Anouk Van de Vel

Non-EEG seizure-detection systems and potential SUDEP prevention: state of the art.

PURPOSE There is a need for a seizure-detection system that can be used long-term and in home situations for early intervention and prevention of seizure related side effects including SUDEP (sudden unexpected death in epileptic patients). The gold standard for monitoring epileptic seizures involves video/EEG (electro-encephalography), which is uncomfortable for the patient, as EEG electrodes are attached to the scalp. EEG analysis is also labour-intensive and has yet to be automated and adapted for real-time monitoring. It is therefore usually performed in a hospital setting, for a few days at the most. The goal of this article is to provide an overview of body signals that can be measured, along with corresponding methods, state-of-art research, and commercially available systems, as well as to stress the importance of a good detection system. METHOD Narrative literature review. RESULTS A range of body signals can be monitored for the purpose of seizure detection. It is particularly interesting to include monitoring of autonomic dysfunction, as this may be an important patho-physiological mechanism of SUDEP, and of movement, as many seizures have a motor component. CONCLUSION The most effective seizure detection systems are multimodal. Such systems should also be comfortable and low-power. The body signals and modalities on which a system is based should take account of the users seizure types and personal preferences.

Long-term home monitoring of hypermotor seizures by patient-worn accelerometers

Long-term home monitoring of epileptic seizures is not feasible with the gold standard of video/electro-encephalography (EEG) monitoring. The authors developed a system and algorithm for nocturnal hypermotor seizure detection in pediatric patients based on an accelerometer (ACM) attached to extremities. Seizure detection is done using normal movement data, meaning that the system can be installed in a new patients room immediately as prior knowledge on the patients seizures is not needed for the patient-specific model. In this study, the authors compared video/EEG-based seizure detection with ACM data in seven patients and found a sensitivity of 95.71% and a positive predictive value of 57.84%. The authors focused on hypermotor seizures given the availability of this seizure type in the data, the typical occurrence of these seizures during sleep, i.e., when the measurements were done, and the importance of detection of hypermotor seizures given their often refractory nature and the possible serious consequences. To our knowledge, it is the first detection system focusing on this type of seizure in pediatric patients.

Accelerometry-Based Home Monitoring for Detection of Nocturnal Hypermotor Seizures Based on Novelty Detection

Nocturnal home monitoring of epileptic children is often not feasible due to the cumbersome manner of seizure monitoring with the standard method of video/EEG-monitoring. We propose a method for hypermotor seizure detection based on accelerometers attached to the extremities. From the acceleration signals, multiple temporal, frequency, and wavelet-based features are extracted. After determining the features with the highest discriminative power, we classify movement events in epileptic and nonepileptic movements. This classification is only based on a nonparametric estimate of the probability density function of normal movements. Such approach allows us to build patient-specific models to classify movement data without the need for seizure data that are rarely available. If, in the test phase, the probability of a data point (event) is lower than a threshold, this event is considered to be an epileptic seizure; otherwise, it is considered as a normal nocturnal movement event. The mean performance over seven patients gives a sensitivity of 95.24% and a positive predictive value of 60.04%. However, there is a noticeable interpatient difference.

Non-EEG seizure detection systems and potential SUDEP prevention: State of the art: Review and update

PURPOSE Detection of, and alarming for epileptic seizures is increasingly demanded and researched. Our previous review article provided an overview of non-invasive, non-EEG (electro-encephalography) body signals that can be measured, along with corresponding methods, state of the art research, and commercially available systems. Three years later, many more studies and devices have emerged. Moreover, the boom of smart phones and tablets created a new market for seizure detection applications. METHOD We performed a thorough literature review and had contact with manufacturers of commercially available devices. RESULTS This review article gives an updated overview of body signals and methods for seizure detection, international research and (commercially) available systems and applications. Reported results of non-EEG based detection devices vary between 2.2% and 100% sensitivity and between 0 and 3.23 false detections per hour compared to the gold standard video-EEG, for seizures ranging from generalized to convulsive or non-convulsive focal seizures with or without loss of consciousness. It is particularly interesting to include monitoring of autonomic dysfunction, as this may be an important pathophysiological mechanism of SUDEP (sudden unexpected death in epilepsy), and of movement, as many seizures have a motor component. CONCLUSION Comparison of research results is difficult as studies focus on different seizure types, timing (night versus day) and patients (adult versus pediatric patients). Nevertheless, we are convinced that the most effective seizure detection systems are multimodal, combining for example detection methods for movement and heart rate, and that devices should especially take into account the users seizure types and personal preferences.

