Automated neonatal seizure detection: a multistage classification system through feature selection based on relevance and redundancy analysis.

OBJECTIVE: Automatic seizure detection obtains valuable information concerning duration and timing of seizures. Commonly used methods for EEG seizure detection in adults are inadequate for the same task in neonates because they lack the specific age-dependant characteristics of normal and pathological EEG. This paper presents an automatic seizure detection system for newborn with focus on feature selection via relevance and redundancy analysis. METHODS: Two linear correlation-based feature selection methods and the ReliefF method were applied to parameterized EEG data acquired from six neonates aged between 39 and 42 weeks. To evaluate the effectiveness of these methods, features extracted from seizure and non-seizure segments were ranked by these methods. The optimized ranked feature subsets were fed into a backpropagation neural network for classifying. Its performance was used as indicator for the feature selection effectiveness. RESULTS: Results showed an average seizure detection rate of 91%, an average non-seizure detection rate of 95%, an average false rejection rate of 95% and an overall average detection rate of 93% with a false seizure detection rate of 1.17/h. CONCLUSIONS: This good performance in detecting newborn ictal activities has been achieved based on an optimized subset of 30 features determined by the ReliefF-based detector, which corresponds to a reduction of the number of features of up to 75%. SIGNIFICANCE: The presented approach takes into account specific characteristics of normal and pathological EEG. Thus, it can improve the accuracy of conventional seizure detection systems in newborn.     

Combination of EEG and ECG for improved automatic neonatal seizure detection.

OBJECTIVE: Neonatal seizures are the most common central nervous system disorder in newborn infants. A system that could automatically detect the presence of seizures in neonates would be a significant advance facilitating timely medical intervention. METHODS: A novel method is proposed for the robust detection of neonatal seizures through the combination of simultaneously-recorded electroencephalogram (EEG) and electrocardiogram (ECG). A patient-specific and a patient-independent system are considered, employing statistical classifier models. RESULTS: Results for the signals combined are compared to results for each signal individually. For the patient-specific system, 617 of 633 (97.52%) expert-labelled seizures were correctly detected with a false detection rate of 13.18%. For the patient-independent system, 516 of 633 (81.44%) expert-labelled seizures were correctly detected with a false detection rate of 28.57%. CONCLUSIONS: A novel algorithm for neonatal seizure detection is proposed. The combination of an ECG-based classifier system with a novel multi-channel EEG-based classifier system has led to improved seizure detection performance. The algorithm was evaluated using a large data-set containing ECG and multi-channel EEG of realistic duration and quality. SIGNIFICANCE: Analysis of simultaneously-recorded EEG and ECG represents a new approach in seizure detection research and the detection performance of the proposed system is a significant improvement on previous reported results for automated neonatal seizure detection.     

Using simulated neuronal cell models for detection of epileptic seizures in foramen ovale and scalp EEG.

OBJECTIVE: To demonstrate a novel approach for real-time and automatic detection of epileptic seizures in EEG recorded with foramen ovale (Fov) or scalp electrodes. METHODS: Our seizure detection method is based on simulated leaky integrate and fire units (LIFU), which are classical simple neuronal cell models. The LIFUs are connected to a signal preprocessing stage and increase their spiking rates in response to rhythmic and synchronous EEG signals as typically occur at the onset and during seizures. RESULTS: We analyzed 22 short-term (10+/-3 min) and 4 long-term (18+/-7 h) Fov or scalp EEGs of 10 patients with drug resistant partial epilepsy. Seizures (n=36) were marked by increases of the LIFUs spiking rates above a preset threshold. The durations of increased spiking rates due to seizures were always longer than 10 s (36+/-21 s) and allowed separation from artifacts, which caused only short durations (1.2+/-0.6 s) of high spiking rates. The LIFUs correctly detected all the seizures and produced no false alarms. In the long term Fov EEGs seizure detection occurred before the onset of clinical signs (41+/-22 s). CONCLUSIONS: By using simulated neuronal cell models it is possible to automatically detect epileptic seizures in scalp and Fov EEG with high sensitivity and specificity.     

