Non-electroencephalography-based seizure detection

Detection of seizures with ictal tachycardia, using heart rate variability and patient adaptive logistic regression machine learning methods: A hospital-based validation study

OBJECTIVE

Automated seizure detection of focal epileptic seizures is needed for objective seizure quantification to optimize the treatment of patients with epilepsy. Heart rate variability (HRV)-based seizure detection using patient-adaptive threshold with logistic regression machine learning (LRML) methods has presented promising performance in a study with a Danish patient cohort. The objective of this study was to assess the generalizability of the novel LRML seizure detection algorithm by validating it in a dataset recorded from long-term video-EEG monitoring (LTM) in a Brazilian patient cohort.

METHODS

Ictal and inter-ictal ECG-data epochs recorded during LTM were analyzed retrospectively. Thirty-four patients had 107 seizures (79 focal, 28 generalized tonic-clonic [GTC] including focal-to-bilateral-tonic-clonic seizures) eligible for analysis, with a total of 185.5 h recording. Because HRV-based seizure detection is only suitable in patients with marked ictal autonomic change, patients with >50 beats/min change in heart rate during seizures were selected as responders. The patient-adaptive LRML seizure detection algorithm was applied to all elected ECG data, and results were computed separately for responders and non-responders.

RESULTS

The patient-adaptive LRML seizure detection algorithm yielded a sensitivity of 84.8% (95% CI: 75.6-93.9) with a false alarm rate of .25/24 h in the responder group (22 patients, 59 seizures). Twenty-five of the 26 GTC seizures were detected (96.2%), and 25 of the 33 focal seizures without bilateral convulsions were detected (75.8%).

SIGNIFICANCE

The study confirms in a new, independent external dataset the good performance of seizure detection from a previous study and suggests that the method is generalizable. This method seems useful for detecting both generalized and focal epileptic seizures. The algorithm can be embedded in a wearable seizure detection system to alert patients and caregivers of seizures and generate objective seizure counts helping to optimize the treatment of the patients.

Automated analysis and detection of epileptic seizures in video recordings using artificial intelligence

Introduction

Automated seizure detection promises to aid in the prevention of SUDEP and improve the quality of care by assisting in epilepsy diagnosis and treatment adjustment.

Methods

In this phase 2 exploratory study, the performance of a contactless, marker-free, video-based motor seizure detection system is assessed, considering video recordings of patients (age 0-80 years), in terms of sensitivity, specificity, and Receiver Operating Characteristic (ROC) curves, with respect to video-electroencephalographic monitoring (VEM) as the medical gold standard. Detection performances of five categories of motor epileptic seizures (tonic-clonic, hyperkinetic, tonic, unclassified motor, automatisms) and psychogenic non-epileptic seizures (PNES) with a motor behavioral component lasting for >10 s were assessed independently at different detection thresholds (rather than as a categorical classification problem). A total of 230 patients were recruited in the study, of which 334 in-scope (>10 s) motor seizures (out of 1,114 total seizures) were identified by VEM reported from 81 patients. We analyzed both daytime and nocturnal recordings. The control threshold was evaluated at a range of values to compare the sensitivity (n = 81 subjects with seizures) and false detection rate (FDR) (n = all 230 subjects).

Results

At optimal thresholds, the performance of seizure groups in terms of sensitivity (CI) and FDR/h (CI): tonic-clonic- 95.2% (82.4, 100%); 0.09 (0.077, 0.103), hyperkinetic- 92.9% (68.5, 98.7%); 0.64 (0.59, 0.69), tonic- 78.3% (64.4, 87.7%); 5.87 (5.51, 6.23), automatism- 86.7% (73.5, 97.7%); 3.34 (3.12, 3.58), unclassified motor seizures- 78% (65.4, 90.4%); 4.81 (4.50, 5.14), and PNES- 97.7% (97.7, 100%); 1.73 (1.61, 1.86). A generic threshold recommended for all motor seizures under study asserted 88% sensitivity and 6.48 FDR/h.

Discussion

These results indicate an achievable performance for major motor seizure detection that is clinically applicable for use as a seizure screening solution in diagnostic workflows.

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.

Seizure Detection Devices in Children: One Step Closer

Multimodal Nocturnal Seizure Detection in Children With Epilepsy: A Prospective, Multicenter, Long-Term, In-Home Trial van Westrhenen A, Lazeron RHC, van Dijk JP, Leijten FSS, Thijs RD; Dutch TeleEpilepsy Consortium. Epilepsia. 2023;64(8):2137-2152. doi:10.1111/epi.17654 Objective: There is a pressing need for reliable automated seizure detection in epilepsy care. Performance evidence on ambulatory non-electroencephalography-based seizure detection devices is low, and evidence on their effect on caregiver’s stress, sleep, and quality of life (QoL) is still lacking. We aimed to determine the performance of NightWatch, a wearable nocturnal seizure detection device, in children with epilepsy in the family home setting and to assess its impact on caregiver burden. Methods: We conducted a phase 4, multicenter, prospective, video-controlled, in-home NightWatch implementation study (NCT03909984). We included children aged 4-16 years, with ≥1 weekly nocturnal major motor seizure, living at home. We compared a 2-month baseline period with a 2-month NightWatch intervention. The primary outcome was the detection performance of NightWatch for major motor seizures (focal to bilateral or generalized tonic-clonic [TC] seizures, focal to bilateral or generalized tonic seizures lasting >30 s, hyperkinetic seizures, and a remainder category of focal to bilateral or generalized clonic seizures and “TC-like” seizures). Secondary outcomes included caregivers’ stress (Caregiver Strain Index [CSI]), sleep (Pittsburgh Quality of Sleep Index), and QoL (EuroQol five-dimension five-level scale). Results: We included 53 children (55% male, mean age = 9.7 ± 3.6 years, 68% learning disability) and analyzed 2310 nights (28 173 h), including 552 major motor seizures. Nineteen participants did not experience any episode of interest during the trial. The median detection sensitivity per participant was 100% (range = 46%-100%), and the median individual false alarm rate was .04 per hour (range = 0-.53). Caregiver’s stress decreased significantly (mean total CSI score = 8.0 vs. 7.1, p = .032), whereas caregiver’s sleep and QoL did not change significantly during the trial. Significance: The NightWatch system demonstrated high sensitivity for detecting nocturnal major motor seizures in children in a family home setting and reduced caregiver stress.