Automated Detection of Tonic-Clonic Seizures Using 3-D Accelerometry and Surface Electromyography in Pediatric Patients.

Epileptic seizure detection is traditionally done using video/electroencephalography monitoring, which is not applicable for long-term home monitoring. In recent years, attempts have been made to detect the seizures using other modalities. In this study, we investigated the application of four accelerometers (ACM) attached to the limbs and surface electromyography (sEMG) electrodes attached to upper arms for the detection of tonic-clonic seizures. sEMG can identify the tension during the tonic phase of tonic-clonic seizure, while ACM is able to detect rhythmic patterns of the clonic phase of tonic-clonic seizures. Machine learning techniques, including feature selection and least-squares support vector machine classification, were employed for detection of tonic-clonic seizures from ACM and sEMG signals. In addition, the outputs of ACM and sEMG-based classifiers were combined using a late integration approach. The algorithms were evaluated on 1998.3 h of data recorded nocturnally in 56 patients of which seven had 22 tonic-clonic seizures. A multimodal approach resulted in a more robust detection of short and nonstereotypical seizures (91%), while the number of false alarms increased significantly compared with the use of single sEMG modality (0.28-0.5/12h). This study also showed that the choice of the recording system should be made depending on the prevailing pediatric patient-specific seizure characteristics and nonepileptic behavior.

Critical evaluation of four different seizure detection systems tested on one patient with focal and generalized tonic and clonic seizures

For long-term home monitoring of epileptic seizures, the measurement of extracerebral body signals such as abnormal movement is often easier and less obtrusive than monitoring intracerebral brain waves with electroencephalography (EEG). Non-EEG devices are commercially available but with little scientifically valid information and no consensus on which system works for which seizure type or patient. We evaluated four systems based on efficiency, comfort, and user-friendliness and compared them in one patient suffering from focal epilepsy with secondary generalization. The Emfit mat, Epi-Care device, and Epi-Care Free bracelet are commercially available alarm systems, while the VARIA (Video, Accelerometry, and Radar-Induced Activity recording) device is being developed by our team and requires offline analysis for seizure detection and does so by presenting the 5% or 10% (patient-specific) most abnormal movement events, irrespective of the number of seizures per night. As we chose to mimic the home situation, we did not record EEG and compared our results to the seizures reported by experienced staff that were monitoring the patient on a semicontinuous basis. This resulted in a sensitivity (sens) of 78% and false detection rate (FDR) of 0.55 per night for Emfit, sens 40% and FDR 0.41 for Epi-Care, sens 41% and FDR 0.05 for Epi-Care Free, and sens 56% and FDR 20.33 for VARIA. Good results were obtained by some of the devices, even though, as expected, nongeneralized and nonrhythmic motor seizures (involving the head only, having a tonic phase, or manifesting mainly as sound) were often missed. The Emfit mat was chosen for our patient, also based on user-friendliness (few setup steps), comfort (contactless), and possibility to adjust patient-specific settings. When in need of a seizure detection system for a patient, a thorough individual search is still required, which suggests the need for a database or overview including results of clinical trials describing the patient and their seizure types.

Detecting rare events using extreme value statistics applied to epileptic convulsions in children