Improving the interpretation of ictal scalp EEG: BSS-CCA algorithm for muscle artifact removal

PURPOSE: To investigate the potential clinical relevance of a new algorithm to remove muscle artifacts in ictal scalp EEG. METHODS: Thirty-seven patients with refractory partial epilepsy with a well-defined seizure onset zone based on full presurgical evaluation, including SISCOM but excluding ictal EEG findings, were included. One ictal EEG of each patient was presented to a clinical neurophysiologist who was blinded to all other data. Ictal EEGs were first rated after band-pass filtering, then after elimination of muscle artifacts using a blind source separation-canonical correlation analysis technique (BSS-CCA). Degree of muscle artifact contamination, lateralization, localization, time and pattern of ictal EEG onset were compared between the two readings and validated against the other localizing information. RESULTS: Muscle artifacts contaminated 97% of ictal EEGs, and interfered with the interpretation in 76%, more often in extratemporal than temporal lobe seizures. BSS-CCA significantly improved the sensitivity to localize the seizure onset from 62% to 81%, and performed best in ictal EEGs with moderate to severe muscle artifact contamination. In a significant number of the contaminated EEGs, BSS-CCA also led to an earlier identification of ictal EEG changes, and recognition of ictal EEG patterns that were hidden by muscle artifact. CONCLUSIONS: Muscle artifacts interfered with the interpretation in a majority of ictal EEGs. BSS-CCA reliably removed these muscle artifacts in a user-friendly manner. BSS-CCA may have an important place in the interpretation of ictal EEGs during presurgical evaluation of patients with refractory partial epilepsy.     

Detection of neonatal seizures through computerized EEG analysis.

Neonatal seizures are a symptom of central nervous system disturbances. Neonatal seizures may be identified by direct clinical observation by the majority of electrographic seizures are clinically silent or subtle. Electrographic seizures in the newborn consist of periodic or rhythmic discharges that are distinctively different from normal background cerebral activity. Utilizing these differences, we have developed a technique to identify electrographic seizure activity. In this study, autocorrelation analysis was used to distinguish seizures from background electrocerebral activity. Autocorrelation data were scored to quantify the periodicity using a newly developed scoring system. This method, Scored Autocorrelation Moment (SAM) analysis, successfully distinguished epochs of EEGs with seizures from those without (N = 117 epochs, 58 with seizure and 59 without). SAM analysis showed a sensitivity of 84% and a specificity of 98%. SAM analysis of EEG may provide a method for monitoring electrographic seizures in high-risk newborns.     

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.     

Utility of the Scalp-Recorded Ictal EEG in Childhood Epilepsy

PURPOSE: To evaluate the usefulness of the scalp-recorded ictal EEGs in diagnosing childhood epilepsy. METHODS: We analyzed the ictal EEGs of 259 seizures in 183 patients who visited the department of child neurology, Okayama University Medical School, during the past 6 years. RESULTS: We divided all seizures into the following four categories, according to the diagnostic usefulness of ictal EEGs in determining the seizure type: 1. (a) Ictal EEGs confirmed the diagnosis of the seizure type based on seizure symptoms (101 seizures); (b) Ictal EEGs aided in the classification of the seizure type based on the seizure symptoms (101 seizures); (c) Ictal EEGs corrected errors in the classification (37 seizures); and (d) Ictal EEGs revealed previously unreported/undocumented seizure type (20 seizures). 2. Of the 37 misdiagnosed seizures (group C), 11 were nonepileptic seizures misdiagnosed as epileptic seizures, eight were complex partial seizures (CPS) misdiagnosed as the other seizure types, and 10 were other seizure types misdiagnosed as CPSs. 3. Of the 20 previously unreported/undocumented seizures (group D), nine were myoclonic seizures, five were absence seizures, five were CPS, and one was tonic spasms. 4. Seventy-two patients had CPS. Among them, 11 patients showed no epileptic spikes in their interictal EEG recordings. Therefore, ictal recordings confirmed the diagnosis of epilepsy. CONCLUSIONS: Ictal EEG recording is a very useful diagnostic tool not only for determining seizure types, but also for uncovering the existence of the unsuspected seizure types. It supplies the physician with useful information for the classification and the treatment of epilepsy. In particular, ictal EEGs are useful in diagnosing patients with CPS.     