Automated detection of focal seizures using subcutaneously implanted electrocardiographic device: A proof-of-concept study

Phase 2 studies showed that focal seizures could be detected by algorithms using heart rate variability (HRV) in patients with marked autonomic ictal changes. However, wearable surface electrocardiographic (ECG) devices use electrode patches that need to be changed often and may cause skin irritation. We report the first study of automated seizure detection using a subcutaneously implantable cardiac monitor (ICM; Confirm Rx, Abbott). For this proof-of-concept (phase 1) study, we recruited six patients admitted to long-term video-electroencephalographic monitoring. Fifteen-minute epochs of ECG signals were saved for each seizure and for control (nonseizure) epochs in the epilepsy monitoring unit (EMU) and in the patients' home environment (1-8 months). We analyzed the ICM signals offline, using a previously developed HRV algorithm. Thirteen seizures were recorded in the EMU, and 41 seizures were recorded in the home-monitoring period. The algorithm accurately identified 50 of 54 focal seizures (sensitivity = 92.6%, 95% confidence interval [CI] = 85.6%-99.6%). Twelve of the 13 seizures in the EMU were detected (sensitivity = 92.3%, 95% CI = 77.2%-100%), and 38 of the 41 seizures in the out-of-hospital setting were detected (sensitivity = 92.7%, 95% CI = 84.7%-100%). Four false detections were found in the 141 control (nonseizure) epochs (false alarm rate = 2.7/24 h). Our results suggest that automated seizure detection using a long-term, subcutaneous ICM device is feasible and accurate in patients with focal seizures and autonomic ictal changes.

Personalized seizure signature: An interpretable approach to false alarm reduction for long-term epileptic seizure detection

OBJECTIVE

Long-term automatic detection of focal seizures remains one of the major challenges in epilepsy due to the unacceptably high number of false alarms from state-of-the-art methods. Our aim was to investigate to what extent a new patient-specific approach based on similarly occurring morphological electroencephalographic (EEG) signal patterns could be used to distinguish seizures from nonseizure events, as well as to estimate its maximum performance.

METHODS

We evaluated our approach on >5500 h of long-term EEG recordings using two public datasets: the PhysioNet.org Children's Hospital Boston-Massachusetts Institute of Technology (CHB-MIT) Scalp EEG database and the EPILEPSIAE European epilepsy database. We visually identified a set of similarly occurring morphological patterns (seizure signature) seen simultaneously over two different EEG channels, and within two randomly selected seizures from each individual. The same seizure signature was then searched for in the entire recording from the same patient using dynamic time warping (DTW) as a similarity metric, with a threshold set to reflect the maximum sensitivity our algorithm could achieve without false alarm.

RESULTS

At a DTW threshold providing no false alarm during the entire recordings, the mean seizure detection sensitivity across patients was 84%, including 96% for the CHB-MIT database and 74% for the European epilepsy database. A 100% sensitivity was reached in 50% of patients, including 79% from the CHB-MIT database and 27% from the European epilepsy database. The median latency from seizure onset to its detection was 17 ± 10 s, with 84% of seizures being detected within 40 s.

SIGNIFICANCE

Personalized EEG signature combined with DTW appears to be a promising method to detect ictal events from a limited number of EEG channels with high sensitivity despite low rate of false alarms, high degree of interpretability, and low computational complexity, compatible with its future use in wearable devices.

Multimodal nocturnal seizure detection in children with epilepsy: A prospective, multicenter, long-term, in-home trial

OBJECTIVE

There is a pressing need for reliable automated seizure detection in epilepsy care. Performance evidence on ambulatory non-electroencephalography-based seizure detection devices is low, and evidence on their effect on caregiver's stress, sleep, and quality of life (QoL) is still lacking. We aimed to determine the performance of NightWatch, a wearable nocturnal seizure detection device, in children with epilepsy in the family home setting and to assess its impact on caregiver burden.

METHODS

We conducted a phase 4, multicenter, prospective, video-controlled, in-home NightWatch implementation study (NCT03909984). We included children aged 4-16 years, with ≥1 weekly nocturnal major motor seizure, living at home. We compared a 2-month baseline period with a 2-month NightWatch intervention. The primary outcome was the detection performance of NightWatch for major motor seizures (focal to bilateral or generalized tonic-clonic [TC] seizures, focal to bilateral or generalized tonic seizures lasting >30 s, hyperkinetic seizures, and a remainder category of focal to bilateral or generalized clonic seizures and "TC-like" seizures). Secondary outcomes included caregivers' stress (Caregiver Strain Index [CSI]), sleep (Pittsburgh Quality of Sleep Index), and QoL (EuroQol five-dimension five-level scale).