OBJECTIVE Nocturnal home monitoring of epileptic children is often not feasible due to the cumbersome manner of seizure detection with the standard method of video electroencephalography monitoring. The goal of this paper is to propose a method for hypermotor seizure detection based on accelerometers that are attached to the extremities. METHODS Supervised methods that are commonly used in literature need annotation of data and hence require expert (neurologist) interaction resulting in a substantial cost. In this paper an unsupervised method is proposed that uses extreme value statistics and seizure detection based on a model of normal behavior that is estimated using all recorded and unlabeled data. In this way the expensive interaction can be avoided. RESULTS When applying this method to a labeled dataset, acquired from 7 patients, all hypermotor seizures are detected in 5 of the 7 patients with an average positive predictive value (PPV) of 53%. For evaluating the performance on an unlabeled dataset, seizure events are presented to the system as normal movement events. Since hypermotor seizures are rare compared to normal movements, the very few abnormal events have a negligible effect on the quality of the model. In this way, it was possible to evaluate the system for 3 of the 7 patients when 3% of the training set was composed of seizure events. This resulted in sensitivity scores of 80%, 22% and 90% and a PPV of 89%, 21% and 44% respectively. These scores are comparable with a state-of-the-art supervised machine learning based approach which requires a labeled dataset. CONCLUSIONS A person-dependent epileptic seizure detection method has been designed that requires little human interaction. In contrast to traditional machine learning approaches, the imbalance of the dataset does not cause substantial difficulties.

Integrating video and accelerometer signals for nocturnal epileptic seizure detection

Epileptic seizure detection is traditionally done using video/electroencephalogram (EEG) monitoring, which is not applicable in a home situation. In recent years, attempts have been made to detect the seizures using other modalities. In this paper we investigate if a combined usage of accelerometers attached to the limbs and video data would increase the performance compared to a single modality approach. Therefore, we used two existing approaches for seizure detection in accelerometers and video and combined them using a linear discriminant analysis (LDA) classifier. The results for a combined detection have a better positive predictive value (PPV) of 95.00% compared to the single modality detection and reached a sensitivity of 83.33%.

Automated non-EEG based seizure detection: Do users have a say?

PURPOSE Quality of life of patients with epilepsy depends largely upon unpredictability of seizure occurrence and would improve by predicting seizures or at least by detecting seizures (after their clinical onset) and react timely. Detection systems are available and researched, but little is known about the actual need and user preferences. The first indicates the market potential; the second allows us to incorporate user requirements into the engineering process. METHODS We questioned 20 pediatric and young adult patients, 114 caregivers, and 21 involved medical doctors and described, analyzed, and compared their experiences with systems for seizure detection, their opinions on usefulness and purpose of seizure detection, and their requirements for such a device. RESULTS Experience with detection systems is limited, but 65% of patients and caregivers and 85% of medical doctors express the usefulness, more so during night than day. The need is higher in patients with more severe intellectual disability. The higher the seizure frequency, the higher the need, opinions in the seizure-free group being more divided. Most patients and caregivers require 100% correct detection, and on average, one false alarm per seizure (one per week for those seizure-free) is accepted. Medical doctors allow 90% correct detections and between two false alarms per week and one per month depending on seizure frequency. Detection of seizures involving heavy movement and falls is judged most important by patients and caregivers and second to most by medical doctors. The latter judge heart rate monitoring most relevant, both towards seizure detection and SUDEP (sudden unexpected death in epilepsy) prevention. CONCLUSIONS The results, including a goal of 90% correct detections and one false alarm per seizure, should be considered in development of seizure detectors.

Online detection of tonic-clonic seizures in pediatric patients using ECG and low-complexity incremental novelty detection

Home monitoring of refractory epilepsy patients has become of more interest the last couple of decades. A biomedical signal that can be used for online seizure detection at home is the electrocardiogram. Previous studies have shown that tonic-clonic seizures are most often accompanied with a strong heart rate increase. The main issue however is the strong patient-specific behavior of the ictal heart rate features, which makes it hard to make a patient-independent seizure detection algorithm. A patient-specific algorithm might be a solution, but existing methods require the availability of data of several seizures, which would make them inefficient in case the first seizure only occurs after a couple of days. Therefore an online method is described here that automatically converts from a patient-independent towards a patient-specific algorithm as more patient-specific data become available. This is done by using online feedback from the users to previously given alarms. By using a simplified one-class classifier, no seizure training data needs to be available for a good performance. The method is already able to adapt to the patient-specific characteristics after a couple of hours, and is able to detect 23 of 24 seizures longer than 10s, with an average of 0.38 false alarms per hour. Due to its low-complexity, it can be easily used for wearable seizure detection at home.