Automated Detection of Convulsive Seizures Using a Wearable Accelerometer Device

Epileptic seizure detection requires specialized approaches such as video/electroencephalography monitoring. However, these approaches are restricted mainly to hospital setting and requires video/EEG analysis by experts, which makes these approaches resource- and labor-intensive. In contrast, we aim to develop a wireless, remote monitoring system using a single wrist-worn accelerometer sensor, which is sensitive to multiple types of convulsive seizures and is capable of detecting seizures with short duration. Simple time domain features including a new set of Poincare plot based features were extracted from the active movement events recorded using a wrist-worn accelerometer sensor. The best features were then selected using the area under the ROC curve analysis. Kernelized support vector data description (SVDD) was then used to classify non-seizure and seizure events. The proposed algorithm was evaluated on 5,576h of recordings from 79 patients and detected 40 (86.95%) of 46 convulsive seizures (generalized tonic-clonic (GTCS), psychogenic non-epileptic (PNES), and complex partial seizures (CPS)) from twenty patients with a total of 270 false alarms (1.16/24h). Furthermore, the algorithm showed a comparable performance (sensitivity 95.23% and false alarm rate 0.64/24h) with respect to existing unimodal and multi-modal methods for GTCS detection. The promising results shows the potential to build an ambulatory monitoring convulsive seizure detection system. A wearable accelerometer based seizure detection system would aid in continuous assessment of convulsive seizures in a timely and non-invasive manner.

[1]  Tobias Loddenkemper,et al.  Seizure detection, seizure prediction, and closed-loop warning systems in epilepsy , 2014, Epilepsy & Behavior.

[2]  G. Baker,et al.  Failure to recognize psychogenic nonepileptic seizures may cause death , 2004, Neurology.

[3]  Roland D. Thijs,et al.  Non-EEG based ambulatory seizure detection designed for home use: What is available and how will it influence epilepsy care? , 2016, Epilepsy & Behavior.

[4]  Robert P. W. Duin,et al.  Support vector domain description , 1999, Pattern Recognit. Lett..

[5]  A. Schulze-Bonhage,et al.  Views of patients with epilepsy on seizure prediction devices , 2010, Epilepsy & Behavior.

[6]  Bernard Yan,et al.  Time‐frequency mapping of the rhythmic limb movements distinguishes convulsive epileptic from psychogenic nonepileptic seizures , 2013, Epilepsia.

[7]  Lojini Logesparan,et al.  Optimal features for online seizure detection , 2012, Medical & Biological Engineering & Computing.

[8]  Sándor Beniczky,et al.  Automatic multi-modal intelligent seizure acquisition (MISA) system for detection of motor seizures from electromyographic data and motion data , 2012, Comput. Methods Programs Biomed..

[9]  Pierre J. M. Cluitmans,et al.  Detection of Subtle Nocturnal Motor Activity From 3-D Accelerometry Recordings in Epilepsy Patients , 2007, IEEE Transactions on Biomedical Engineering.

[10]  Paolo Bonato,et al.  Development of a Body Sensor Network to Detect Motor Patterns of Epileptic Seizures , 2012, IEEE Transactions on Biomedical Engineering.

[11]  Ronald M. Aarts,et al.  Time-Frequency Analysis of Accelerometry Data for Detection of Myoclonic Seizures , 2010, IEEE Transactions on Information Technology in Biomedicine.

[12]  Sándor Beniczky,et al.  Detection of generalized tonic–clonic seizures by a wireless wrist accelerometer: A prospective, multicenter study , 2013, Epilepsia.

[13]  Vasile Palade,et al.  Class Imbalance Learning Methods for Support Vector Machines , 2013 .

[14]  Elske Ammenwerth,et al.  Measurement and quantification of generalized tonic–clonic seizures in epilepsy patients by means of accelerometry—An explorative study , 2011, Epilepsy Research.

[15]  Sabine Van Huffel,et al.  Automated Detection of Tonic–Clonic Seizures Using 3-D Accelerometry and Surface Electromyography in Pediatric Patients , 2016, IEEE Journal of Biomedical and Health Informatics.