RESULTS

We included 53 children (55% male, mean age = 9.7 ± 3.6 years, 68% learning disability) and analyzed 2310 nights (28 173 h), including 552 major motor seizures. Nineteen participants did not experience any episode of interest during the trial. The median detection sensitivity per participant was 100% (range = 46%-100%), and the median individual false alarm rate was .04 per hour (range = 0-.53). Caregiver's stress decreased significantly (mean total CSI score = 8.0 vs. 7.1, p = .032), whereas caregiver's sleep and QoL did not change significantly during the trial.

SIGNIFICANCE

The NightWatch system demonstrated high sensitivity for detecting nocturnal major motor seizures in children in a family home setting and reduced caregiver stress.

Personalized seizure detection using logistic regression machine learning based on wearable ECG-monitoring device

PURPOSE

Wearable automated detection devices of focal epileptic seizures are needed to alert patients and caregivers and to optimize the medical treatment. Heart rate variability (HRV)-based seizure detection devices have presented good detection sensitivity. However, false alarm rates (FAR) are too high.

METHODS

In this phase-2 study we pursued to decrease the FAR, by using patient-adaptive logistic regression machine learning (LRML) to improve the performance of a previously published HRV-based seizure detection algorithm. ECG-data were prospectively collected using a dedicated wearable electrocardiogram-device during long-term video-EEG monitoring. Sixty-two patients had 174 seizures during 4,614 h recording. The dataset was divided into training-, cross-validation-, and test-sets (chronological) in order to avoid overfitting. Patients with >50 beats/min change in heart rate during first recorded seizure were selected as responders. We compared 18 LRML-settings to find the optimal algorithm.

RESULTS

The patient-adaptive LRML-classifier in combination with using only responders to train the initial decision boundary was superior to both the generic approach and including non-responders to train the LRML-classifier. Using the optimal setting of the LRML in responders in the test dataset yielded a sensitivity of 78.2% and FAR of 0.62/24 h. The FAR was reduced by 31% compared to the previous method, upholding similar sensitivity.

CONCLUSION

The novel, patient-adaptive LRML seizure detection algorithm outperformed both the generic approach and the previously published patient-tailored method. The proposed method can be implemented in a wearable online HRV-based seizure detection system alerting patients and caregivers of seizures and improve seizure-count which may help optimizing the patient treatment.

Assessing epilepsy-related autonomic manifestations: Beyond cardiac and respiratory investigations

The Autonomic Nervous System (ANS) regulates many critical physiological functions. Its control relies on cortical input, especially limbic areas, which are often involved in epilepsy. Peri-ictal autonomic dysfunction is now well documented, but inter-ictal dysregulation is less studied. In this review, we discuss the available data on epilepsy-related autonomic dysfunction and the objective tests available. Epilepsy is associated with sympathetic-parasympathetic imbalance and a shift towards sympathetic dominance. Objective tests report alterations in heart rate, baroreflex function, cerebral autoregulation, sweat glands activity, thermoregulation, gastrointestinal and urinary function. However, some tests have found contradictory results and many tests suffer from a lack of sensitivity and reproducibility. Further study on interictal ANS function is required to further understand autonomic dysregulation and the potential association with clinically-relevant complications, including risk of Sudden Unexpected Death In Epilepsy (SUDEP).

Detect, predict, and prevent acute seizures and status epilepticus

Status epilepticus is one of the most frequent pediatric neurological emergencies. While etiology is often influencing the outcome, more easily modifiable risk factors of outcome include detection of prolonged convulsive seizures and status epilepticus and appropriately dosed and timely applied medication treatment. Unpredictability and delayed or incomplete treatment may at times lead to longer seizures, thereby affecting outcomes. Barriers in the care of acute seizures and status epilepticus include the identification of patients at greatest risk of convulsive status epilepticus, potential stigma, distrust, and uncertainties in acute seizure care, including caregivers, physicians, and patients. Furthermore, unpredictability, detection capability, and identification of acute seizures and status epilepticus, limitations in access to obtaining and maintaining appropriate treatment, and rescue treatment options pose challenges. Additionally, timing and dosing of treatment and related acute management algorithms, potential variations in care due to healthcare and physician culture and preference, and factors related to access, equity, diversity, and inclusion of care. We outline strategies for the identification of patients at risk of acute seizures and status epilepticus, improved status epilepticus detection and prediction, and acute closed-loop treatment and status epilepticus prevention. This paper was presented at the 8th London-Innsbruck Colloquium on Status Epilepticus and Acute Seizures held in September 2022.

Clinical utility of a video/audio-based epilepsy monitoring system Nelli

OBJECTIVE

The aim of this study was to evaluate the clinical utility of a semi-automated hybrid video/audio-based epilepsy monitoring system (Nelli®) in a home setting.

METHODS

In this retrospective study, 104 consecutive patients underwent Nelli-registration for an average of 29 days at their home. The seizure-related data obtained from the registration were assessed to investigate the utility of the Nelli-registration regarding clinical decision-making.

