Detecting seizure onset in the ambulatory setting: demonstrating feasibility

Motion Artifacts Correction from Single-Channel EEG and fNIRS Signals Using Novel Wavelet Packet Decomposition in Combination with Canonical Correlation Analysis

The electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) signals, highly non-stationary in nature, greatly suffers from motion artifacts while recorded using wearable sensors. Since successful detection of various neurological and neuromuscular disorders is greatly dependent upon clean EEG and fNIRS signals, it is a matter of utmost importance to remove/reduce motion artifacts from EEG and fNIRS signals using reliable and robust methods. In this regard, this paper proposes two robust methods: (i) Wavelet packet decomposition (WPD) and (ii) WPD in combination with canonical correlation analysis (WPD-CCA), for motion artifact correction from single-channel EEG and fNIRS signals. The efficacy of these proposed techniques is tested using a benchmark dataset and the performance of the proposed methods is measured using two well-established performance matrices: (i) difference in the signal to noise ratio ( ) and (ii) percentage reduction in motion artifacts ( ). The proposed WPD-based single-stage motion artifacts correction technique produces the highest average (29.44 dB) when db2 wavelet packet is incorporated whereas the greatest average (53.48%) is obtained using db1 wavelet packet for all the available 23 EEG recordings. Our proposed two-stage motion artifacts correction technique, i.e., the WPD-CCA method utilizing db1 wavelet packet has shown the best denoising performance producing an average and values of 30.76 dB and 59.51%, respectively, for all the EEG recordings. On the other hand, for the available 16 fNIRS recordings, the two-stage motion artifacts removal technique, i.e., WPD-CCA has produced the best average (16.55 dB, utilizing db1 wavelet packet) and largest average (41.40%, using fk8 wavelet packet). The highest average and using single-stage artifacts removal techniques (WPD) are found as 16.11 dB and 26.40%, respectively, for all the fNIRS signals using fk4 wavelet packet. In both EEG and fNIRS modalities, the percentage reduction in motion artifacts increases by 11.28% and 56.82%, respectively when two-stage WPD-CCA techniques are employed in comparison with the single-stage WPD method. In addition, the average also increases when WPD-CCA techniques are used instead of single-stage WPD for both EEG and fNIRS signals. The increment in both and values is a clear indication that two-stage WPD-CCA performs relatively better compared to single-stage WPD. The results reported using the proposed methods outperform most of the existing state-of-the-art techniques.

Ambulatory diffuse optical tomography and multimodality physiological monitoring system for muscle and exercise applications

Ambulatory diffuse optical tomography (aDOT) is based on near-infrared spectroscopy (NIRS) and enables three-dimensional imaging of regional hemodynamics and oxygen consumption during a person’s normal activities. Although NIRS has been previously used for muscle assessment, it has been notably limited in terms of the number of channels measured, the extent to which subjects can be ambulatory, and/or the ability to simultaneously acquire synchronized auxiliary data such as electromyography (EMG) or electrocardiography (ECG). We describe the development of a prototype aDOT system, called NINscan-M, capable of ambulatory tomographic imaging as well as simultaneous auxiliary multimodal physiological monitoring. Powered by four AA size batteries and weighing 577 g, the NINscan-M prototype can synchronously record 64-channel NIRS imaging data, eight channels of EMG, ECG, or other analog signals, plus force, acceleration, rotation, and temperature for 24+ h at up to 250 Hz. We describe the system’s design, characterization, and performance characteristics. We also describe examples of isometric, cycle ergometer, and free-running ambulatory exercise to demonstrate tomographic imaging at 25 Hz. NINscan-M represents a multiuse tool for muscle physiology studies as well as clinical muscle assessment.

An electroencephalographic recording platform for real-time seizure detection

There are currently no clinical devices that can be worn by epilepsy patients who suffer from intractable seizures to warn them of seizure onset. Here we summarize state-of-the-art therapies and devices, and present a second-generation hardware platform in which seizure detection algorithms may be programmed into the device. Bi-polar electrographic data is presented for a prototype device and future implementations are discussed.

Artifact removal in physiological signals--practices and possibilities

The combination of reducing birth rate and increasing life expectancy continues to drive the demographic shift toward an aging population. This, in turn, places an ever-increasing burden on healthcare due to the increasing prevalence of patients with chronic illnesses and the reducing income-generating population base needed to sustain them. The need to urgently address this healthcare "time bomb" has accelerated the growth in ubiquitous, pervasive, distributed healthcare technologies. The current move from hospital-centric healthcare toward in-home health assessment is aimed at alleviating the burden on healthcare professionals, the health care system and caregivers. This shift will also further increase the comfort for the patient. Advances in signal acquisition, data storage and communication provide for the collection of reliable and useful in-home physiological data. Artifacts, arising from environmental, experimental and physiological factors, degrade signal quality and render the affected part of the signal useless. The magnitude and frequency of these artifacts significantly increases when data collection is moved from the clinic into the home. Signal processing advances have brought about significant improvement in artifact removal over the past few years. This paper reviews the physiological signals most likely to be recorded in the home, documenting the artifacts which occur most frequently and which have the largest degrading effect. A detailed analysis of current artifact removal techniques will then be presented. An evaluation of the advantages and disadvantages of each of the proposed artifact detection and removal techniques, with particular application to the personal healthcare domain, is provided.

