•We developed an algorithm for automatic detection of epileptiform EEG discharges, based on a novel deep learning method.•We validated it against the diagnostic gold standard from video-EEG ...recordings of the seizures.•The sensitivity of the algorithm was 89% and the specificity was 70%.
To validate an artificial intelligence-based computer algorithm for detection of epileptiform EEG discharges (EDs) and subsequent identification of patients with epilepsy.
We developed an algorithm for automatic detection of EDs, based on a novel deep learning method that requires a low amount of labeled EEG data for training. Detected EDs are automatically grouped into clusters, consisting of the same type of EDs, for rapid visual inspection. We validated the algorithm on an independent dataset of 100 patients with sharp transients in their EEG recordings (54 with epilepsy and 46 with non-epileptic paroxysmal events). The diagnostic gold standard was derived from the video-EEG recordings of the patients’ habitual events.
The algorithm had a sensitivity of 89% for identifying EEGs with EDs recorded from patients with epilepsy, a specificity of 70%, and an overall accuracy of 80%.
Automated detection of EDs using an artificial intelligence-based computer algorithm had a high sensitivity. Human (expert) supervision is still necessary for confirming the clusters of detected EDs and for describing clinical correlations. Further studies on different patient populations will be needed to confirm our results.
The automated algorithm we describe here is a useful tool, assisting neurophysiologist in rapid assessment of EEG recordings.
Ongoing or recurrent seizure activity without prominent motor features is a common burden in neurological critical care patients and people with epilepsy during ICU stays. Continuous EEG (CEEG) is ...the gold standard for detecting ongoing ictal EEG patterns and monitoring functional brain activity. However CEEG review is very demanding and time consuming. The purpose of the present multirater, EEG expert reviewer study, is to test and assess the clinical feasibility of an automatic EEG pattern detection method (Neurotrend).
Four board certified EEG reviewers used Neurotrend to annotate 76 CEEG datasets à 6 h (in total 456 h of EEG) for rhythmic and periodic EEG patterns (RPP), unequivocal ictal EEG patterns and burst suppression. All reviewers had a predefined time limit of 5 min (± 2 min) per CEEG dataset and were compared to a predefined gold standard (conventional EEG review with unlimited time). Subanalysis of specific features of RPP was conducted as well. We used Gwet's AC
and AC
coefficients to calculate interrater agreement (IRA) and multirater agreement (MRA). Also, we determined individual performance measures for unequivocal ictal EEG patterns and burst suppression. Bonferroni-Holmes correction for multiple testing was applied to all statistical tests.
Mean review time was 3.3 min (± 1.9 min) per CEEG dataset. We found substantial IRA for unequivocal ictal EEG patterns (0.61-0.79; mean sensitivity 86.8%; mean specificity 82.2%,
< 0.001) and burst suppression (0.68-0.71; mean sensitivity 96.7%; mean specificity 76.9%
< 0.001). Two reviewers showed substantial IRA for RPP (0.68-0.72), whereas the other two showed moderate agreement (0.45-0.54), compared to the gold standard (
< 0.001). MRA showed almost perfect agreement for burst suppression (0.86) and moderate agreement for RPP (0.54) and unequivocal ictal EEG patterns (0.57).
We demonstrated the clinical feasibility of an automatic critical care EEG pattern detection method on two levels: (1) reasonable high agreement compared to the gold standard, (2) reasonable short review times compared to previously reported EEG review times with conventional EEG analysis.
•Data-driven classification of patients with epilepsy based on their temporal activation patterns of interictal discharges.•AI-based detection and clustering resulted in five distinct activation ...patterns showing interrelations with sleep and seizures.•Clinical applicable assignment rules for taxonomy of patients with epilepsy open new pathways in diagnosis and research.
To quantify effects of sleep and seizures on the rate of interictal epileptiform discharges (IED) and to classify patients with epilepsy based on IED activation patterns.
We analyzed long-term EEGs from 76 patients with at least one recorded epileptic seizure during monitoring. IEDs were detected with an AI-based algorithm and validated by visual inspection. We then used unsupervised clustering to characterize patient sub-cohorts with similar IED activation patterns regarding circadian rhythms, deep sleep activation, and seizure occurrence.