Seizure detection using scalp‐EEG

Scalp electroencephalography (EEG)–based seizure‐detection algorithms applied in a clinical setting should detect a broad range of different seizures with high sensitivity and selectivity and should be easy to use with identical parameter settings for all patients. Available algorithms provide sensitivities between 75% and 90%. EEG seizure patterns with short duration, low amplitude, circumscribed focal activity, high frequency, and unusual morphology as well as EEG seizure patterns obscured by artifacts are generally difficult to detect. Therefore, detection algorithms generally perform worse on seizures of extratemporal origin as compared to those of temporal lobe origin. Specificity (false‐positive alarms) varies between 0.1 and 5 per hour. Low false‐positive alarm rates are of critical importance for acceptance of algorithms in a clinical setting. Reasons for false‐positive alarms include physiological and pathological interictal EEG activities as well as various artifacts. To achieve a stable, reproducible performance (especially concerning specificity), algorithms need to be tested and validated on a large amount of EEG data comprising a complete temporal assessment of all interictal EEG. Patient‐specific algorithms can further improve sensitivity and specificity but need parameter adjustments and training for individual patients. Seizure alarm systems need to provide on‐line calculation with short detection delays in the order of few seconds. Scalp‐EEG–based seizure detection systems can be helpful in an everyday clinical setting in the epilepsy monitoring unit, but at the current stage cannot replace continuous supervision of patients and complete visual review of the acquired data by specially trained personnel. In an outpatient setting, application of scalp‐EEG–based seizure‐detection systems is limited because patients won't tolerate wearing widespread EEG electrode arrays for long periods in everyday life. Recently developed subcutaneous EEG electrodes may offer a solution in this respect.     

The EEG in nonepileptic seizures.

Nonepileptic seizures are episodes that resemble seizures but are not epileptic. The importance of EEG in the diagnosis of NES is that misread (overread) EEGs are an important contributor to the misdiagnosis of epilepsy. About 20% to 30% of patients with refractory "seizures" seen at epilepsy centers have been misdiagnosed, and the vast majority have psychogenic nonepileptic seizures (PNES). Many such patients have had previous EEGs interpreted as epileptiform. These misdiagnoses based on EEG are easily perpetuated, complicate management, and adversely affect outcome. The reasons for the overinterpretation of EEGs include the common misconception that phase reversals indicate abnormalities and not applying strict criteria to make sharp transients epileptiform. The diagnosis of PNES typically begins with a clinical suspicion and then is confirmed with EEG-video monitoring. However, ictal EEG may be negative in some partial seizures and may be uninterpretable because of artifacts. Movements can generate rhythmic artifacts that mimic an electrographic seizure. Analysis of the ictal semiology (i.e., video) is at least as important as the ictal EEG. Provocative techniques, activation procedures, or "inductions" can also be useful for the diagnosis of PNES.     

An automatic warning system for epileptic seizures recorded on intracerebral EEGs.

OBJECTIVE: A new clinical seizure waning system for intracerebral EEG is proposed. It is aimed at a better performance than existing systems and at user tuneability. METHODS: The system employs data filtering in multiple bands, spectral feature extraction, Bayes' theorem, and spatio-temporal analysis. The a priori information in Bayes' theorem was provided by 407 h of EEG from 19 patients having 152 seizures. RESULTS: The testing data (19 patients, 389 h, 100 seizures, independent of the training data) yielded a sensitivity of 89.4%, a false detection rate of 0.22/h, and median delay time of 17.1 s when tuning was used, and 86%, 0.47/h and 16.2 s without tuning. Missed seizures were of short duration or had subtle seizure activity. False detections were caused by technical artefacts, non-epileptic large amplitude rhythmic bursts or very low amplitude activity. It was established that performance could easily be tuned. Results were also compared to the clinical system of . CONCLUSIONS: The system offers a performance that is acceptable for clinical use. User tuneability allows for reduction in false detection with minimal loss to sensitivity. SIGNIFICANCE: Epilepsy monitoring generates large amounts of recordings and requires intense observation. Automatic seizure detection and warning systems reduce review time and facilitate observation. We propose a method with high sensitivity and few false alarms.     

