High precision in epileptic seizure self-reporting with an app diary.

People with epilepsy frequently under- or inaccurately report their seizures, which poses a challenge for evaluating their treatment. The introduction of epilepsy health apps provides a novel approach that could improve seizure documentation. This study assessed the documentation performance of an app-based seizure diary and a conventional paper seizure diary. At two tertiary epilepsy centers patients were asked to use one of two offered methods to report their seizures (paper or app diary) during their stay in the epilepsy monitoring unit. The performances of both methods were assessed based on the gold standard of video-EEG annotations. In total 89 adults (54 paper and 35 app users) with focal epilepsy were included in the analysis, of which 58 (33 paper and 25 app users) experienced at least one seizure and made at least one seizure diary entry. We observed a high precision of 85.7% for the app group, whereas the paper group's precision was lower due to overreporting (66.9%). Sensitivity was similar for both methods. Our findings imply that performance of seizure self-reporting is patient-dependent but is more precise for patients who are willing to use digital apps. This may be relevant for treatment decisions and future clinical trial design.

Data quality evaluation in wearable monitoring.

Wearable recordings of neurophysiological signals captured from the wrist offer enormous potential for seizure monitoring. Yet, data quality remains one of the most challenging factors that impact data reliability. We suggest a combined data quality assessment tool for the evaluation of multimodal wearable data. We analyzed data from patients with epilepsy from four epilepsy centers. Patients wore wristbands recording accelerometry, electrodermal activity, blood volume pulse, and skin temperature. We calculated data completeness and assessed the time the device was worn (on-body), and modality-specific signal quality scores. We included 37,166 h from 632 patients in the inpatient and 90,776 h from 39 patients in the outpatient setting. All modalities were affected by artifacts. Data loss was higher when using data streaming (up to 49% among inpatient cohorts, averaged across respective recordings) as compared to onboard device recording and storage (up to 9%). On-body scores, estimating the percentage of time a device was worn on the body, were consistently high across cohorts (more than 80%). Signal quality of some modalities, based on established indices, was higher at night than during the day. A uniformly reported data quality and multimodal signal quality index is feasible, makes study results more comparable, and contributes to the development of devices and evaluation routines necessary for seizure monitoring.

Intra- and Inter-Subject Perspectives on the Detection of Focal Onset Motor Seizures in Epilepsy Patients.

Focal onset epileptic seizures are highly heterogeneous in their clinical manifestations, and a robust seizure detection across patient cohorts has to date not been achieved. Here, we assess and discuss the potential of supervised machine learning models for the detection of focal onset motor seizures by means of a wrist-worn wearable device, both in a personalized context as well as across patients. Wearable data were recorded in-hospital from patients with epilepsy at two epilepsy centers. Accelerometry, electrodermal activity, and blood volume pulse data were processed and features for each of the biosignal modalities were calculated. Following a leave-one-out approach, a gradient tree boosting machine learning model was optimized and tested in an intra-subject and inter-subject evaluation. In total, 20 seizures from 9 patients were included and we report sensitivities of 67% to 100% and false alarm rates of down to 0.85 per 24 h in the individualized assessment. Conversely, for an inter-subject seizure detection methodology tested on an out-of-sample data set, an optimized model could only achieve a sensitivity of 75% at a false alarm rate of 13.4 per 24 h. We demonstrate that robustly detecting focal onset motor seizures with tonic or clonic movements from wearable data may be possible for individuals, depending on specific seizure manifestations.

Detecting Tonic-Clonic Seizures in Multimodal Biosignal Data From Wearables: Methodology Design and Validation.