Five sub-cohorts with similar IED activation patterns were found: “Sporadic” (14%, n = 10) without or few IEDs, “Continuous” (32%, n = 23) with weak circadian/deep sleep or seizure modulation, “Nighttime & seizure activation” (23%, n = 17) with high IED rates during normal sleep times and after seizures but without deep sleep modulation, “Deep sleep” (19%, n = 14) with strong IED modulation during deep sleep, and “Seizure deactivation” (12%, n = 9) with deactivation of IEDs after seizures. Patients showing “Deep sleep” IED pattern were diagnosed with temporal lobe epilepsy in 86%, while 80% of the “Sporadic” cluster were extratemporal.
Patients with epilepsy can be characterized by using temporal relationships between rates of IEDs, circadian rhythms, deep sleep and seizures.
This work presents the first approach to data-driven classification of epilepsy patients based on their fully validated temporal pattern of IEDs.
Ultra-long-term electroencephalographic (EEG) registration using minimally invasive low-channel devices is an emerging technology to assess sporadic seizure events. Highly sensitive automatic seizure ...detection algorithms are needed for semiautomatic evaluation of these prolonged recordings. We describe the design and validation of a deep neural network for two-channel seizure detection. The model is trained using EEG recordings from 590 patients in a publicly available seizure database. These recordings are based on the full 10-20 electrode system and include seizure annotations created by reviews of the full set of EEG channels. Validation was performed using 48 scalp EEG recordings from an independent epilepsy center and consensus seizure annotations from three neurologists. For each patient, a three-electrode subgroup (two channels with a common reference) of the full montage was selected for validation of the two-channel model. Mean sensitivity across patients of 88.8% and false positive rate across patients of 12.9/day were achieved. The proposed training approach is of great practical relevance, because true recordings from low-channel devices are currently available only in small numbers, and the generation of gold standard seizure annotations in two EEG channels is often difficult. The study demonstrates that automatic seizure detection based on two-channel EEG data is feasible and review of ultra-long-term recordings can be made efficient and effective.
Objective
To evaluate the diagnostic performance of artificial intelligence (AI)–based algorithms for identifying the presence of interictal epileptiform discharges (IEDs) in routine (20‐min) ...electroencephalography (EEG) recordings.
Methods
We evaluated two approaches: a fully automated one and a hybrid approach, where three human raters applied an operational IED definition to assess the automated detections grouped into clusters by the algorithms. We used three previously developed AI algorithms: Encevis, SpikeNet, and Persyst. The diagnostic gold standard (epilepsy or not) was derived from video‐EEG recordings of patients' habitual clinical episodes. We compared the algorithms with the gold standard at the recording level (epileptic or not). The independent validation data set (not used for training) consisted of 20‐min EEG recordings containing sharp transients (epileptiform or not) from 60 patients: 30 with epilepsy (with a total of 340 IEDs) and 30 with nonepileptic paroxysmal events. We compared sensitivity, specificity, overall accuracy, and the review time‐burden of the fully automated and hybrid approaches, with the conventional visual assessment of the whole recordings, based solely on unrestricted expert opinion.
Results
For all three AI algorithms, the specificity of the fully automated approach was too low for clinical implementation (16.67%; 63.33%; 3.33%), despite the high sensitivity (96.67%; 66.67%; 100.00%). Using the hybrid approach significantly increased the specificity (93.33%; 96.67%; 96.67%) with good sensitivity (93.33%; 56.67%; 76.67%). The overall accuracy of the hybrid methods (93.33%; 76.67%; 86.67%) was similar to the conventional visual assessment of the whole recordings (83.33%; 95% confidence interval CI: 71.48–91.70%; p > .5), yet the time‐burden of review was significantly lower (p < .001).
Significance
The hybrid approach, where human raters apply the operational IED criteria to automated detections of AI‐based algorithms, has high specificity, good sensitivity, and overall accuracy similar to conventional EEG reading, with a significantly lower time‐burden. The hybrid approach is accurate and suitable for clinical implementation.
•A common neurophysiology data format is needed to improving long-term storage and data exchange in clinical practice and research.•The DICOM standard is widely adopted and offers a unique ...environment to accomplish neurophysiology format standardization.•DICOM Working Group 32 (WG-32) has created an initial set of standards for routine EEG, PSG, EMG and EOG.