[16]  Marimuthu Palaniswami,et al.  Automatic Detection and Classification of Convulsive Psychogenic Nonepileptic Seizures Using a Wearable Device , 2016, IEEE Journal of Biomedical and Health Informatics.

[17]  Robert P. W. Duin,et al.  Support Vector Data Description , 2004, Machine Learning.

[18]  T. Nijsen,et al.  The potential value of three-dimensional accelerometry for detection of motor seizures in severe epilepsy , 2005, Epilepsy & Behavior.

[19]  Josemir W. Sander,et al.  Sudden unexpected death in epilepsy: risk factors and potential pathomechanisms , 2009, Nature Reviews Neurology.

[20]  Robert S. Fisher,et al.  Detection of seizure-like movements using a wrist accelerometer , 2011, Epilepsy & Behavior.

[21]  Jane Hanna,et al.  Safe and sound? A systematic literature review of seizure detection methods for personal use , 2016, Seizure.

[22]  Rosalind W. Picard,et al.  Convulsive seizure detection using a wrist‐worn electrodermal activity and accelerometry biosensor , 2012, Epilepsia.

[23]  Philippe Kahane,et al.  Classification of Epileptic Motor Manifestations and Detection of Tonic–Clonic Seizures With Acceleration Norm Entropy , 2013, IEEE Transactions on Biomedical Engineering.

[24]  Sabine Van Huffel,et al.  Feature selection methods for accelerometry-based seizure detection in children , 2016, Medical & Biological Engineering & Computing.

[25]  R. C. Oldfield.  The assessment and analysis of handedness: the Edinburgh inventory. , 1971, Neuropsychologia.

[26]  Tamara M.E. Nijsen,et al.  A model of heart rate changes to detect seizures in severe epilepsy , 2006, Seizure.

[27]  Chih-Jen Lin,et al.  A Revisit to Support Vector Data Description , 2015 .

[28]  Sabine Van Huffel,et al.  Peri-ictal ECG changes in childhood epilepsy: Implications for detection systems , 2013, Epilepsy & Behavior.

[29]  Sabine Van Huffel,et al.  Accelerometry-Based Home Monitoring for Detection of Nocturnal Hypermotor Seizures Based on Novelty Detection , 2014, IEEE Journal of Biomedical and Health Informatics.

[30]  Dennis Velakoulis,et al.  Clinical Characteristics and Outcome in Patients With Psychogenic Nonepileptic Seizures , 2010, Psychosomatic medicine.

[31]  Rosalind W. Picard,et al.  Autonomic changes with seizures correlate with postictal EEG suppression , 2012, Neurology.

[32]  Svetlana Kipervasser,et al.  A Novel Portable Seizure Detection Alarm System: Preliminary Results , 2011, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[33]  J. Cavazos,et al.  Electromyography‐based seizure detector: Preliminary results comparing a generalized tonic–clonic seizure detection algorithm to video‐EEG recordings , 2015, Epilepsia.

[34]  Marimuthu Palaniswami,et al.  Poincaré Plot Methods for Heart Rate Variability Analysis , 2013, Springer US.

[35]  Poul Jennum,et al.  Quantitative analysis of surface electromyography during epileptic and nonepileptic convulsive seizures , 2014, Epilepsia.

[36]  Helge B. D. Sørensen,et al.  Evaluation of novel algorithm embedded in a wearable sEMG device for seizure detection , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[37]  E. Mascha,et al.  Complex partial seizures of frontal lobe onset statistical analysis of ictal semiology , 2003, Seizure.

[38]  Helge B. D. Sørensen,et al.  Automated Algorithm for Generalized Tonic–Clonic Epileptic Seizure Onset Detection Based on sEMG Zero-Crossing Rate , 2012, IEEE Transactions on Biomedical Engineering.

[39]  J. Hanley,et al.  A method of comparing the areas under receiver operating characteristic curves derived from the same cases. , 1983, Radiology.