RESULTS

Of 104 patients, Nelli® hybrid system was able to recognize clinically relevant events in 83 (80%) patients: epileptic seizures in 67 (65%) and nonepileptic events in 16 (15%). A total of 2767 epileptic seizures of different seizure types were captured and identified. These seizures included not only tonic-clonic seizures but also other complex or simple motor seizures. For the outcomes regarding clinical decision-making, a need for a new therapeutic intervention was recognized in 54 (51.9%) patients based on the number and severity of seizures captured by Nelli-registration. In 12 (11.5%) patients, the need to change the treatment plan was excluded because no evidence of suspected epileptic seizures was found. Nelli-registration aided in confirming the therapeutic efficacy of modifications of antiseizure medications (ASMs) or neuromodulation therapies in 13 (12.5%) patients. Nelli-registration enabled to determine the change in seizure classification and facilitated to reach clear diagnostic conclusions in 11 (10.6%) patients. In 14 (13.5%) patients, there was no change in clinical outcome, as Nelli-registration was unable to infer any clinical decision either due to inconclusive results or lack of typical events. Seizures detected during Nelli-registration aided in decision-making for therapeutic interventions in 71 (68%) patients. Altogether, 44 (42%) patients had adjustment of ASMs, and in 9 (9%) patients, Nelli-registrations led to the change in the settings of vagus nerve stimulation (VNS) or deep brain stimulation (DBS) treatment. Additionally, 18 (17%) patients were referred to presurgical evaluation or established a baseline seizure frequency before surgical implantation for neuromodulation treatment with VNS or DBS, while 33 (32%) patients had no change in therapy. Nine patients (8.7%) were referred to video-EEG monitoring (VEM), as Nelli-recorded events highlighted the need for presurgical evaluation in 6 patients or further diagnostic evaluation in 3 patients.

CONCLUSION

This study confirms the clinical utility of the video/audio monitoring system Nelli® in home settings. Home monitoring with Nelli® hybrid system provides a new alternative for the assessment of frequency and type of epileptic seizures as well as for a recognition of nonepileptic events. Thus, Nelli-registration can facilitate the optimization of seizure monitoring and management in clinical practice, complementing existing methods such as VEM and ambulatory EEG recordings.

Feasibility of video/audio monitoring in the analysis of motion and treatment effects on night-time seizures - Interventional study

THE AIM OF THE STUDY

This pilot study assessed the ability of a video/audio-based seizure monitoring system to evaluate (I) baseline frequency and severity of nocturnal seizures with motor features in patients with drug-resistant epilepsy (DRE) and (II) the individual effect of brivaracetam (BRV) treatment on number, duration and movement intensity of these seizure types. Algorithmic feature analysis was developed for assessment of qualitative changes in movement intensity measurements within seizure types before and after BRV intervention.

MATERIALS AND METHODS

Night-time motor seizures of recruited patients were recorded in two separate four-week monitoring periods. The first period defined a prescreening phase (n = 13 patients) to establish a baseline, and the second period defined the intervention phase (n = 9 patients), with BRV initiated during the second week of the second monitoring period. All recorded nights were analyzed by an expert video reviewer, and all unequivocal seizures were classified by an epileptologist. Seizure frequencies using both seizure diaries and video monitoring were compared. The effect of BRV on both seizure duration and movement intensity was assessed by numerical comparison of visual features calculated from motion characteristics of the video, as well as spectral features from the recorded audio. The statistical significance of changes in seizure duration and intensity before and after the intervention were investigated by Wilcoxon rank-sum test and visual inspection of Kernel density estimation.

RESULTS

8 patients marked seizures in their seizure diaries during the prescreening phase. During the three-week follow-up, three patients achieved > 50% seizure decrease, four patients did not respond to treatment, and two patients experienced worsening of seizures. Five patients were able to document 40-70% of their seizures compared to the video/audio monitoring system. According to the signal feature analysis the intervention decreased movement intensity with clear clinical significance in three patients, whereas statistically significant differences in features appeared in 8 out of 9 patients.

CONCLUSIONS

The novel video/audio monitoring system improved the evaluation of treatment effect compared to the seizure diaries and succeeded in providing a comparative intra-patient assessment of the movement intensity and duration of the recorded seizures.

The Prospects of Non-EEG Seizure Detection Devices in Dogs

The unpredictable nature of seizures is challenging for caregivers of epileptic dogs, which calls the need for other management strategies such as seizure detection devices. Seizure detection devices are systems that rely on non-electroencephalographic (non-EEG) ictal changes, designed to detect seizures. The aim for its use in dogs would be to provide owners with a more complete history of their dog's seizures and to help install prompt (and potentially life-saving) intervention. Although seizure detection via wearable intracranial EEG recordings is associated with a higher sensitivity in humans, there is robust evidence for reliable detection of generalized tonic-clonic seizures (GTCS) using non-EEG devices. Promising non-EEG changes described in epileptic humans, include heart rate variability (HRV), accelerometry (ACM), electrodermal activity (EDA), and electromyography (EMG). Their sensitivity and false detection rate to detect seizures vary, however direct comparison of studies is nearly impossible, as there are many differences in study design and standards for testing. A way to improve sensitivity and decrease false-positive alarms is to combine the different parameters thereby profiting from the strengths of each one. Given the challenges of using EEG in veterinary clinical practice, non-EEG ictal changes could be a promising alternative to monitor seizures more objectively. This review summarizes various seizure detection devices described in the human literature, discusses their potential use and limitations in veterinary medicine and describes what is currently known in the veterinary literature.

Parental preferences for seizure detection devices: a discrete choice experiment

Objective

Previous studies identified essential user preferences for seizure detection devices (SDDs), without addressing their relative strength. We performed a discrete choice experiment (DCE) to quantify attributes' strength, and to identify the determinants of user SDD preferences.

Methods

We designed an online questionnaire targeting parents of children with epilepsy to define the optimal balance between SDD sensitivity and positive predictive value (PPV) while accounting for individual seizure frequency. We selected five DCE attributes from a recent study. Using a Bayesian design, we constructed 11 unique choice tasks and analyzed these using a mixed multinomial logit model.

