Syncope vs. Seizure: Ictal Bradycardia and Ictal Asystole.

Background: Ictal arrhythmia is a rare condition that causes arrhythmic manifestations induced by epileptic seizures, including asystole or bradycardia. Ictal asystole (IA) is a very rare condition found in patients undergoing video-encephalography (EEG) monitoring. It is often related to temporal lobe epilepsy and can cause syncope, which can lead to injury or even death. Case Presentation. Two patients with epilepsy showed symptoms of syncope. Both patients underwent 4-day ambulatory EEG tests and were diagnosed with IA. Following the tests, the patients were implanted with a permanent pacemaker, and one of them underwent a temporal lobectomy. As a result of these procedures, the patients experienced a reduction in episodes of symptomatic syncope. Conclusion: Patients with ictal asystole and symptomatic ictal bradycardia are at increased risk of falls due to seizures. Although there are no specific guidelines for managing this condition, antiseizure medications, epilepsy surgery, and cardiac pacemaker implantation have been effective treatments.

Efficient Edge-AI Models for Robust ECG Abnormality Detection on Resource-Constrained Hardware.

This study introduces two models, ConvLSTM2D-liquid time-constant network (CLTC) and ConvLSTM2D-closed-form continuous-time neural network (CCfC), designed for abnormality identification using electrocardiogram (ECG) data. Trained on the Telehealth Network of Minas Gerais (TNMG) subset dataset, both models were evaluated for their performance, generalizability capacity, and resilience. They demonstrated comparable results in terms of F1 scores and AUROC values. The CCfC model achieved slightly higher accuracy, while the CLTC model showed better handling of empty channels. Remarkably, the models were successfully deployed on a resource-constrained microcontroller, proving their suitability for edge device applications. Generalization capabilities were confirmed through the evaluation on the China Physiological Signal Challenge 2018 (CPSC) dataset. The models' efficient resource utilization, occupying 70.6% of memory and 9.4% of flash memory, makes them promising candidates for real-world healthcare applications. Overall, this research advances abnormality identification in ECG data, contributing to the progress of AI in healthcare.

Comparative effectiveness of digital mental healthcare models for adults with epilepsy: A study protocol of a randomized controlled trial.

OBJECTIVE: Mental health complaints are prevalent among people with epilepsy, yet there are major barriers that prevent access to psychological care, including high out-of-pocket costs and a lack of accessible specialized services. The purpose of the current study is to examine the comparative efficacy, acceptability, cost-effectiveness, and long-term outcomes of a digital psychological intervention when delivered under two models of care (i.e., guided vs. unguided) in supporting the mental health and functioning of adults with epilepsy. METHOD: Approximately 375 participants across Australia will be enrolled. Eligible participants will have a confirmed diagnosis of epilepsy, experience difficulties with their emotional health, be at least 18 years of age, and live in Australia. Participants will be randomized (2:2:1) to receive the Wellbeing Neuro Course, a 10-week internet-delivered program, with (i.e., guided) or without guidance by a mental health clinician (i.e., unguided), or be allocated to a treatment-as-usual waiting-list control group. Participants will complete online questionnaires at pre-, post-treatment, and 3- and 12-month follow-up and consent to have their data linked to their medical records to capture healthcare system resource use and costs. ANALYSIS: Primary outcome measures will be symptoms of depression and anxiety. A cost-utility analysis will be undertaken using the Australian healthcare system perspective and according to current economic evaluation guidelines. Resource use and costs to the healthcare system during the study period will be captured via data linkage to relevant administrative datasets in Australia. SIGNIFICANCE: The results of this trial will provide important data concerning the relative outcomes of these different models of care and will inform the integration of digital psychological interventions translation into healthcare services. ETHICS AND DISSEMINATION: The Human Research Ethics Committee of Macquarie University approved the proposed study (Reference No: 520231325151475). The results will be disseminated through peer-reviewed publication(s). ANZCTR TRIAL REGISTRATION NUMBER: ACTRN12623001327673. PLAIN LANGUAGE SUMMARY: This study seeks to find out if a 10-week online psychological treatment can improve the mental health and well-being of Australian adults with epilepsy. Around 375 participants will be randomly assigned to different groups: one will receive treatment with guidance from mental health clinician (guided group), one without guidance (unguided group), and one starting later (waiting control group). All participants will fill out the same outcome measures online. The main goal of this research is to compare these groups and assess how well the treatment works in improving mental health outcomes.