Neonatal seizure detection using multichannel display of envelope trend

We aimed to determine whether analysis of EEG envelope trend aids bedside detection of neonatal seizures. Five neonatal EEGs with multiple seizures were used to determine optimal trend parameters for seizure detection. Using these parameters, envelope trends were generated on eight additional EEGs, evaluated by experienced and inexperienced users, and compared to traditional EEG interpretation. Seizures were best detected using envelope trend of 2-6 Hz activity over 20-s epochs. Experienced and inexperienced users identified 88% and 55% of prolonged seizures, respectively, 40% and 6% of brief seizures, and 20% and 0% of slowly evolving seizures. All users identified less than two false positives per hour. Thus, an experienced envelope trend user accurately identified longer seizures but did not identify brief or slowly evolving seizures. Less experienced users were less accurate. Trending may be a useful tool for seizure detection in some neonates.     

Serum Prolactin in Neonates with Seizures

Summary: We studied serum prolactin (PRL) in 28 newborn infants with acute encephalopathy. Six patients had electrographically confirmed seizures. Twenty-two patients comprised the nonictal group. In the seizure group, PRL was determined at the first onset of the seizure (baseline) and at 15 and 30 min postictal. In the nonseizure group, PRL was determined at the end of the EEG and 15 min later. EEGs were visually analyzed for the presence of seizures and background abnormality (normal or mildly, moderately, or markedly abnormal). Etiologic diagnoses included congenital heart disease (12), hypoxic-ischemic encephalopathy (4), sepsis (4), respiratory distress syndrome (5) meconium aspiration (1), and metabolic disease (2). Serum PRL was significantly higher (p < 0.05) at baseline and 15 min postictally in the patients with seizures than in the nonictal group. However, PRL levels 15 and 30 min postictally were not statistically different from baseline values. Baseline PRL correlated significantly (p < 0.001) with EEG background abnormality in both groups; therefore, patients with the most abnormal EEG backgrounds had higher levels of PRL than those with a relatively normal EEG background. We conclude that newborns with EEG-confirmed seizures, particularly if seizures are not associated with clinical signs, have high baseline serum PRL levels that do not increase significantly in the immediate postictal period. Serum PRL levels correlate with the severity of the brain insult as evaluated by EEG background. Further studies are needed to enhance our understanding of the dynamics of PRL secretion in newborns with seizures and acute encephalopathy.     

Detecting temporal lobe seizures from scalp EEG recordings: a comparison of various features.

OBJECTIVE: Sixteen different features are evaluated in their potential ability to detect seizures from scalp EEG recordings containing temporal lobe (TL) seizures. Features include spectral measures, non-linear methods (e.g. zero-crossings), phase synchronization and the recently introduced Brain Symmetry Index (BSI). Besides an individual comparison, several combinations of features are evaluated as well in their potential ability to detect TL seizures. METHODS: Sixteen long-term scalp EEG recordings, containing TL seizures from patients suffering from temporal lobe epilepsy (TLE), were analyzed. For each EEG, all 16 features were determined for successive 10s epochs of the recording. All epochs were labeled by experts for the presence or absence of seizure activity. In addition, triplet combinations of various features were evaluated using pattern recognition tools. Final performance was evaluated by the sensitivity and specificity (False Alarm Rate (FAR)), using ROC curves. RESULTS: In those TL seizures characterized by unilateral epileptiform discharges, the BSI was the best single feature. Except for one low-voltage EEG with many artifacts, the sensitivity found ranged from 0.55 to 0.90 at a FAR of approximately 1/h. Using three features increased the sensitivity to 0.77-0.97. In patients with bilateral electroencephalographic changes, the single best feature most often found was a measure for the number of minima and maxima (mmax) in the recording, yielding sensitivities of approximately 0.30-0.96 at FAR approximately 1/h. Using three features increased the sensitivity to 0.38-0.99, at the same FAR. In various recordings, it was even possible to obtain sensitivities of 0.70-0.95 at a FAR = 0. CONCLUSIONS: The Brain Symmetry Index is the most relevant individual feature to detect electroencephalographic seizure activity in TLE with unilateral epileptiform discharges. In patients with bilateral discharges, mmax performs best. Using a triplet of features significantly improves the performance of the detector. SIGNIFICANCE: Improved seizure detection can improve patient care in both the epilepsy monitoring unit and the intensive care unit.     

