Milica Milosevic

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.

Autonomic effects of refractory epilepsy on heart rate variability in children: influence of intermittent vagus nerve stimulation.

Aim  Vagus nerve stimulation (VNS) is a therapeutic option for individuals with refractory epilepsy. Individuals with refractory epilepsy are prone to dysfunction of the autonomic nervous system. Reduced heart rate variability is a marker of dysfunction of the autonomic nervous system. Our goal was to study heart rate variability in children with refractory epilepsy and the influence of VNS on this parameter.

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.

Instrumented BASFI (iBASFI) Shows Promising Reliability and Validity in the Assessment of Activity Limitations in Axial Spondyloarthritis

Objective. The Bath Ankylosing Spondylitis Functional Index (BASFI) is the most popular method to assess activity capacity in axial spondyloarthritis (axSpA), to our knowledge. It is endorsed by the Assessment of Spondyloarthritis international Society. But it may have recall bias or aberrant self-judgments in individual patients. Therefore, we aimed to (1) develop the instrumented BASFI (iBASFI) by adding a body-worn accelerometer with automated algorithms to performance-based measurements (PBM), (2) study the iBASFI’s core psychometric properties, and (3) reduce the number of iBASFI items. Methods. Twenty-eight patients with axSpA wore a 2-axial accelerometer while completing 12 PBM derived from the BASFI. A chronometer and both manual and “automated algorithm-based” acceleration segmentation identified movement time. Test-retest trials and methods (algorithm vs manual segmentation/chronometer/BASFI) were compared with ICC, standard error of measurement [percentage of movement time (SEM%)], and Spearman ρ correlation coefficients. Linear regression identified the optimal set of reliable iBASFI PBM. Results. Good to excellent test-retest reliability was found for 8/12 iBASFI items (ICC range 0.812–0.997, SEM range 0.4–30.4%), typically with repeated and fast movements. Automated algorithms excellently mimicked manual segmentation (ICC range 0.900–0.998) and the chronometer (ICC range 0.878–0.998) for 10/12 iBASFI items. Construct validity compared with the BASFI was confirmed for 7/12 iBASFI items (δ range 0.504–0.755). Together, sit-to-stand speed test (stBeta 0.483), cervical rotation (stBeta −0.392), and height (stBeta −0.375) explained 59% of the variance in the BASFI (p < 0.01). Conclusion. The proof-of-concept iBASFI showed promising reliability and validity in measuring activity capacity. The number of the iBASFI’s PBM may be minimized, but further validation in larger axSpA cohorts is needed before its clinical use.

DETECTION OF EPILEPTIC CONVULSIONS FROM ACCELEROMETRY SIGNALS THROUGH MACHINE LEARNING APPROACH

A seizure detection system in the non-clinical environment would enable long-term monitoring and give better insights into the number of seizures and their characteristics. Moreover, an alarm at seizure onset is important for alerting the parents or care-givers so they could comfort the child and optionally give the treatment. Therefore, we developed a patient-independent automatic algorithm for registration and detection of (tonic-)clonic seizures based on four accelerometers attached to the wrists and ankles. The objective is to classify two second epochs as seizure or non-seizure epochs employing supervised learning techniques. Starting from 140 features found in similar publications, a filter method based on mutual information is applied to remove irrelevant and redundant features. A least-squares support vector machine classifier is used to distinguish seizure and non-seizure epochs based on the selected features. For seizures longer than 30 seconds, median sensitivity of 100%, false detection rate of 0.39 h-1 and alarm delay of 15.2 s over all patients are reached.

Advanced EEG Processing for the Detection of Drowsiness in Drivers

Drowsiness is a serious problem for drivers which causes many accidents every day. It is estimated that drowsiness is the cause of four deaths and 100 injuries per day in the United States. In this paper two methods have been developed to detect drowsiness based on features of ocular artifacts in EEG signals. The ocular artifacts are derived from the EEG signals by using Canonical Correlation Analysis (BSS-CCA). Wavelet transforms are used to automatically select components containing eye blinks. Sixteen features are then calculated from the eye blink and used for drowsiness detection. The first method is based on linear regression, the second on fuzzy detection. For the first method, the drowsiness level is correctly detected in 72% of the epochs. The second method uses fuzzy detection and detects the drowsiness correctly in 65% of the epochs. The best results are obtained when using one single eye blink feature.

THU0605-HPR Patterns of Physical Activity Matter: Bout Analysis Reveals Differences Between Patients with Axial Spondyloarthritis and Healthy Controls

Background Low total physical activity (PA) levels and remarkably less (very)vigorous physical activities have been shown in patients with axial spondyloarthritis (aSpA) compared to healthy controls using objective sensor-based technology1. Ten minute bouts of moderate to (very)vigorous PA (instead of frequent interruptions) are associated with additional health benefits. These within-day patterns of PA are unknown in aSpA. Objectives To compare PA patterns (bouts) between patients with aSpA and healthy controls. Methods PA was compared between 40 patients with aSpA (male/female: 24/16; Mean ± SD, Age:44.38±11.30 yrs, BMI:26.27±5.11 kg/m2, disease duration: 11.40±9.50 yrs) and 40 healthy, age and sex matched controls (Age:44.33±10.63 yrs, BMI:25.05±3.59 kg/m2) during five consecutive days (three weekdays and two weekend days) using the SenseWear Pro3 Armband. Weekly PA accumulated in 10-minute bouts (A) and the number of bouts (N) for each PA intensity level were contrasted between groups with Wilcoxon signed- rank tests (p<.05). Differences with prior non-bout (NB) data were provided for comparison with median group differences in %. Results Weekly vigorous and very vigorous PA were significantly lower in aSpA irrespective of analysis technique (vigorous: NB: p<0.001,A&N: p=.003; very vigorous: NB p<001,A&N p=.008). Bouts analysis revealed novel and more profound (%) differences for moderate PA (NB: p=.070,-28%, A: p=.062,-49%, N:.046,-55%) and moderate to (very)vigorous PA (NB: p=.029,-32%, A: p=.003,-65%, N:p=.002,-67%) with lower values for patients. Thus in absolute terms, patients accumulate 21 minutes (trend) and two 10-minute bouts (significant) less moderate PA per day, a difference not detected with NB analysis. Similarly, patients performed 40 minutes and three 10-minute bouts less moderate to (very)vigorous PA. No differences between groups were found for inactivity and light PA (p>.05). Conclusions Bout analysis revealed additional differences in health-enhancing PA behavior between patients with aSpA and healthy controls. This work adds to the emerging body of evidence showing lower PA in this patient group. Future work in aSpA should focus on the consequences of low PA, its relevance for outcome assessment and on the development of tailored PA interventions. References Swinnen TW, Scheers T, Lefevre J, Dankaerts W, Westhovens R, de Vlam K. Physical activity assessment in patients with axial spondyloarthritis compared to healthy controls: a technology-based approach. PLoS One. 2014 Feb 28;9(2): e85309. Disclosure of Interest None declared