Results

One hundred parents responded to the online questionnaire link; 49 completed all tasks, whereas 28 completed the questions, but not the DCE. Most parents preferred a relatively high sensitivity (80%–90%) over a high PPV (>50%). The preferred sensitivity‐to‐PPV ratio correlated with seizure frequency (r = −.32), with a preference for relative high sensitivity and low PPV among those with relative low seizure frequency (p = .04). All DCE attributes significantly impacted parental choices. Parents expressed preferences for consulting a neurologist before device use, personally training the device's algorithm, interaction with their child via audio and video, alarms for all seizure types, and an interface detailing measurements during an alarm. Preferences varied between subgroups (learning disability or not, SDD experience, relative low vs. high seizure frequency based on the population median).

Significance

Various attributes impact parental SDD preferences and may explain why preferences vary among users. Tailored approaches may help to meet the contrasting needs among SDD users.

Wearable electroencephalography for ultra-long-term seizure monitoring: a systematic review and future prospects

INTRODUCTION

: Wearable electroencephalography (EEG) for objective seizure counting might transform the clinical management of epilepsy. Non-EEG modalities have been validated for the detection of convulsive seizures, but there is still an unmet need for the detection of non-convulsive seizures.

AREAS COVERED

: The main objective of this systematic review was to explore the current status on wearable surface- and subcutaneous EEG for long-term seizure monitoring in epilepsy. We included 17 studies and evaluated the progress on the field, including device specifications, intended populations, and main results on the published studies including diagnostic accuracy measures. Furthermore, we examine the hurdles for widespread clinical implementation. This systematic review and expert opinion both consults the PRISMA guidelines and reflects on the future perspectives of this emerging field.

EXPERT OPINION

: Wearable EEG for long-term seizure monitoring is an emerging field, with plenty of proposed devices and proof-of-concept clinical validation studies. The possible implications of these devices are immense including objective seizure counting and possibly forecasting. However, the true clinical value of the devices, including effects on patient important outcomes and clinical decision making is yet to be unveiled and large-scale clinical validation trials are called for.

Autonomic manifestations of epilepsy: emerging pathways to sudden death?

Epileptic networks are intimately connected with the autonomic nervous system, as exemplified by a plethora of ictal (during a seizure) autonomic manifestations, including epigastric sensations, palpitations, goosebumps and syncope (fainting). Ictal autonomic changes might serve as diagnostic clues, provide targets for seizure detection and help us to understand the mechanisms that underlie sudden unexpected death in epilepsy (SUDEP). Autonomic alterations are generally more prominent in focal seizures originating from the temporal lobe, demonstrating the importance of limbic structures to the autonomic nervous system, and are particularly pronounced in focal-to-bilateral and generalized tonic-clonic seizures. The presence, type and severity of autonomic features are determined by the seizure onset zone, propagation pathways, lateralization and timing of the seizures, and the presence of interictal autonomic dysfunction. Evidence is mounting that not all autonomic manifestations are linked to SUDEP. In addition, experimental and clinical data emphasize the heterogeneity of SUDEP and its infrequent overlap with sudden cardiac death. Here, we review the spectrum and diagnostic value of the mostly benign and self-limiting autonomic manifestations of epilepsy. In particular, we focus on presentations that are likely to contribute to SUDEP and discuss how wearable devices might help to prevent SUDEP.

Prospective Study of a Multimodal Convulsive Seizure Detection Wearable System on Pediatric and Adult Patients in the Epilepsy Monitoring Unit

Background: Using machine learning to combine wrist accelerometer (ACM) and electrodermal activity (EDA) has been shown effective to detect primarily and secondarily generalized tonic-clonic seizures, here termed as convulsive seizures (CS). A prospective study was conducted for the FDA clearance of an ACM and EDA-based CS-detection device based on a predefined machine learning algorithm. Here we present its performance on pediatric and adult patients in epilepsy monitoring units (EMUs).

Methods: Patients diagnosed with epilepsy participated in a prospective multi-center clinical study. Three board-certified neurologists independently labeled CS from video-EEG. The Detection Algorithm was evaluated in terms of Sensitivity and false alarm rate per 24 h-worn (FAR) on all the data and on only periods of rest. Performance were analyzed also applying the Detection Algorithm offline, with a less sensitive but more specific parameters configuration (“Active mode”).

Results: Data from 152 patients (429 days) were used for performance evaluation (85 pediatric aged 6–20 years, and 67 adult aged 21–63 years). Thirty-six patients (18 pediatric) experienced a total of 66 CS (35 pediatric). The Sensitivity (corrected for clustered data) was 0.92, with a 95% confidence interval (CI) of [0.85-1.00] for the pediatric population, not significantly different (p > 0.05) from the adult population's Sensitivity (0.94, CI: [0.89–1.00]). The FAR on the pediatric population was 1.26 (CI: [0.87–1.73]), higher (p < 0.001) than in the adult population (0.57, CI: [0.36–0.81]). Using the Active mode, the FAR decreased by 68% while reducing Sensitivity to 0.95 across the population. During rest periods, the FAR's were 0 for all patients, lower than during activity periods (p < 0.001).

Conclusions: Performance complies with FDA's requirements of a lower bound of CI for Sensitivity higher than 0.7 and of a FAR lower than 2, for both age groups. The pediatric FAR was higher than the adult FAR, likely due to higher pediatric activity. The high Sensitivity and precision (having no false alarms) during sleep might help mitigate SUDEP risk by summoning caregiver intervention. The Active mode may be advantageous for some patients, reducing the impact of the FAR on daily life. Future work will examine the performance and usability outside of EMUs.