A standard format for neurophysiology data is urgently needed to improve clinical care and promote research data exchange. Previous neurophysiology format standardization projects have provided valuable insights into how to accomplish the project. In medical imaging, the Digital Imaging and Communication in Medicine (DICOM) standard is widely adopted. DICOM offers a unique environment to accomplish neurophysiology format standardization because neurophysiology data can be easily integrated with existing DICOM-supported elements such as video, ECG, and images and also because it provides easy integration into hospital Picture Archiving and Communication Systems (PACS) long-term storage systems. Through the support of the International Federation of Clinical Neurophysiology (IFCN) and partners in industry, DICOM Working Group 32 (WG-32) has created an initial set of standards for routine electroencephalography (EEG), polysomnography (PSG), electromyography (EMG), and electrooculography (EOG). Longer and more complex neurophysiology data types such as high-definition EEG, long-term monitoring EEG, intracranial EEG, magnetoencephalography, advanced EMG, and evoked potentials will be added later. In order to provide for efficient data compression, a DICOM neurophysiology codec design competition will be held by the IFCN and this is currently being planned. We look forward to a future when a common DICOM neurophysiology data format makes data sharing and storage much simpler and more efficient.
Quantitative analysis and automated seizure detection is able to increase efficiency of EEG review. However, acceptance of software assisted review is often low because results are inaccurate in real ...world patient cohorts and the reason for false detections cannot be deduced. The graphical software tool encevis visualizes detections of fast rhythmic activity and patterns defined by the ACNS critical care EEG terminology. Based on these detections as well as quantitative information of EEG, ECG, and EMG a multimodal seizure detection algorithm was developed. Simple rule based classification is utilized that facilitates easy interpretability. Aim of this work was to assess detection performance of different modalities and patient groups.
Our computer algorithm automatically detects seizures including rhythmic EEG patterns that show an increased amplitude compared to baseline. EMG signal is extracted by bandpass filtering EEG (30–60 Hz) to measure line length (LL) for detection of sustained and excessive ictal EMG activity of generalized tonic-clonic seizures (GTCS). High absolute values of LL and an increase of 500% to baseline trigger detections. Heart rate is calculated from ECG signals to detect ictal tachycardia (ITC) with more than 100 beats per minute and an increase of over 30% compared to baseline. To assess sensitivity and false detection rate a retrospective study was conducted including EEG/ECG recordings of 92 patients from two epilepsy monitoring units. Inclusion criteria were an age above 18 and at least one recorded epileptic seizure. EEGs were used without modification or manual editing of any kind. Automatic seizure detection was calculated for all 11,978 h of EEG (min = 23 h, max = 547 h). In total 410 manual seizure annotations were compared to automatic detections to define sensitivity (SE) and false detection in 24 h (FD/24 h).
Combination of all three seizure detection methods (EMG + ECG + EEG) resulted in SE = 88% with 10.5 FD/24 h on average. By using only EMG based detections 100% of GTCS (n = 49) were found with an average false detection rate of 3.39 FD/24 h. Seizure detection solely based on ECG yielded SE = 31% with 1.35 FD/24 h. Analysis of the temporal lobe epilepsy patients showed SE = 93.3% and 6.75 FD/24 h, the extra temporal lobe patient group resulted in SE = 80% at 15.3 FD/24 h.
We showed that automatic seizure detection based on multimodal signal quantification can reach high sensitivity. The low false detection rate results in an average of 20 false detections per week than can be validated quickly by using EEG and time synchronized quantitative screens in parallel. By visualizing quantitative information that is the source of automatic seizure detection the interpretability of results is improved. Our proposed approach to automatic EEG analysis will raise efficiency of post hoc analysis compared to the current state of the art.
Highlights • Rhythmic and periodic EEG patterns of ‘ictal–interictal uncertainty’ (RPPIIIU) occurred three times more frequently than electrographic seizures. • RPPIIIU were highly predictive for ...electrographic seizures. • RPPIIIU might represent interictal rather than ictal EEG patterns in patients with co-occurrence of electrographic seizures.