporting seizure detection algorithms.

Results

Twenty-one out of 638 studies were included in the analysis. Fifteen studies presented a single-modality algorithm based on heart rate variability (n = 10), heart rate (n = 4), or QRS morphology (n = 1), while six studies assessed multimodal algorithms using various combinations of HR, corrected QT interval, oxygen saturation, electrodermal activity, and accelerometry. Most studies had small sample sizes and a short follow-up period. Only two studies performed a prospective validation. A tendency for a lower FAR was found for retrospectively validated algorithms using multimodal autonomic parameters compared to those using single modalities (mean sensitivity per participant 71–100% vs. 64–96%, and mean FAR per participant 0.0–2.4/h vs. 0.7–5.4/h).

Conclusions

The overall quality of studies on seizure detection using autonomic parameters is low. Unimodal autonomic algorithms cannot reach acceptable performance as false alarm rates are still too high. Larger prospective studies are needed to validate multimodal automatic seizure detection.

Electronic supplementary material

The online version of this article (10.1007/s10286-018-0568-1) contains supplementary material, which is available to authorized users.

Understanding perception of active noise control system through multichannel EEG analysis

In this Letter, a method is proposed to investigate the effect of noise with and without active noise control (ANC) on multichannel electroencephalogram (EEG) signal. The multichannel EEG signal is recorded during different listening conditions such as silent, music, noise, ANC with background noise and ANC with both background noise and music. The multiscale analysis of EEG signal of each channel is performed using the discrete wavelet transform. The multivariate multiscale matrices are formulated based on the sub-band signals of each EEG channel. The singular value decomposition is applied to the multivariate matrices of multichannel EEG at significant scales. The singular value features at significant scales and the extreme learning machine classifier with three different activation functions are used for classification of multichannel EEG signal. The experimental results demonstrate that, for ANC with noise and ANC with noise and music classes, the proposed method has sensitivity values of 75.831% (\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$p \lt 0.001$\end{document}p<0.001) and 99.31% (\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$p \lt 0.001$\end{document}p<0.001), respectively. The method has an accuracy value of 83.22% for the classification of EEG signal with music and ANC with music as stimuli. The important finding of this study is that by the introduction of ANC, music can be better perceived by the human brain.

Bio-Signal Complexity Analysis in Epileptic Seizure Monitoring: A Topic Review

Complexity science has provided new perspectives and opportunities for understanding a variety of complex natural or social phenomena, including brain dysfunctions like epilepsy. By delving into the complexity in electrophysiological signals and neuroimaging, new insights have emerged. These discoveries have revealed that complexity is a fundamental aspect of physiological processes. The inherent nonlinearity and non-stationarity of physiological processes limits the methods based on simpler underlying assumptions to point out the pathway to a more comprehensive understanding of their behavior and relation with certain diseases. The perspective of complexity may benefit both the research and clinical practice through providing novel data analytics tools devoted for the understanding of and the intervention about epilepsies. This review aims to provide a sketchy overview of the methods derived from different disciplines lucubrating to the complexity of bio-signals in the field of epilepsy monitoring. Although the complexity of bio-signals is still not fully understood, bundles of new insights have been already obtained. Despite the promising results about epileptic seizure detection and prediction through offline analysis, we are still lacking robust, tried-and-true real-time applications. Multidisciplinary collaborations and more high-quality data accessible to the whole community are needed for reproducible research and the development of such applications.