BACKGROUND: Video electroencephalography recordings, routinely used in epilepsy monitoring units, are the gold standard for monitoring epileptic seizures. However, monitoring is also needed in the day-to-day lives of people with epilepsy, where video electroencephalography is not feasible. Wearables could fill this gap by providing patients with an accurate log of their seizures. OBJECTIVE: Although there are already systems available that provide promising results for the detection of tonic-clonic seizures (TCSs), research in this area is often limited to detection from 1 biosignal modality or only during the night when the patient is in bed. The aim of this study is to provide evidence that supervised machine learning can detect TCSs from multimodal data in a new data set during daytime and nighttime. METHODS: An extensive data set of biosignals from a multimodal watch worn by people with epilepsy was recorded during their stay in the epilepsy monitoring unit at 2 European clinical sites. From a larger data set of 243 enrolled participants, those who had data recorded during TCSs were selected, amounting to 10 participants with 21 TCSs. Accelerometry and electrodermal activity recorded by the wearable device were used for analysis, and seizure manifestation was annotated in detail by clinical experts. Ten accelerometry and 3 electrodermal activity features were calculated for sliding windows of variable size across the data. A gradient tree boosting algorithm was used for seizure detection, and the optimal parameter combination was determined in a leave-one-participant-out cross-validation on a training set of 10 seizures from 8 participants. The model was then evaluated on an out-of-sample test set of 11 seizures from the remaining 2 participants. To assess specificity, we additionally analyzed data from up to 29 participants without TCSs during the model evaluation. RESULTS: In the leave-one-participant-out cross-validation, the model optimized for sensitivity could detect all 10 seizures with a false alarm rate of 0.46 per day in 17.3 days of data. In a test set of 11 out-of-sample TCSs, amounting to 8.3 days of data, the model could detect 10 seizures and produced no false positives. Increasing the test set to include data from 28 more participants without additional TCSs resulted in a false alarm rate of 0.19 per day in 78 days of wearable data. CONCLUSIONS: We show that a gradient tree boosting machine can robustly detect TCSs from multimodal wearable data in an original data set and that even with very limited training data, supervised machine learning can achieve a high sensitivity and low false-positive rate. This methodology may offer a promising way to approach wearable-based nonconvulsive seizure detection.

Identification of Ictal Tachycardia in Focal Motor- and Non-Motor Seizures by Means of a Wearable PPG Sensor.

Photoplethysmography (PPG) as an additional biosignal for a seizure detector has been underutilized so far, which is possibly due to its susceptibility to motion artifacts. We investigated 62 focal seizures from 28 patients with electrocardiography-based evidence of ictal tachycardia (IT). Seizures were divided into subgroups: those without epileptic movements and those with epileptic movements not affecting and affecting the extremities. PPG-based heart rate (HR) derived from a wrist-worn device was calculated for sections with high signal quality, which were identified using spectral entropy. Overall, IT based on PPG was identified in 37 of 62 (60%) seizures (9/19, 7/8, and 21/35 in the three groups, respectively) and could be found prior to the onset of epileptic movements affecting the extremities in 14/21 seizures. In 30/37 seizures, PPG-based IT was in good temporal agreement (<10 s) with ECG-based IT, with an average delay of 5.0 s relative to EEG onset. In summary, we observed that the identification of IT by means of a wearable PPG sensor is possible not only for non-motor seizures but also in motor seizures, which is due to the early manifestation of IT in a relevant subset of focal seizures. However, both spontaneous and epileptic movements can impair PPG-based seizure detection.

Wearable devices for seizure detection: Practical experiences and recommendations from the Wearables for Epilepsy And Research (WEAR) International Study Group.

The Wearables for Epilepsy And Research (WEAR) International Study Group identified a set of methodology standards to guide research on wearable devices for seizure detection. We formed an international consortium of experts from clinical research, engineering, computer science, and data analytics at the beginning of 2020. The study protocols and practical experience acquired during the development of wearable research studies were discussed and analyzed during bi-weekly virtual meetings to highlight commonalities, strengths, and weaknesses, and to formulate recommendations. Seven major essential components of the experimental design were identified, and recommendations were formulated about: (1) description of study aims, (2) policies and agreements, (3) study population, (4) data collection and technical infrastructure, (5) devices, (6) reporting results, and (7) data sharing. Introducing a framework of methodology standards promotes optimal, accurate, and consistent data collection. It also guarantees that studies are generalizable and comparable, and that results can be replicated, validated, and shared.

Intracranial correlates of small sharp spikes.