S4D-ECG: A Shallow State-of-the-Art Model for Cardiac Abnormality Classification.

PURPOSE: This study introduces an algorithm specifically designed for processing unprocessed 12-lead electrocardiogram (ECG) data, with the primary aim of detecting cardiac abnormalities. METHODS: The proposed model integrates Diagonal State Space Sequence (S4D) model into its architecture, leveraging its effectiveness in capturing dynamics within time-series data. The S4D model is designed with stacked S4D layers for processing raw input data and a simplified decoder using a dense layer for predicting abnormality types. Experimental optimization determines the optimal number of S4D layers, striking a balance between computational efficiency and predictive performance. This comprehensive approach ensures the model's suitability for real-time processing on hardware devices with limited capabilities, offering a streamlined yet effective solution for heart monitoring. RESULTS: Among the notable features of this algorithm is its strong resilience to noise, enabling the algorithm to achieve an average F1-score of 81.2% and an AUROC of 95.5% in generalization. The model underwent testing specifically on the lead II ECG signal, exhibiting consistent performance with an F1-score of 79.5% and an AUROC of 95.7%. CONCLUSION: It is characterized by the elimination of pre-processing features and the availability of a low-complexity architecture that makes it suitable for implementation on numerous computing devices because it is easily implementable. Consequently, this algorithm exhibits considerable potential for practical applications in analyzing real-world ECG data. This model can be placed on the cloud for diagnosis. The model was also tested on lead II of the ECG alone and has demonstrated promising results, supporting its potential for on-device application.

Deep learning distinguishes connectomes from focal epilepsy patients and controls: feasibility and clinical implications.

The application of deep learning models to evaluate connectome data is gaining interest in epilepsy research. Deep learning may be a useful initial tool to partition connectome data into network subsets for further analysis. Few prior works have used deep learning to examine structural connectomes from patients with focal epilepsy. We evaluated whether a deep learning model applied to whole-brain connectomes could classify 28 participants with focal epilepsy from 20 controls and identify nodal importance for each group. Participants with epilepsy were further grouped based on whether they had focal seizures that evolved into bilateral tonic-clonic seizures (17 with, 11 without). The trained neural network classified patients from controls with an accuracy of 72.92%, while the seizure subtype groups achieved a classification accuracy of 67.86%. In the patient subgroups, the nodes and edges deemed important for accurate classification were also clinically relevant, indicating the model's interpretability. The current work expands the evidence for the potential of deep learning to extract relevant markers from clinical datasets. Our findings offer a rationale for further research interrogating structural connectomes to obtain features that can be biomarkers and aid the diagnosis of seizure subtypes.

Late-onset epilepsy with cognitive symptoms: Comparison of cognitive and imaging profiles with probable Alzheimer's disease.

OBJECTIVE: We aimed to (i) compare the clinical, neuropsychological, and neuroimaging characteristics of unprovoked late-onset epilepsy (LOE) patients with cognitive symptoms against probable Alzheimer's disease (AD) patients; (ii) clarify how neurodegeneration and other processes could be implicated in the cognitive symptoms of unprovoked LOE patients; and (iii) characterize the longitudinal trajectory of unprovoked LOE patients with cognitive symptoms. METHODS: Twenty-six unprovoked LOE patients with cognitive symptoms and 26 probable AD were retrospectively recruited from epilepsy and memory clinics at a single tertiary referral center. The patients underwent comprehensive clinical, neuropsychological, and 18Fluorodeoxyglucose PET-CT assessments. All LOE patients had clinical follow-up and a subset of 17 patients had repeat neuropsychological assessments. RESULTS: At baseline, 18% of LOE patients with cognitive symptoms had dementia-range cognitive impairment and one received a diagnosis of probable AD. Compared with the probable AD group, the LOE group did not perform significantly better in global measures of cognition (total ACE-III), neuropsychological tests for fluency, working memory, language, attention, or executive function, but performed better in naming, memory, and visuospatial ability. The commonest patterns of cognitive impairment in the LOE group were frontal and left temporal, whereas all AD patients exhibited parietotemporal patterns. The AD group had more 18Fluorodeoxyglucose PET-CT hypometabolism in the parietal and occipital, but not the temporal and frontal lobes. During the 3.0 ± 3.2 years follow-up, improved seizure frequency in the LOE group covaried with improved total ACE-III score, there was no further conversion to probable AD and no group-level cognitive decline. CONCLUSION: Unprovoked LOE patients with cognitive symptoms had varying severities of cognitive impairment, and different patterns of cognitive and imaging abnormalities compared with AD patients. They were rarely diagnosed with probable AD at presentation or follow-up. Cognitive outcome in LOE may be related to seizure control. Cerebral small vessel disease may play a role in LOE-associated cognitive impairment.