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.     

Adequacy of routine EEG examinations in neonates with clinically suspected seizures.

This study identified the clinical and electroencephalographic (EEG) characteristics that distinguished neonates with EEG-confirmed seizures from those without, in order to assess the adequacy of routine short-term EEG examinations in neonates with clinically suspected seizures. Two different subgroups of tracings were analyzed: EEGs performed on therapeutically paralyzed (TP+) neonates and EEGs performed on non-therapeutically paralyzed (TP-) neonates. The rate of electrographic seizures, abnormal EEG background activity, and excessive sharp EEG transients (SETs) was significantly more common in the tracings performed on TP- neonates. In lethargic/comatose TP- neonates with clinically suspected seizures and abnormal EEG background activity, the rate of EEGs with excessive SETs (implying a "lowered seizure threshold") occurred equally in tracings with or without documented electrographic seizures. Consequently, we suspect that routine EEGs may be inadequate to electrographically confirm suspected seizures in some TP- neonates due to a large sampling error. In contrast, routine 40-minute EEGs are probably adequate to seek evidence of electrographic seizure activity in TP+ neonates because their seizure rate is low and most do not display background abnormalities or excessive SETs.     

An evaluation of automated neonatal seizure detection methods.

OBJECTIVE: To evaluate 3 published automated algorithms for detecting seizures in neonatal EEG. METHODS: One-minute, artifact-free EEG segments consisting of either EEG seizure activity or non-seizure EEG activity were extracted from EEG recordings of 13 neonates. Three published neonatal seizure detection algorithms were tested on each EEG recording. In an attempt to obtain improved detection rates, threshold values in each algorithm were manipulated and the actual algorithms were altered. RESULTS: We tested 43 data files containing seizure activity and 34 data files free from seizure activity. The best results for Gotman, Liu and Celka, respectively, were as follows: sensitivities of 62.5, 42.9 and 66.1% along with specificities of 64.0, 90.2 and 56.0%. CONCLUSIONS: The levels of performance achieved by the seizure detection algorithms are not high enough for use in a clinical environment. The algorithm performance figures for our data set are considerably worse than those quoted in the original algorithm source papers. The overlap of frequency characteristics of seizure and non-seizure EEG, artifacts and natural variances in the neonatal EEG cause a great problem to the seizure detection algorithms. SIGNIFICANCE: This study shows the difficulties involved in detecting seizures in neonates and the lack of a reliable detection scheme for clinical use. It is clear from this study that while each algorithm does produce some meaningful information, the information would only be usable in a reliable neonatal seizure detection process when accompanied by more complex analysis, and more advanced classifiers.     

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.     

EEG Abnormalities in Children with a First Unprovoked Seizure

Summary: We examined EEG findings from an ongoing study of 347 children with a first unprovoked seizure. EEGs were available in 321 (93%), and 135 (42%) had an abnormal EEG. EEG abnormalities included focal spikes (n = 77), generalized spike and wave discharges (n = 28), slowing (n = 43), and nonspecific abnormalities (n = 7). Abnormal EEGs were more common in children with remote symptomatic seizures (60%) than in those with idiopathic seizures (38%) (p < 0.003), more common in partial seizures (56%) than in generalized seizures (35%) (p < 0.001), and more common in children age >3 years (52%) than in younger children (12%) (p < 0.001). Records including both awake and sleep tracings were available in 148 (46%) cases. For 122 (38%) only awake tracings and for 51 (16%) only sleep tracings were available. Fifty-nine (40%) of the 148 patients with both an awake and asleep tracing had abnormal EEGs. Of 50 such EEGs with epileptiform abnormalities, 15 (30%) demonstrated the abnormality either only while awake (n = 8) or only while asleep (n = 7). Of 17 patients with EEG slowing, 8 showed slowing only in the awake tracing and 9 showed slowing in both the awake and asleep tracing. Children with even a single unprovoked seizure have a high incidence of EEG abnormalities. Obtaining a combined awake and sleep EEG significantly increases the yield of EEG abnormalities. In children with an idiopathic first seizure, EEG abnormalities are associated with an increased risk of seizure recurrence.