Video-Based Detection of Generalized Tonic-Clonic Seizures Using Deep Learning

Timely detection of seizures is crucial to implement optimal interventions, and may help reduce the risk of sudden unexpected death in epilepsy (SUDEP) in patients with generalized tonic-clonic seizures (GTCSs). While video-based automated seizure detection systems may be able to provide seizure alarms in both in-hospital and at-home settings, earlier studies have primarily employed hand-designed features for such a task. In contrast, deep learning-based approaches do not rely on prior feature selection and have demonstrated outstanding performance in many data classification tasks. Despite these advantages, neural network-based video classification has rarely been attempted for seizure detection. We here assessed the feasibility and efficacy of automated GTCSs detection from videos using deep learning. We retrospectively identified 76 GTCS videos from 37 participants who underwent long-term video-EEG monitoring (LTM) along with interictal video data from the same patients, and 10 full-night seizure-free recordings from additional patients. Using a leave-one-subject-out cross-validation approach (LOSO-CV), we evaluated the performance to detect seizures based on individual video frames (convolutional neural networks, CNNs) or video sequences [CNN+long short-term memory (LSTM) networks]. CNN+LSTM networks based on video sequences outperformed GTCS detection based on individual frames yielding a mean sensitivity of 88% and mean specificity of 92% across patients. The average detection latency after presumed clinical seizure onset was 22 seconds. Detection performance increased as a function of training dataset size. Collectively, we demonstrated that automated video-based GTCS detection with deep learning is feasible and efficacious. Deep learning-based methods may be able to overcome some limitations associated with traditional approaches using hand-crafted features, serve as a benchmark for future methods and analyses, and improve further with larger datasets.

Ictal and Interictal Cardiac Manifestations in Epilepsy. A Review of Their Relation With an Altered Central Control of Autonomic Functions and With the Risk of SUDEP

There is a complex interrelation between epilepsy and cardiac pathology, with both acute and long-term effects of seizures on the regulation of the cardiac rhythm and on the heart functioning. A specific issue is the potential relation between these cardiac manifestations and the risk of Sudden and Unexpected Death in Epilepsy (SUDEP), with unclear respective role of centrally-control ictal changes, long-term epilepsy-related dysregulation of the neurovegetative control and direct effects on the heart function. In the present review, we detailed available data about ictal cardiac changes, along with interictal cardiac manifestations associated with long-term functional and structural alterations of the heart. Pathophysiological mechanisms of these cardiac changes are discussed, with a specific focus on central mechanisms and the investigation of a possible deregulation of the central control of autonomic functions in addition to the role of catecholamine and hypoxemia on heart.

Seizure detection devices: Exploring caregivers' needs and wishes

INTRODUCTION

User preferences for seizure detection devices (SDDs) have been previously assessed using surveys and interviews, but these have not addressed the latent needs and wishes. Context mapping is an approach in which designers explore users' dreams and fears to anticipate potential future experiences and optimize the product design.

METHODS

A generative group session was held using the context mapping approach. Two types of nocturnal SDD users were included: three professional caregivers at a residential care facility and two informal caregivers of children with refractory epilepsy and learning disabilities. Participants were invited to share their personal SDD experiences and briefed to make their needs and wishes explicit. The audiotaped session was transcribed and analyzed together with the collected material using inductive content analysis. The qualitative data was classified by coding the content, grouping codes into categories and themes, and combining those into general statements (abstraction).

RESULTS

"Trust" emerged as the most important theme, entangling various emotional and practical factors that influence caregiver's trust in a device. Caregivers expressed several factors that could help to gain their trust in an SDD, including integration of different modalities, insight on all parameters overnight, personal adjustment of the algorithm, recommendation by a neurologist, and a set-up period. Needs regarding alerting seemed to differ between the two types of caregivers in our study: professional caregivers preferred to be alerted only for potentially dangerous seizures, whereas informal caregivers emphasized the urge to be alerted for every event, thus indicating the need for personal adjustment of SDD settings.

CONCLUSION

In this explorative study, we identified several key elements for nocturnal SDD implementation including the importance of gaining trust and the possibility to adjust SDD settings for different types of caregivers.

Precision Medicine: Academic dreaming or clinical reality?

Precision medicine can be distilled into a concept of accounting for an individual's unique collection of clinical, physiologic, genetic, and sociodemographic characteristics to provide patient-level predictions of disease course and response to therapy. Abundant evidence now allows us to determine how an average person with epilepsy will respond to specific medical and surgical treatments. This is useful, but not readily applicable to an individual patient. This has brought into sharp focus the desire for a more individualized approach through which we counsel people based on individual characteristics, as opposed to population-level data. We are now accruing data at unprecedented rates, allowing us to convert this ideal into reality. In addition, we have access to growing volumes of administrative and electronic health records data, biometric, imaging, genetics data, microbiome, and other "omics" data, thus paving the way toward phenome-wide association studies and "the epidemiology of one." Despite this, there are many challenges ahead. The collating, integrating, and storing sensitive multimodal data for advanced analytics remains difficult as patient consent and data security issues increase in complexity. Agreement on many aspects of epilepsy remains imperfect, rendering models sensitive to misclassification due to a lack of "ground truth." Even with existing data, advanced analytics models are prone to overfitting and often failure to generalize externally. Finally, uptake by clinicians is often hindered by opaque, "black box" algorithms. Systematic approaches to data collection and model generation, and an emphasis on education to promote uptake and knowledge translation, are required to propel epilepsy-based precision medicine from the realm of the theoretical into routine clinical practice.

