Wavelet based automatic seizure detection in intracerebral electroencephalogram.

BACKGROUND: Automatic seizure detection is often used during long-term monitoring, and is particularly important during intracerebral investigations. Existing methods make many false detections, particularly in intracerebral electroencephalogram (EEG) because of frequent large amplitude rhythmic activity bursts that are non-epileptiform. OBJECTIVE: To develop a seizure detection method for intracerebral monitoring that is as sensitive as existing methods but has fewer false detections. METHODS: To capture the rhythmic nature of seizure discharges, we developed a wavelet-based method, examining how different frequency ranges fluctuate compared to the background. In particular, the system remembers rhythmic bursts occurring commonly in the background to avoid detecting them as seizures. RESULTS: The method was evaluated on test data from 11 patients, including 229 h and 66 seizures, and its performance compared to the method of Gotman (Electroencephalogr clin Neurophysiol 76 (1990) 317). Detection sensitivity was unchanged at close to 90%, but false detections were reduced from 2.4 to 0.3/h. CONCLUSIONS: Perfect sensitivity is unlikely because the morphology of seizure discharges is so variable. Nevertheless, the 87% sensitivity obtained in the combined training and testing data is quite high. We reduced the average false alarm rate to one per 3 h of recording, or 6 per 24-h period. Given how rapidly one can decide visually that a detection is erroneous, false detections should not cause any burden to the reviewer. SIGNIFICANCE: In intracerebral EEG it is possible to detect seizures automatically with high sensitivity and high specificity.     

A system to detect the onset of epileptic seizures in scalp EEG.

OBJECTIVE: A new method for automatic seizure detection and onset warning is proposed. The system is based on determining the seizure probability of a section of EEG. Operation features a user-tuneable threshold to exploit the trade-off between sensitivity and detection delay and an acceptable false detection rate. METHODS: The system was designed using 652 h of scalp EEG, including 126 seizures in 28 patients. Wavelet decomposition, feature extraction and data segmentation were employed to compute the a priori probabilities required for the Bayesian formulation used in training, testing and operation. RESULTS: Results based on the analysis of separate testing data (360 h of scalp EEG, including 69 seizures in 16 patients) initially show a sensitivity of 77.9%, a false detection rate of 0.86/h and a median detection delay of 9.8 s. Results after use of the tuning mechanism show a sensitivity of 76.0%, a false detection rate of 0.34/h and a median detection delay of 10 s. Missed seizures are characterized mainly by subtle or focal activity, mixed frequencies, short duration or some combination of these traits. False detections are mainly caused by short bursts of rhythmic activity, rapid eye blinking and EMG artifact caused by chewing. Evaluation of the traditional seizure detection method of using both data sets shows a sensitivity of 50.1%, a false detection rate of 0.5/h and a median detection delay of 14.3 s. CONCLUSIONS: The system performed well enough to be considered for use within a clinical setting. In patients having an unacceptable level of false detection, the tuning mechanism provided an important reduction in false detections with minimal loss of detection sensitivity and detection delay. SIGNIFICANCE: During prolonged EEG monitoring of epileptic patients, the continuous recording may be marked where seizures are likely to have taken place. Several methods of automatic seizure detection exist, but few can operate as an on-line seizure alert system. We propose a seizure detection system that can alert medical staff to the onset of a seizure and hence improve clinical diagnosis.     

Improvement in seizure detection performance by automatic adaptation to the EEG of each patient

An important problem in the use of automatic seizure detection during long-term epilepsy monitoring is that false detections can be very frequent, often because a paroxysmal but non-epileptiform pattern occurs repeatedly in a particular patient. We therefore introduce a method to reduce such patient-specific false seizure detections. The program “learns” about the false detections occurring in the first day of a prolonged monitoring session and attempts to eliminate similar patterns occurring during the remainder of the session. This method was evaluated in 20 patients having particularly high false detection rates. Seventy EEG sessions from 10 patients with scalp electrodes and 64 sessions from 10 patients with depth electrodes, covering a total of 2600 h were used in the evaluation. False detections were reduced by 61% (50% in scalp recordings and 71% in depth recordings), with only a 5% probability of losing true seizures. The average false detection rate in these patients fell from 3.25/h to 1.26/h. This significant reduction in false detections could also lead to lower detection thresholds and consequently to the detection of more true seizures.     