OBJECTIVE: To identify cortical correlates of scalp small sharp spikes (SSS) using simultaneous scalp and intracranial EEG recordings. METHODS: Patients were retrospectively evaluated based on a database of intracranial long-term recordings at the Epilepsy Center Freiburg. Inclusion criteria were: simultaneous recordings with intracranial and scalp EEGs and the presence of at least five unequivocal SSS in the scalp EEG. Intracranial recordings were analyzed regarding the co-occurring intracranial potentials during scalp SSS. RESULTS: 33 patients, aged 9-60y, 17 females, fulfilled the above-mentioned criteria. Almost all patients had intracranial SSS correlates in the form of spike/polyspike-waves in the temporal lobe, predominantly in the hippocampus (24/28), less frequently involving the amygdala (5/29), temporal basal (3/18), lateral neocortical (4/32), entorhinal cortices (1/12), and the parietal lobe (2/13). Amplitudes of intrahippocampal spikes or polyspikes co-occurring with SSS were significantly higher than intracranial discharges without scalp correlates. In 45% of patients, intracranial spikes accompanying SSS were located within the seizure onset zone (SOZ). CONCLUSIONS: Our results strongly support an epileptic origin of SSS and provide evidence about their heterogenous generators. SIGNIFICANCE: This study suggests that SSS cannot with certainty be classified as "benign" but rather considered as one of the EEG manifestations of focal epilepsy.

Basal Ganglia Dysmorphism in Patients With Aicardi Syndrome.

OBJECTIVE: Aiming to detect associations between neuroradiologic and EEG evaluations and long-term clinical outcome in order to detect possible prognostic factors, a detailed clinical and neuroimaging characterization of 67 cases of Aicardi syndrome (AIC), collected through a multicenter collaboration, was performed. METHODS: Only patients who satisfied Sutton diagnostic criteria were included. Clinical outcome was assessed using gross motor function, manual ability, and eating and drinking ability classification systems. Brain imaging studies and statistical analysis were reviewed. RESULTS: Patients presented early-onset epilepsy, which evolved into drug-resistant seizures. AIC has a variable clinical course, leading to permanent disability in most cases; nevertheless, some cases presented residual motor abilities. Chorioretinal lacunae were present in 86.56% of our patients. Statistical analysis revealed correlations between MRI, EEG at onset, and clinical outcome. On brain imaging, 100% of the patients displayed corpus callosum malformations, 98% cortical dysplasia and nodular heterotopias, and 96.36% intracranial cysts (with similar rates of 2b and 2d). As well as demonstrating that posterior fossa abnormalities (found in 63.63% of cases) should also be considered a common feature in AIC, our study highlighted the presence (in 76.36%) of basal ganglia dysmorphisms (never previously reported). CONCLUSION: The AIC neuroradiologic phenotype consists of a complex brain malformation whose presence should be considered central to the diagnosis. Basal ganglia dysmorphisms are frequently associated. Our work underlines the importance of MRI and EEG, both for correct diagnosis and as a factor for predicting long-term outcome. CLASSIFICATION OF EVIDENCE: This study provides Class II evidence that for patients with AIC, specific MRI abnormalities and EEG at onset are associated with clinical outcomes.

Post-ictal accelerometer silence as a marker of post-ictal immobility.

OBJECTIVE: Movement-based wearable sensors are used for detection of convulsive seizures. The identification of the absence of motion following a seizure, known as post-ictal immobility (PI), may represent a potential additional application of wearables. PI has been associated with potentially life-threatening complications and with sudden unexpected death in epilepsy (SUDEP). We aimed to assess whether wearable accelerometers (ACCs) could be used as a digital marker of PI. METHOD: Devices with embedded ACCs were worn by patients admitted to an epilepsy monitoring unit. Participants presenting with convulsive seizures were included in the study. PI presence and duration were assessed by experts reviewing video recordings. An algorithm for the automatic detection of post-ictal ACC silence and its duration was developed and the linear pairwise relationship between the automatically detected duration of post-ictal ACC silence and the duration of the expert-labeled PI was analyzed. RESULTS: Twenty-two convulsive seizures were recorded from 18 study participants. Twenty were followed by PI and two by agitation. The automated estimation of post-ictal ACC silence identified all the 20 expert-labeled PI. The regression showed that the duration of the post-ictal ACC silence was correlated with the duration of PI (Pearson r = .92; P < .001), with the age of study participants (Pearson r = .78; P < .001), and with the duration of post-ictal generalized electroencephalography suppression (PGES; Pearson r = .4; P = .033). SIGNIFICANCE: We highlight a novel application of wearables as a way to record post-ictal manifestations associated with an increased risk of SUDEP. The occurrence of a fatal seizure is unpredictable and the continuous, non-invasive, long-term identification of risk factors associated with each individual seizure may assume a great clinical importance.