Intelligent artifact classification for ambulatory physiological signals

Connected health represents an increasingly important model for health-care delivery. The concept is heavily reliant on technology and in particular remote physiological monitoring. One of the principal challenges is the maintenance of high quality data streams which must be collected with minimally intrusive, inexpensive sensor systems operating in difficult conditions. Ambulatory monitoring represents one of the most challenging signal acquisition challenges of all in that data is collected as the patient engages in normal activities of everyday living. Data thus collected suffers from considerable corruption as a result of artifact, much of it induced by motion and this has a bearing on its utility for diagnostic purposes. We propose a model for ambulatory signal recording in which the data collected is accompanied by labeling indicating the quality of the collected signal. As motion is such an important source of artifact we demonstrate the concept in this case with a quality of signal measure derived from motion sensing technology viz. accelerometers. We further demonstrate how different types of artifact might be tagged to inform artifact reduction signal processing elements during subsequent signal analysis. This is demonstrated through the use of multiple accelerometers which allow the algorithm to distinguish between disturbance of the sensor relative to the underlying tissue and movement of this tissue. A brain monitoring experiment utilizing EEG and fNIRS is used to illustrate the concept.

Patient-specific early seizure detection from scalp electroencephalogram

The objective of this study is to develop a method for automatic detection of seizures before or immediately after clinical onset using features derived from scalp electroencephalogram. This detection method is patient specific. It uses recurrent neural networks and a variety of input features. For each patient, we trained and optimized the detection algorithm for two cases: (1) during the period immediately preceding seizure onset and (2) during the period immediately after seizure onset. Continuous scalp electroencephalogram recordings (duration 15-62 hours, median 25 hours) from 25 patients, including a total of 86 seizures, were used in this study. Preonset detection was successful in 14 of the 25 patients. For these 14 patients, all of the testing seizures were detected before seizure onset with a median preonset time of 51 seconds and false-positive (FP) rate was 0.06/hour. Postonset detection had 100% sensitivity, 0.023/hour FP rate, and median delay of 4 seconds after onset. The unique results of this study relate to preonset detection. Our results suggest that reliable preonset seizure detection may be achievable for a significant subset of patients with epilepsy without use of invasive electrodes.

Non-invasive computerized system for automatically initiating vagus nerve stimulation following patient-specific detection of seizures or epileptiform discharges

OBJECTIVE

To demonstrate the feasibility of using a computerized system to detect the onset of a seizure and, in response, initiate Vagus nerve stimulation (VNS) in patients with medically refractory epilepsy.

METHODS

We designed and built a non-invasive, computerized system that automatically initiates VNS following the real-time detection of a pre-identified seizure or epileptiform discharge. The system detects these events through patient-specific analysis of the scalp electroencephalogram (EEG) and electrocardiogram (ECG) signals.

RESULTS

We evaluated the performance of the system on 5 patients (A-E). For patients A and B the computerized system initiated VNS in response to seizures; for patients C and D the system initiated VNS in response to epileptiform discharges; and for patient E neither seizures nor epileptiform discharges were observed during the evaluation period. During the 81 hour clinical test of the system on patient A, the computerized system detected 5/5 seizures and initiated VNS within 5 seconds of the appearance of ictal discharges in the EEG; VNS did not seem to alter the electrographic or behavioral characteristics of the seizures in this case. During the same testing session the computerized system initiated false stimulations at the rate of 1 false stimulus every 2.5 hours while the subject was at rest and not ambulating. During the 26 hour clinical test of the system on patient B, the computerized system detected 1/1 seizures and initiated VNS within 16 seconds of the appearance of ictal discharges; VNS did not alter the electrographic duration of the seizure but decreased anxiety and increased awareness during the post-seizure recovery phase. During the same testing session the computerized system did not declare any false detections.

SIGNIFICANCE

Initiating Vagus nerve stimulation soon after the onset of a seizure may abort or ameliorate seizure symptoms in some patients; unfortunately, a significant number of patients cannot initiate VNS by themselves following the start of a seizure. A system that automatically couples automated detection of seizure onset to initiation of VNS may be helpful for seizure treatment.

On data reduction in EEG monitoring: comparison between ambulatory and non-ambulatory recordings

OBJECTIVE

To compare the performance of an EEG data selection/reduction algorithm for epileptic EEGs on ambulatory and non-ambulatory recorded data to confirm that acceptable performance is achievable in ambulatory recordings despite the presence of overt artifacts.

METHODS

A total of 167 hours of EEG data containing 899 marked interictal events is analysed to determine the percentage of events correctly recorded (the sensitivity) and the amount of data reduction achieved.

RESULTS

A better sensitivity-data reduction trade-off is found in the ambulatory recorded data. This may be unexpected as ambulatory recordings are known to contain large numbers of artifacts, but is accounted for by these artifacts being easily detected and discarded, improving the data reduction.

CONCLUSIONS

Satisfactory performance levels are found in both data types, no degradation is present with ambulatory recordings.

SIGNIFICANCE

Demonstrates that the processing of EEG data for wearable EEG applications is feasible without a loss in performance compared to traditional inpatient EEG usage.