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

PurposeQuality 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.MethodsWe 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.ResultsExperience 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.ConclusionsThe results, including a goal of 90% correct detections and one false alarm per seizure, should be considered in development of seizure detectors.     

An approach to seizure detection using an artificial neural network (ANN)

We have developed an EEG seizure detector based on an artificial neural network. The input layer of the ANN has 31 nodes quantifying the amplitude, slope, curvature, rhythmicity, and frequency components of EEG in a 2 sec epoch. The hidden layer has 30 nodes and the output layer has 8 nodes representing various patterns of EEG activity (e.g. seizure, muscle, noise, normal). The value of the output node representing seizure activity is averaged over 3 consecutive epochs and a seizure is declared when that average exceeds 0.65.Among 78 randomly selected files from 50 patients not in the original training set, the detector declared at least one seizure in 76% of 34 files containing seizures. It declared no seizures in 93% of 44 files not containing seizures. Four false detections during 4.1 h of recording yielded a false detection rate of 1.0/h. The detector can continuously process 40 channels of EEG with a 33 MHz 486 CPU.Although this method is still in its early stages of development, our results represent proof of the principle that ANN could be utilized to provide a practical approach for automatic, on-line, seizure detection.     

Long-term EEG-video-audio monitoring: computer detection of focal EEG seizure patterns.

Twelve individuals with medically refractory partial seizures had undergone EEG-video-audio (EVA) monitoring over 1-15 (mean 10.5) days. We selectively reexamined available 15-channel EEGs (video-cassettes) totaling 461 h and containing 253 EEG focal seizures. Computer analysis (CA) of these bipolar records was performed using a mimetic method of seizure detection at 6 successive computer settings. We determined the computer parameters at which this method correctly detected a reasonably large percentage of seizures (81.42%) while generating an acceptable rate of false positive results (5.38/h). These parameters were adopted as the default setting for identifying focal EEG seizure patterns in all subsequent long-term bipolar scalp and sphenoidal recordings. Factors hindering or facilitating automatic seizure identification are discussed. It is concluded that on-line computer detection of focal EEG seizure patterns by this method offers a satisfactory alternative to and represents a distinct improvement over the extremely time consuming and fatiguing off-line fast visual review (FVR). Combining CA with seizure signaling (SS) by the patients and other observers increased the correct detections to 85.38% CA is best used in conjunction with SS.     

Multimodal seizure detection: A review

A review is given on the combined use of multiple modalities in non electroencephalography (EEG)‐based detection of motor seizures in children and adults. A literature search of papers was done on multimodal seizure detection with extraction of data on type of modalities, study design and algorithm, sensitivity, false detection rate, and seizure types. Evidence of superiority was sought for using multiple instead of single modalities. Seven papers were found from 2010 to 2017, mostly using contact sensors such as accelerometers (n = 5), electromyography (n = 2), heart rate (n = 2), electrodermal activity (n = 1), and oximetry (n = 1). Remote sensors included video, radar, movement, and sound. All studies but one were in‐hospital, with video‐EEG as a gold standard. Algorithms were based on physiology and supervised machine learning, but did not always include a separate test dataset. Sensitivity ranged from 4% to 100% and false detection rate from 0.25 to 20 per 8 hours. Tonic–clonic seizure detection performed best. False detections tended to be restricted to a minority (16%‐30%) of patients. Use of multiple sensors increased sensitivity; false detections decreased in one study, but increased in another. These preliminary studies suggest that detection of tonic–clonic seizures might be feasible, but larger field studies are required under more rigorous design that precludes bias. Generic algorithms probably suffice for the majority of patients.     

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.     