New insights in phenomenology and treatment of epilepsy in CDKL5 encephalopathy.

Eight patients, seven girls and one boy, had CDKL5 gene mutation, duplication, or deletion. Epileptic spasms started at a mean age of 3.5 months (range = 4 weeks-8 months). In five cases, tonic seizures preceded spasms at a median age of 6 weeks. In one patient who started at 8 months, spasms had a component of terror on awakening, reminding sleep terror. In two patients, electroencephalogram polygraphy of a so-called tonic seizure revealed that the tonic phase was followed by an overlooked clonic phase and then by a cluster of spasms during which each spasm was preceded by a brief clonic jerk revealed by electromyography. This sequence is rather particular and can be an early diagnostic clue. Progressive transition from this seizure type to epileptic spasms in clusters seems to result from increasing expression of the CDKL5 gene, as the child grows older. Five patients responded to the combination of vigabatrin and zonisamide.

Scalp electroencephalographic biomarkers in epilepsy patients with focal cortical dysplasia.

OBJECTIVE: To assess scalp electroencephalographic (EEG) patterns as possible biomarkers for an underlying focal cortical dysplasia (FCD) in patients with structural epilepsy. METHODS: Scalp electroencephalograms (EEGs) of epilepsy patients with histologically confirmed diagnosis of FCD type I or II (n = 71, age = 3-66 years, 28 female) and of controls with other underlying pathologies (n = 43, age = 2-60 years, 16 female) were retrospectively evaluated regarding the presence or absence of 12 scalp EEG patterns previously reported to be associated with FCD. Furthermore, 2 subgroups of these biomarkers with common characteristics were also analyzed. Each of the 12 biomarkers was tested for association with FCD by comparing the presence of each feature in FCD patients and controls using Fisher exact test. RESULTS: A significant association with FCD as underlying etiology was found for 6 of 12 previously reported biomarkers. With decreasing odds ratios, these were continuous epileptiform discharges, 2 types of rhythmic epileptiform discharges, polyspikes, frequent rhythmic bursting epileptiform activity, and repetitive discharges as well as the subgroups containing repetitive activity and polyspikes, respectively. Presence of EEG biomarkers was independent of a visible underlying magnetic resonance imaging-visible lesion, and had similar prevalence with FCD I and II. Individual biomarkers had specificities of 65 to 98% and sensitivities of 17 to 61% for an underlying FCD, and combinations of EEG biomarkers achieved 100% specificity. INTERPRETATION: This study confirms that there are several surface EEG biomarkers significantly associated with an underlying cortical dysplasia. These biomarkers may aid in localizing suspicious brain regions and provide evidence for dysplastic brain tissue also in nonlesional patients of either histological FCD subtype. Ann Neurol 2018;84:564-575.

A single channel sleep-spindle detector based on multivariate classification of EEG epochs: MUSSDET.

BACKGROUND: Studies on sleep-spindles are typically based on visual-marks performed by experts, however this process is time consuming and presents a low inter-expert agreement, causing the data to be limited in quantity and prone to bias. An automatic detector would tackle these issues by generating large amounts of objectively marked data. NEW METHOD: Our goal was to develop a sensitive, precise and robust sleep-spindle detection method. Emphasis has been placed on achieving a consistent performance across heterogeneous recordings and without the need for further parameter fine tuning. The developed detector runs on a single channel and is based on multivariate classification using a support vector machine. Scalp-electroencephalogram recordings were segmented into epochs which were then characterized by a selection of relevant and non-redundant features. The training and validation data came from the Medical Center-University of Freiburg, the test data consisted of 27 records coming from 2 public databases. RESULTS: Using a sample based assessment, 53% sensitivity, 37% precision and 96% specificity was achieved on the DREAMS database. On the MASS database, 77% sensitivity, 46% precision and 96% specificity was achieved. The developed detector performed favorably when compared to previous detectors. The classification of normalized EEG epochs in a multidimensional space, as well as the use of a validation set, allowed to objectively define a single detection threshold for all databases and participants. CONCLUSIONS: The use of the developed tool will allow increasing the data-size and statistical significance of research studies on the role of sleep-spindles.