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.

A miniaturized and low-energy subcutaneous optical telemetry module for neurotechnology.

Objective.This study presents a proof-of-concept optical telemetry module that leverages a single light-emitting diode (LED) to transmit data at a high bit rate while consuming low power and occupying a small area. Our experiments showed that we could achieve 108 Mbit s-1and 54 Mbit s-1back telemetry data rates for tissue thicknesses of 3 mm and 8 mm, respectively.Approach.The proposed module is designed to be powered by near-field coupling and achieve bidirectional communication by low-speed downlink from near-field communication. It aims to minimize the size of the implant while providing reliable transmission that meets the requirements of high-speed wireless communication from a multi-electrode array neurotechnology implant outside the body.Results.The power consumption of the module is 1.57 mW, including the power consumption of related circuits, resulting in an efficiency of 14.5 pJ bit-1, at a tissue thickness of 3 mm and a data rate of 108 Mbit. The use of an optical lens, combined with tissue scattering effect and optimized emission angle, makes the module robust to misalignments of up to ±5 mm and ±15° between the implantable and external units. The LED in the implantable unit is only 0.98 × 0.98 × 0.6 mm3, and the testing module is composed of discrete components and laboratory instruments.Significance.This work aims to show how it is possible to strike a balance between a small, reliable, and high-bit-rate data uplink between a neural implant and its proximal, wirelessly connected external unit. This optical telemetry module has the potential to be integrated into a significantly miniaturized system through an application-specific integrated circuit and can support up to 1000 channels of neural recordings, each sampled at 9 kSps with a 12-bit readout resolution.

Determining the role and responsibilities of the community epilepsy nurse in the management of epilepsy.

AIMS AND OBJECTIVES: The aim of this study is to enhance the understanding of the core elements and influencing factors on the community-based epilepsy nurse's role and responsibilities. BACKGROUND: Internationally, epilepsy nurse specialists play a key role in providing person-centred care and management of epilepsy but there is a gap in understanding of their role in the community. DESIGN: A national three-stage, mixed-method study was conducted. METHODS: One-on-one, in-depth semi-structured qualitative interviews were conducted online with 12 community-based epilepsy nurses (Stage 1); retrospective analysis of data collected from the National Epilepsy Line, a nurse-led community helpline (Stage 2); and focus group conducted with four epilepsy nurses, to delve further into emerging findings (Stage 3). A thematic analysis was conducted in Stages 1 and 3, and a descriptive statistical analysis of Stage 2 data. Consolidated Criteria for Reporting Qualitative studies checklist was followed for reporting. RESULTS: Three key themes emerged: (1) The epilepsy nurse career trajectory highlighted a lack of standardised qualifications, competencies, and career opportunities. (2) The key components of the epilepsy nurse role explored role diversity, responsibilities, and models of practice in the management of living with epilepsy, and experiences navigating complex fragmented systems and practices. (3) Shifting work practices detailed the adapting work practices, impacted by changing service demands, including COVID-19 pandemic experiences, role boundaries, funding, and resource availability. CONCLUSION: Community epilepsy nurses play a pivotal role in providing holistic, person-centred epilepsy management They contribute to identifying and addressing service gaps through innovating and implementing change in service design and delivery. RELEVANCE TO CLINICAL PRACTICE: Epilepsy nurses' person-centred approach to epilepsy management is influenced by the limited investment in epilepsy-specific integrated care initiatives, and their perceived value is impacted by the lack of national standardisation of their role and scope of practice. NO PATIENT OR PUBLIC CONTRIBUTION: Only epilepsy nurses' perspectives were sought.

The long-term outcomes of patients with negative prolonged ambulatory electroencephalography tests: A cross-sectional follow-up study.