A fuzzy rule-based system for epileptic seizure detection in intracranial EEG

ObjectiveWe present a method for automatic detection of seizures in intracranial EEG recordings from patients suffering from medically intractable focal epilepsy.MethodsWe designed a fuzzy rule-based seizure detection system based on knowledge obtained from experts’ reasoning. Temporal, spectral, and complexity features were extracted from IEEG segments, and spatio-temporally integrated using the fuzzy rule-based system for seizure detection. A total of 302.7 h of intracranial EEG recordings from 21 patients having 78 seizures was used for evaluation of the system.ResultsThe system yielded a sensitivity of 98.7%, a false detection rate of 0.27/h, and an average detection latency of 11 s. There was only one missed seizure. Most of false detections were caused by high-amplitude rhythmic activities. The results from the system correlate well with those from expert visual analysis.ConclusionThe fuzzy rule-based seizure detection system enabled us to deal with imprecise boundaries between interictal and ictal IEEG patterns.SignificanceThis system may serve as a good seizure detection tool with high sensitivity and low false detection rate for monitoring long-term IEEG.     

Detecting epileptic seizures in long-term human EEG: a new approach to automatic online and real-time detection and classification of polymorphic seizure patterns.

Epileptic seizures can cause a variety of temporary changes in perception and behavior. In the human EEG they are reflected by multiple ictal patterns, where epileptic seizures typically become apparent as characteristic, usually rhythmic signals, often coinciding with or even preceding the earliest observable changes in behavior. Their detection at the earliest observable onset of ictal patterns in the EEG can, thus, be used to start more-detailed diagnostic procedures during seizures and to differentiate epileptic seizures from other conditions with seizure-like symptoms. Recently, warning and intervention systems triggered by the detection of ictal EEG patterns have attracted increasing interest. Since the workload involved in the detection of seizures by human experts is quite formidable, several attempts have been made to develop automatic seizure detection systems. So far, however, none of these found widespread application. Here, we present a novel procedure for generic, online, and real-time automatic detection of multimorphologic ictal-patterns in the human long-term EEG and its validation in continuous, routine clinical EEG recordings from 57 patients with a duration of approximately 43 hours and additional 1,360 hours of seizure-free EEG data for the estimation of the false alarm rates. We analyzed 91 seizures (37 focal, 54 secondarily generalized) representing the six most common ictal morphologies (alpha, beta, theta, and delta- rhythmic activity, amplitude depression, and polyspikes). We found that taking the seizure morphology into account plays a crucial role in increasing the detection performance of the system. Moreover, besides enabling a reliable (mean false alarm rate<0.5/h, for specific ictal morphologies<0.25/h), early and accurate detection (average correct detection rate>96%) within the first few seconds of ictal patterns in the EEG, this procedure facilitates the automatic categorization of the prevalent seizure morphologies without the necessity to adapt the proposed system to specific patients.     

An automated seizure monitoring system for patients with indwelling recording electrodes

An automated monitoring system has been developed to record from indwelling electrode arrays in patients undergoing evaluation for surgical treatment of intractable seizures. The functional aspects of this system's design are discussed and the range of electrical seizure patterns, other epileptiform events and artifacts that the system must handle are described. The system includes a flowing graphics image of as many as 32 channels of real-time ECoG, automatic seizure detection, recording of the ECoG for up to 6 min prior to seizure onset, and EEG machine start and stop control. In 40 monitored patients, the automated system achieved a seizure detection and recording accuracy of 95% for 792 clinical and subclinical seizures during 1578 h of monitoring with an artifact rate of 28% for all events recorded. However, system performance was judged upon the 86% accuracy for detection and recording of patient-specific seizures patterns (multiple seizures with the same pattern counted as 1) with 1.26 brief spike bursts and 0.67 artifacts/h.     

In-hospital and home-based long-term monitoring of focal epilepsy with a wearable electroencephalographic device: Diagnostic yield and user experience

Objective

The aim is to report the performance of an electroencephalogram (EEG) seizure-detector algorithm on data obtained with a wearable device (WD) in patients with focal refractory epilepsy and their experience.

Methods

Patients used a WD, the Sensor Dot (SD), to measure two channels of EEG using dry electrode patches during presurgical evaluation and at home for up to 8 months. An automated seizure detection algorithm flagged EEG regions with possible seizures, which we reviewed to evaluate the algorithm's diagnostic yield. In addition, we collected data on usability, side effects, and patient satisfaction with an electronic seizure diary application (Helpilepsy).