Evaluation of an Activity Tracker to Detect Seizures Using Machine Learning

Currently, the tracking of seizures is highly subjective, dependent on qualitative information provided by the patient and family instead of quantifiable seizure data. Usage of a seizure detection device to potentially detect seizure events in a population of epilepsy patients has been previously done. Therefore, we chose the Fitbit Charge 2 smart watch to determine if it could detect seizure events in patients when compared to continuous electroencephalographic (EEG) monitoring for those admitted to an epilepsy monitoring unit. A total of 40 patients were enrolled in the study that met the criteria between 2015 and 2016. All seizure types were recorded. Twelve patients had a total of 53 epileptic seizures. The patient-aggregated receiver operating characteristic curve had an area under the curve of 0.58 [0.56, 0.60], indicating that the neural network models were generally able to detect seizure events at an above-chance level. However, the overall low specificity implied a false alarm rate that would likely make the model unsuitable in practice. Overall, the use of the Fitbit Charge 2 activity tracker does not appear well suited in its current form to detect epileptic seizures in patients with seizure activity when compared to data recorded from the continuous EEG.

Machine learning and wearable devices of the future

Machine learning (ML) is increasingly recognized as a useful tool in healthcare applications, including epilepsy. One of the most important applications of ML in epilepsy is seizure detection and prediction, using wearable devices (WDs). However, not all currently available algorithms implemented in WDs are using ML. In this review, we summarize the state of the art of using WDs and ML in epilepsy, and we outline future development in these domains. There is published evidence for reliable detection of epileptic seizures using implanted electroencephalography (EEG) electrodes and wearable, non-EEG devices. Application of ML using the data recorded with WDs from a large number of patients could change radically the way we diagnose and manage patients with epilepsy.

Biomarkers of seizure severity derived from wearable devices

Besides triggering alarms, wearable seizure detection devices record a variety of biosignals that represent biomarkers of seizure severity. There is a need for automated seizure characterization, to identify high-risk seizures. Wearable devices can automatically identify seizure types with the highest associated morbidity and mortality (generalized tonic-clonic seizures), quantify their duration and frequency, and provide data on postictal position and immobility, autonomic changes derived from electrocardiography/heart rate variability, electrodermal activity, respiration, and oxygen saturation. In this review, we summarize how these biosignals reflect seizure severity, and how they can be monitored in the ambulatory outpatient setting using wearable devices. Multimodal recording of these biosignals will provide valuable information for individual risk assessment, as well as insights into the mechanisms and prevention of sudden unexpected death in epilepsy.

Automated video-based detection of nocturnal motor seizures in children

Seizure detection devices can improve epilepsy care, but wearables are not always tolerated. We previously demonstrated good performance of a real‐time video‐based algorithm for detection of nocturnal convulsive seizures in adults with learning disabilities. The algorithm calculates the relative frequency content based on the group velocity reconstruction from video‐sequence optical flow. We aim to validate the video algorithm on nocturnal motor seizures in a pediatric population. We retrospectively analyzed the algorithm performance on a database including 1661 full recorded nights of 22 children (age = 3‐17 years) with refractory epilepsy at home or in a residential care setting. The algorithm detected 118 of 125 convulsions (median sensitivity per participant = 100%, overall sensitivity = 94%, 95% confidence interval = 61%‐100%) and identified all 135 hyperkinetic seizures. Most children had no false alarms; 81 false alarms occurred in six children (median false alarm rate [FAR] per participant per night = 0 [range = 0‐0.47], overall FAR = 0.05 per night). Most false alarms (62%) were behavior‐related (eg, awake and playing in bed). Our noncontact detection algorithm reliably detects nocturnal epileptic events with only a limited number of false alarms and is suitable for real‐time use.

Seizure detection using heart rate variability: A prospective validation study

Although several validated seizure detection algorithms are available for convulsive seizures, detection of nonconvulsive seizures remains challenging. In this phase 2 study, we have validated a predefined seizure detection algorithm based on heart rate variability (HRV) using patient-specific cutoff values. The validation data set was independent from the previously published data set. Electrocardiography (ECG) was recorded using a wearable device (ePatch) in prospectively recruited patients. The diagnostic gold standard was inferred from video-EEG monitoring. Because HRV-based seizure detection is suitable only for patients with marked ictal autonomic changes, we defined responders as the patients who had a>50 beats/min ictal change in heart rate. Eleven of the 19 included patients with seizures (57.9%) fulfilled this criterion. In this group, the algorithm detected 20 of the 23 seizures (sensitivity: 87.0%). The algorithm detected all but one of the 10 recorded convulsive seizures and all of the 8 focal impaired awareness seizures, and it missed 2 of the 4 focal aware seizures. The median sensitivity per patient was 100% (in nine patients all seizures were detected). The false alarm rate was 0.9/24 h (0.22/night). Our results suggest that HRV-based seizure detection has high performance in patients with marked autonomic changes.

Wearable devices for seizure detection: Is it time to translate into our clinical practice?

With the exponential development of mobile health technologies over the past ten years, there has been a growing interest in the potential applications in the field of epilepsy, and specifically for seizure detection. Better detection of seizures is probably one of the best ways to improve patient safety. Overall, we are observing an exponential increase in the number of non-EEG based seizure detection systems and a progressive homogenization of their evaluation procedures. Most importantly, the properties of these devices for detection of tonic-clonic seizures are now very interesting, both in terms of sensitivity and in terms of false-alarm rates. Accordingly, we might expect that these be used in clinical practice in the near future, especially in patients at high risk of seizure-related injuries or sudden unexpected death in epilepsy (SUDEP).