Background: Ambulatory electroencephalography (AEEG) recording is an essential aid for detecting interictal discharges and providing a clinical diagnosis. This study aimed to describe long-term outcomes among a cohort of patients who yielded negative results on AEEG at the time of assessment and identify factors associated with contemporary quality of life (QOL) and ultimate epilepsy diagnosis. Methods: This cross-sectional telephone follow-up study was conducted in June-November 2021 at the Neurology Department in a metropolitan hospital in Sydney, Australia. Results: In total, 47 of 105 eligible (45%) participants were enrolled. Overall, 21 (45%) participants had been diagnosed with epilepsy at a 12-year follow-up. Taking anti-seizure medication, having experienced a seizure event, and having marriage and education-related characteristics were associated with an epilepsy diagnosis. QOL was found to be associated with age, employment status and history of experience of a seizure event. QOL and an epilepsy diagnosis were not shown to be statistically related. Conclusions: Nearly half of the participants had received an epilepsy diagnosis at long-term follow-up, despite having tested negative on AEEG at the time of assessment. Prolonged AEEG testing is an important tool to aid the diagnostic process. However, clinical examination, including accurate history taking, is vital in establishing an epilepsy diagnosis.

Ambulatory electroencephalography (AEEG) recording is an essential aid for detecting interictal discharges and providing a clinical diagnosis. This study aimed to describe long-term outcomes among a cohort of patients who yielded negative results on AEEG at the time of assessment and identify factors associated with contemporary quality of life (QOL) and ultimate epilepsy diagnosis. This cross-sectional telephone follow-up study was conducted in June-November 2021 at the Neurology Department in a metropolitan hospital in Sydney, Australia. In total, 47 of 105 eligible (45%) participants were enrolled. Overall, 21 (45%) participants had been diagnosed with epilepsy at a 12-year follow-up. Taking anti-seizure medication, having experienced a seizure event, and having marriage and education-related characteristics were associated with an epilepsy diagnosis. QOL was found to be associated with age, employment status and history of experience of a seizure event. QOL and an epilepsy diagnosis were not shown to be statistically related. Nearly half of the participants had received an epilepsy diagnosis at long-term follow-up, despite having tested negative on AEEG at the time of assessment. Prolonged AEEG testing is an important tool to aid the diagnostic process. However, clinical examination, including accurate history taking, is vital in establishing an epilepsy diagnosis.

Seizure Detection: A Low Computational Effective Approach without Classification Methods.

Epilepsy is a severe neurological disorder that is usually diagnosed by using an electroencephalogram (EEG). However, EEG signals are complex, nonlinear, and dynamic, thus generating large amounts of data polluted by many artefacts, lowering the signal-to-noise ratio, and hampering expert interpretation. The traditional seizure-detection method of professional review of long-term EEG signals is an expensive, time-consuming, and challenging task. To reduce the complexity and cost of the task, researchers have developed several seizure-detection approaches, primarily focusing on classification systems and spectral feature extraction. While these methods can achieve high/optimal performances, the system may require retraining and following up with the feature extraction for each new patient, thus making it impractical for real-world applications. Herein, we present a straightforward manual/automated detection system based on the simple seizure feature amplification analysis to minimize these practical difficulties. Our algorithm (a simplified version is available as additional material), borrowing from the telecommunication discipline, treats the seizure as the carrier of information and tunes filters to this specific bandwidth, yielding a viable, computationally inexpensive solution. Manual tests gave 93% sensitivity and 96% specificity at a false detection rate of 0.04/h. Automated analyses showed 88% and 97% sensitivity and specificity, respectively. Moreover, our proposed method can accurately detect seizure locations within the brain. In summary, the proposed method has excellent potential, does not require training on new patient data, and can aid in the localization of seizure focus/origin.

White matter alterations in focal to bilateral tonic-clonic seizures.