Results

Sixteen inpatients used the SD for up to 5 days and had 21 seizures. Sixteen outpatients used the device for up to 8 months and reported 101 focal impaired awareness seizures during the periods selected for analysis. Focal seizure detection sensitivity based on behind-the-ear EEG was 52% in inpatients and 23% in outpatients. False detections/h, positive predictive value (PPV), and F1 scores were 7.13%, .11%, and .002% for inpatients and 7.77%, .04%, and .001% for outpatients. Artifacts and low signal quality contributed to poor performance metrics. The seizure detector identified 19 nonreported seizures during sleep, when the signal quality was better. Regarding patients' experience, the likelihood of using the device at 6 months was 62%, and side effects were the main reason for dropping out. Finally, daily and monthly questionnaire completion rates were 33% and 65%, respectively.

Significance

Focal seizure detection sensitivity based on behind-the-ear EEG was 52% in inpatients and 23% in outpatients, with high false alarm rates and low PPV and F1 scores. This unobtrusive wearable seizure detection device was well received but had side effects. The current workflow and low performance limit its implementation in clinical practice. We suggest different steps to improve these performance metrics and patient experience.     

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.     

Automated video‐based detection of nocturnal convulsive seizures in a residential care setting

People with epilepsy need assistance and are at risk of sudden death when having convulsive seizures (CS). Automated real‐time seizure detection systems can help alert caregivers, but wearable sensors are not always tolerated. We determined algorithm settings and investigated detection performance of a video algorithm to detect CS in a residential care setting. The algorithm calculates power in the 2‐6 Hz range relative to 0.5‐12.5 Hz range in group velocity signals derived from video‐sequence optical flow. A detection threshold was found using a training set consisting of video‐electroencephalogaphy (EEG) recordings of 72 CS. A test set consisting of 24 full nights of 12 new subjects in residential care and additional recordings of 50 CS selected randomly was used to estimate performance. All data were analyzed retrospectively. The start and end of CS (generalized clonic and tonic–clonic seizures) and other seizures considered desirable to detect (long generalized tonic, hyperkinetic, and other major seizures) were annotated. The detection threshold was set to the value that obtained 97% sensitivity in the training set. Sensitivity, latency, and false detection rate (FDR) per night were calculated in the test set. A seizure was detected when the algorithm output exceeded the threshold continuously for 2 seconds. With the detection threshold determined in the training set, all CS were detected in the test set (100% sensitivity). Latency was ≤10 seconds in 78% of detections. Three/five hyperkinetic and 6/9 other major seizures were detected. Median FDR was 0.78 per night and no false detections occurred in 9/24 nights. Our algorithm could improve safety unobtrusively by automated real‐time detection of CS in video registrations, with an acceptable latency and FDR. The algorithm can also detect some other motor seizures requiring assistance.     

Automatic multimodal detection for long-term seizure documentation in epilepsy

Objective

This study investigated sensitivity and false detection rate of a multimodal automatic seizure detection algorithm and the applicability to reduced electrode montages for long-term seizure documentation in epilepsy patients.

Measurement and quantification of generalized tonic-clonic seizures in epilepsy patients by means of accelerometry--an explorative study

Epilepsy is one of the most common neurological diseases, which has a cumulative lifetime incidence of 3%. Two to threefold increased morbidity and mortality rates are reported, especially if generalized tonic-clonic seizures (GTCS) occur. A wireless small and user-friendly detection system would be helpful in early identification of seizures. This could minimize the risk of seizure-related injuries and further allow complete seizure frequency documentation, especially in a non-clinical private setting. The aim of our study was to develop a design and to conduct an exploratory validation of an accelerometry (ACM)-based detection system for GTCS detection in real-time. Patients were recruited via the Epilepsy Monitoring Unit at the Department of Neurology, Medical University Innsbruck. In three out of 20 patients, four GTCS could be recorded. The ACM sensors recorded increased activities at the stated seizure time, which clearly differed from everyday movements. The temporary sensitivity (100%), specificity (≥88%) and the positive predictive value (≥75%) of the detection suggests a promising alarm/false alarm ratio. The validity of the detection device has to be evaluated with more data in order to be able to significantly confirm the positive results and to further develop a cut-off algorithm for automatic seizure detection.     