Seizure detection devices and health-related quality of life: A patient- and caregiver-centered evaluation

INTRODUCTION

The unpredictability of epilepsy has a severe impact on health-related quality of life (HR-QOL) for people with epilepsy. Seizure detection devices have the potential to improve HR-QOL by improving seizure safety, reducing caregiver hypervigilance, and reducing seizure anxiety. Emerging data have led to an improved understanding of characteristics that promote acceptability of detection devices for people with epilepsy and caregivers. However, whether usage of seizure detection devices is associated with clinically meaningful improvement in anxiety and HR-QOL remains poorly understood.

METHODS

We analyzed cross-sectional survey data collected first-hand from 371 people with epilepsy and caregivers on seizure detection device and HR-QOL using an enriched population of electronic seizure diary users. Metrics related to quality of life and anxiety reduction were compared between users and nonusers of seizure detection devices.

RESULTS

Compared with nonusers of seizure detection devices, device users were significantly more likely to have been impacted by epilepsy in multiple HR-QOL domains, including anxiety, mood, emotional regulation/aggression, speech/language, sleep quality, social life, activities of daily living, independence, and education/academic potential. The majority (80.2%) of people using seizure detection devices experienced moderate or greater anxiety reduction from seizure detection device usage, while 11.1% reported that detection devices did not help at all with anxiety. Despite potential benefit, seizure detection devices were used only by a minority (21.8%) of people with epilepsy surveyed, and usage tended to be skewed toward younger patient age, higher income, and caregivers. There was no significant difference in overall HR-QOL between users and nonusers.

CONCLUSIONS

Seizure detection devices provide moderate or greater anxiety reduction among the majority of people with epilepsy and their caregivers, but current translatability into improvements in overall HR-QOL may be limited. Affordability and technological support are potential barriers to maximizing benefit equally among the epilepsy community. These considerations may be useful to help guide future device development and inform patient-clinician discussions on device usage and HR-QOL.

Sounds of seizures

PURPOSE

A phase I feasibility study to determine the accuracy of identifying seizures based on audio recordings.

METHODS

We systematically generated 166 audio clips of 30 s duration from 83 patients admitted to an epilepsy monitoring unit between 1/2015 and 12/2016, with one clip during a seizure period and one clip during a non-seizure control period for each patient. Five epileptologists performed a blinded review of the audio clips and rated whether a seizure occurred or not, and indicated the confidence level (low or high) of their rating. The accuracy of individual and consensus ratings were calculated.

RESULTS

The overall performance of the consensus rating between the five epileptologists showed a positive predictive value (PPV) of 0.91 and a negative predictive value (NPV) of 0.66. The performance improved when confidence was high (PPV of 0.96, NPV of 0.70). The agreement between the epileptologists was moderate with a kappa of 0.584. Hyperkinetic (PPV 0.92, NPV 0.86) and tonic-clonic (PPV and NPV 1.00) seizures were most accurately identified. Seizures with automatisms only and non-motor seizures could not be accurately identified. Specific seizure-related sounds associated with accurate identification included disordered breathing (PPV and NPV 1.00), rhythmic sounds (PPV 0.93, NPV 0.80), and ictal vocalizations (PPV 1.00, NPV 0.97).

CONCLUSION

This phase I feasibility study shows that epileptologists are able to accurately identify certain seizure types from audio recordings when the seizures produce sounds. This provides guidance for the development of audio-based seizure detection devices and demonstrate which seizure types could potentially be detected.

Seizure detection based on heart rate variability using a wearable electrocardiography device

OBJECTIVE

To assess the feasibility and accuracy of seizure detection based on heart rate variability (HRV) using a wearable electrocardiography (ECG) device. Noninvasive devices for detection of convulsive seizures (generalized tonic-clonic and focal to bilateral tonic-clonic seizures) have been validated in phase 2 and 3 studies. However, detection of nonconvulsive seizures still needs further research, since currently available methods have either low sensitivity or an extremely high false alarm rate (FAR).

METHODS

In this phase 2 study, we prospectively recruited patients admitted to long-term video-EEG monitoring (LTM). ECG was recorded using a dedicated wearable device. Seizures were automatically detected using HRV parameters computed off-line, blinded to all other data. We compared the performance of 26 automated algorithms with the seizure time-points marked by experts who reviewed the LTM recording. Patients were classified as responders if >66% of their seizures were detected.

RESULTS

We recruited 100 consecutive patients and analyzed 126 seizures (108 nonconvulsive and 18 convulsive) from 43 patients who had seizures during monitoring. The best-performing HRV algorithm combined a measure of sympathetic activity with a measure of how quickly HR changes occurred. The algorithm identified 53.5% of the patients with seizures as responders. Among responders, detection sensitivity was 93.1% (95% CI: 86.6%-99.6%) for all seizures and 90.5% (95% CI: 77.4%-97.3%) for nonconvulsive seizures. FAR was 1.0/24 h (0.11/night). Median seizure detection latency was 30 s. Typically, patients with prominent autonomic nervous system changes were responders: An ictal change of >50 heartbeats per minute predicted who would be responder with a positive predictive value of 87% and a negative predictive value of 90%.

SIGNIFICANCE

The automated HRV algorithm, using ECG recorded with a wearable device, has high sensitivity for detecting seizures, including the nonconvulsive ones. FAR was low during the night. This approach is feasible in patients with prominent ictal autonomic changes.