We examined the white matter of patients with and without focal to bilateral tonic-clonic seizures (FBTCS), and control participants. A neural network based tract segmentation model (Tractseg) was used to isolate tract-specific, track-weighted tensor-based measurements from the tracts of interest. We compared the group differences in the track-weighted tensor-based measurements derived from whole and hemispheric tracts. We identified several regions that displayed significantly altered white matter in patients with focal epilepsy compared to controls. Furthermore, patients without FBTCS showed significantly increased white matter disruption in the inferior fronto-occipital fascicle and the striato-occipital tract. In contrast, the track-weighted tensor-based measurements from the FBTCS cohort exhibited a stronger resemblance to the healthy controls (compared to the non-FBTCS group). Our findings revealed marked alterations in a range of subcortical tracts considered critical in the genesis of seizures in focal epilepsy. Our novel application of tract-specific, track-weighted tensor-based measurements to a new clinical dataset aided the elucidation of specific tracts that may act as a predictive biomarker to distinguish patients likely to develop FBTCS.

Weak self-supervised learning for seizure forecasting: a feasibility study.

This paper proposes an artificial intelligence system that continuously improves over time at event prediction using initially unlabelled data by using self-supervised learning. Time-series data are inherently autocorrelated. By using a detection model to generate weak labels on the fly, which are concurrently used as targets to train a prediction model on a time-shifted input data stream, this autocorrelation can effectively be harnessed to reduce the burden of manual labelling. This is critical in medical patient monitoring, as it enables the development of personalized forecasting models without demanding the annotation of long sequences of physiological signal recordings. We perform a feasibility study on seizure prediction, which is identified as an ideal test case, as pre-ictal brainwaves are patient-specific, and tailoring models to individual patients is known to improve forecasting performance significantly. Our self-supervised approach is used to train individualized forecasting models for 10 patients, showing an average relative improvement in sensitivity by 14.30% and a reduction in false alarms by 19.61% in early seizure forecasting. This proof-of-concept on the feasibility of using a continuous stream of time-series neurophysiological data paves the way towards a low-power neuromorphic neuromodulation system.

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.

Implementation of a New Clinical Testing Tool to Assess Patients During Ictal and Postictal Periods.

ABSTRACT: BACKGROUND: A seizure is a sudden, uncontrolled electrical disturbance of the cortical neurons in the brain, which can cause changes in behavior, movements, feelings, and consciousness. Clinical signs and symptoms before, during, and after a seizure can help to determine the seizure onset. The use of standardized clinical testing tools has been reported as being valuable, although also challenging, by some institutions. This study investigated the effectiveness of implementing a new clinical testing tool designed with an emphasis on simplicity for use during and after seizures. METHODS: A pre-and-post evaluation study was conducted from January 2020 to November 2020 in the epilepsy monitoring unit/neurology unit at a hospital in Sydney, Australia. The primary outcome of interest was the incidence of clinical testing during seizures. The secondary outcome of interest was nurse knowledge about clinical testing during a seizure. This knowledge was measured via testing before and after clinical education sessions. The third outcome of interest was nurse confidence regarding the use of the clinical testing tool. The confidence level was measured via posteducation session follow-up surveying. RESULTS: Forty-seven nursing staff (10 neurophysiology nurse technologists and 37 neurology unit nurses) participated in the education program. Forty-four seizures were evaluated. Clinical testing during ictal and postictal periods was performed by nursing staff 82% of the time during 2020, compared with 67% during the 2018 to 2019 preeducation comparison period. This difference was not statistically significant, but it was clinically relevant (P = .07). In addition, the time from seizure alarm to clinical testing improved significantly from a median of 30.5 seconds in 2018 to 2019 to 14 seconds in 2020 (P < .001). CONCLUSION: The tool is easy and convenient for nursing staff to perform clinical examinations accurately during ictal and postictal periods.

A Prospective Randomized Controlled Trial: Alternative Approach to EEG Application to Reduce Electrode-induced Skin Injury among Ambulatory EEG Patients.

Ambulatory electroencephalography (AEEG) is a technique of continuous EEG recording of patients in their natural setting, outside the controlled environment of the hospital. Electrode-induced skin injury is a common complication of prolonged EEG monitoring. This randomized study aimed to investigate the performance of two methods of electrode application in reducing electrode-induced skin injury among patients undergoing 4-day AEEG monitoring. A randomized interventional study was conducted from November 2020 to May 2021 in the Neurosciences Ambulatory Care Unit at a metropolitan hospital in Sydney, Australia. We enrolled patients into two groups: i) Group 1 (standard protocol group) received Ten20 Conductive PasteTM with Tensive® adhesive gel as the primary approach to electrode application and ii) Group 2 (intervention group) received Ten20 Conductive PasteTM with Tensive® adhesive gel and hydrogel electrodes on hairless locations as the primary approach to electrode application. A total of 79 patients participated in this study. The group that received the addition of hydrogel electrodes (Group 2) performed better than the standard protocol group on electrode site inflammation for the frontal region, particularly FP1, FP2, F8, and the ground electrode sites. EEG quality and self-reports of patient comfort and mood did not differ significantly between the two groups. The addition of hydrogel electrodes using a Ten20 Conductive PasteTM with a Tensive® adhesive gel protocol results in reduced inflammation at frontal lobe and ground electrode sites.