Convulsive seizure detection using a wrist-worn electrodermal activity and accelerometry biosensor

The special requirements for a seizure detector suitable for everyday use in terms of cost, comfort, and social acceptance call for alternatives to electroencephalography (EEG)–based methods. Therefore, we developed an algorithm for automatic detection of generalized tonic–clonic (GTC) seizures based on sympathetically mediated electrodermal activity (EDA) and accelerometry measured using a novel wrist‐worn biosensor. The problem of GTC seizure detection was posed as a supervised learning task in which the goal was to classify 10‐s epochs as a seizure or nonseizure event based on 19 extracted features from EDA and accelerometry recordings using a Support Vector Machine. Performance was evaluated using a double cross‐validation method. The new seizure detection algorithm was tested on >4,213 h of recordings from 80 patients and detected 15 (94%) of 16 of the GTC seizures from seven patients with 130 false alarms (0.74 per 24 h). This algorithm can potentially provide a convulsive seizure alarm system for caregivers and objective quantification of seizure frequency.     

An algorithm for seizure onset detection using intracranial EEG

This article addresses the problem of real-time seizure detection from intracranial EEG (IEEG). One difficulty in creating an approach that can be used for many patients is the heterogeneity of seizure IEEG patterns across different patients and even within a patient. In addition, simultaneously maximizing sensitivity and minimizing latency and false detection rates has been challenging as these are competing objectives. Automated machine learning systems provide a mechanism for dealing with these hurdles. Here we present and evaluate an algorithm for real-time seizure onset detection from IEEG using a machine-learning approach that permits a patient-specific solution. We extract temporal and spectral features across all intracranial EEG channels. A pattern recognition component is trained using these feature vectors and tested against unseen continuous data from the same patient. When tested on more than 875 hours of IEEG data from 10 patients, the algorithm detected 97% of 67 test seizures of several types with a median detection delay of 5 seconds and a median false alarm rate of 0.6 false alarms per 24-hour period. The sensitivity was 100% for 8 of 10 patients. These results indicate that a sensitive, specific, and relatively short-latency detection system based on machine learning can be employed for seizure detection from EEG using a full set of intracranial electrodes to individual patients. This article is part of a Supplemental Special Issue entitled The Future of Automated Seizure Detection and Prediction.     

Seizure detection method based on fractal dimension and gradient boosting

Automatic seizure detection technology is necessary and crucial for the long-term electroencephalography (EEG) monitoring of patients with epilepsy. This article presents a patient-specific method for the detection of epileptic seizures. The fractal dimensions of preprocessed multichannel EEG were firstly estimated using a k-nearest neighbor algorithm. Then, the feature vector constructed for each epoch was fed into a trained gradient boosting classifier. After a series of postprocessing, including smoothing, threshold processing, collar operation, and union of seizure detections in a short time interval, a binary decision was made to determine whether the epoch belonged to seizure status or not. Both the epoch-based and event-based assessments were used for the performance evaluation of this method on the EEG data of 21 patients from the Freiburg dataset. An average epoch-based sensitivity of 91.01% and a specificity of 95.77% were achieved. For the event-based assessment, this method obtained an average sensitivity of 94.05%, with a false detection rate of 0.27/h.     

Band-sensitive seizure onset detection via CSP-enhanced EEG features

This paper presents two novel epileptic seizure onset detectors. The detectors rely on a common spatial pattern (CSP)-based feature enhancement stage that increases the variance between seizure and nonseizure scalp electroencephalography (EEG). The proposed feature enhancement stage enables better discrimination between seizure and nonseizure features. The first detector adopts a conventional classification stage using a support vector machine (SVM) that feeds the energy features extracted from different subbands to an SVM for seizure onset detection. The second detector uses logical operators to pool SVM seizure onset detections made independently across different EEG spectral bands. The proposed detectors exhibit an improved performance, with respect to sensitivity and detection latency, compared with the state-of-the-art detectors. Experimental results have demonstrated that the first detector achieves a sensitivity of 95.2%, detection latency of 6.43 s, and false alarm rate of 0.59 per hour. The second detector achieves a sensitivity of 100%, detection latency of 7.28 s, and false alarm rate of 1.2 per hour for the MAJORITY fusion method.