Semantic and episodic memory in adults with temporal lobe epilepsy.

The primary aims were to (1) identify the factor structure of tests thought to measure semantic and episodic memory and (2) examine whether patterns of impairment would show a double dissociation between these two memory systems at an individual level in patients with temporal lobe epilepsy (TLE). The secondary aim was to explore the impact of epilepsy-related variables on performance. This retrospective study involved a cohort of 54 adults who had been diagnosed with TLE and had undergone a neuropsychological assessment that included four memory tests traditionally used to measure either semantic memory (picture naming, animal fluency) or episodic memory (story recall, word list recall) at a single epilepsy surgery center in Australia. Principal component analysis revealed two factors albeit with unexpected loadings. Picture naming and story recall loaded on one factor. Animal fluency and word list recall loaded on another factor. There was no evidence of a double dissociation between semantic and episodic memory at an individual level. Left hemisphere seizure focus and early age of seizure onset related to worse performance on word list recall, picture naming and animal fluency, respectively. Our study highlights the importance of caution when interpreting the results of neuropsychological assessments, as not all putative tests of semantic and episodic memory may necessarily be measuring the same construct. Future directions for research are also considered.

A comparative study of AI systems for epileptic seizure recognition based on EEG or ECG.

The majority of studies for automatic epileptic seizure (ictal) detection are based on electroencephalogram (EEG) data, but electrocardiogram (ECG) presents a simpler and more wearable alternative for long-term ambulatory monitoring. To assess the performance of EEG and ECG signals, AI systems offer a promising way forward for developing high performing models in securing both a reasonable sensitivity and specificity. There are crucial needs for these AI systems to be developed with more clinical relevance and inference generalization. In this work, we implement an ECG-specific convolutional neural network (CNN) model with residual layers and an EEG-specific convolutional long short-term memory (ConvLSTM) model. We trained, validated, and tested these models on a publicly accessible Temple University Hospital (TUH) dataset for reproducibility and performed a non-patient-specific inference-only test on patient EEG and ECG data of The Royal Prince Alfred Hospital (RPAH) in Sydney, Australia. We selected 31 adult patients to balance groups with the following seizure types: generalized, frontal, frontotemporal, temporal, parietal, and unspecific focal epilepsy. Our tests on both EEG and ECG of these patients achieve an AUC score of 0.75. Our results show ECG outperforms EEG with an average improvement of 0.21 and 0.11 AUC score in patients with frontal and parietal focal seizures, respectively.Clinical relevance-Prior research has demonstrated the value of using ECG for seizure documentation. It is believed that specific epileptic foci (seizure origin) may involve network inputs to the autonomic nervous system. Our result indicates that ECG could outperform EEG for individuals with specific seizure origin, particularly in the frontal and parietal lobes.

Seizure Susceptibility Prediction in Uncontrolled Epilepsy.

Epileptic seizure forecasting, combined with the delivery of preventative therapies, holds the potential to greatly improve the quality of life for epilepsy patients and their caregivers. Forecasting seizures could prevent some potentially catastrophic consequences such as injury and death in addition to several potential clinical benefits it may provide for patient care in hospitals. The challenge of seizure forecasting lies within the seemingly unpredictable transitions of brain dynamics into the ictal state. The main body of computational research on determining seizure risk has been focused solely on prediction algorithms, which involves a challenging issue of balancing sensitivity and false alarms. There have been some studies on identifying potential biomarkers for seizure forecasting; however, the questions of "What are the true biomarkers for seizure prediction" or even "Is there a valid biomarker for seizure prediction?" are yet to be fully answered. In this paper, we introduce a tool to facilitate the exploration of the potential biomarkers. We confirm using our tool that interictal slowing activities are a promising biomarker for epileptic seizure susceptibility prediction.