Calibrating Deep Learning Classifiers for Patient-Independent Electroencephalogram Seizure Forecasting.

The recent scientific literature abounds in proposals of seizure forecasting methods that exploit machine learning to automatically analyze electroencephalogram (EEG) signals. Deep learning algorithms seem to achieve a particularly remarkable performance, suggesting that the implementation of clinical devices for seizure prediction might be within reach. However, most of the research evaluated the robustness of automatic forecasting methods through randomized cross-validation techniques, while clinical applications require much more stringent validation based on patient-independent testing. In this study, we show that automatic seizure forecasting can be performed, to some extent, even on independent patients who have never been seen during the training phase, thanks to the implementation of a simple calibration pipeline that can fine-tune deep learning models, even on a single epileptic event recorded from a new patient. We evaluate our calibration procedure using two datasets containing EEG signals recorded from a large cohort of epileptic subjects, demonstrating that the forecast accuracy of deep learning methods can increase on average by more than 20%, and that performance improves systematically in all independent patients. We further show that our calibration procedure works best for deep learning models, but can also be successfully applied to machine learning algorithms based on engineered signal features. Although our method still requires at least one epileptic event per patient to calibrate the forecasting model, we conclude that focusing on realistic validation methods allows to more reliably compare different machine learning approaches for seizure prediction, enabling the implementation of robust and effective forecasting systems that can be used in daily healthcare practice.

Electroencephalographic microstates as a potential neurophysiological marker differentiating bilateral from unilateral temporal lobe epilepsy.

OBJECTIVE: Electroencephalographic (EEG) microstate abnormalities have been documented in different neurological disorders. We aimed to assess whether EEG microstates are altered also in patients with temporal epilepsy (TLE) and whether they show different activations in patients with unilateral TLE (UTLE) and bilateral TLE (BTLE). METHODS: Nineteen patients with UTLE, 12 with BTLE, and 15 healthy controls were enrolled. Resting state high-density electroencephalography (128 channels) was recorded for 15 min with closed eyes. We obtained a set of stable scalp maps representing the EEG activity, named microstates, from which we acquired the following variables: global explained variance (GEV), mean duration (MD), time coverage (TC), and frequency of occurrence (FO). Two-way repeated measures analysis of variance was used to compare groups, and Spearman correlation was performed to study the maps in association with the clinical and neuropsychological data. RESULTS: Patients with BTLE and UTLE showed differences in most of the parameters (GEV, MD, TC, FO) of the four microstate maps (A-D) compared to controls. Patients with BTLE showed a significant increase in all parameters for the microstates in Map-A and a decrease in Map-D compared to UTLE and controls. We observed a correlation between Map-A, disease duration, and spatial short-term memory, whereas microstate Map-D was correlated with the global intelligence score and short-term memory performance. SIGNIFICANCE: A global alteration of the neural dynamics was observed in patients with TLE compared to controls. A different pattern of EEG microstate abnormalities was identified in BTLE compared to UTLE, which might represent a distinctive biomarker.

Altered spread of waves of activities at large scale is influenced by cortical thickness organization in temporal lobe epilepsy: a magnetic resonance imaging-high-density electroencephalography study.

Temporal lobe epilepsy is a brain network disorder characterized by alterations at both the structural and the functional levels. It remains unclear how structure and function are related and whether this has any clinical relevance. In the present work, we adopted a novel methodological approach investigating how network structural features influence the large-scale dynamics. The functional network was defined by the spatio-temporal spreading of aperiodic bursts of activations (neuronal avalanches), as observed utilizing high-density electroencephalography in patients with temporal lobe epilepsy. The structural network was modelled as the region-based thickness covariance. Loosely speaking, we quantified the similarity of the cortical thickness of any two brain regions, both across groups and at the individual level, the latter utilizing a novel approach to define the subject-wise structural covariance network. In order to compare the structural and functional networks (at the nodal level), we studied the correlation between the probability that a wave of activity would propagate from a source to a target region and the similarity of the source region thickness as compared with other target brain regions. Building on the recent evidence that large-waves of activities pathologically spread through the epileptogenic network in temporal lobe epilepsy, also during resting state, we hypothesize that the structural cortical organization might influence such altered spatio-temporal dynamics. We observed a stable cluster of structure-function correlation in the bilateral limbic areas across subjects, highlighting group-specific features for left, right and bilateral temporal epilepsy. The involvement of contralateral areas was observed in unilateral temporal lobe epilepsy. We showed that in temporal lobe epilepsy, alterations of structural and functional networks pair in the regions where seizures propagate and are linked to disease severity. In this study, we leveraged on a well-defined model of neurological disease and pushed forward personalization approaches potentially useful in clinical practice. Finally, the methods developed here could be exploited to investigate the relationship between structure-function networks at subject level in other neurological conditions.

Neuropsychological Functioning in Bilateral versus Unilateral Temporal Lobe Epilepsy.

Although relatively specific anatomo-electro-clinical features of temporal lobe epilepsy (TLE) with bilateral ictal involvement (bitemporal epilepsy-BTLE) have been described, differentiating between BTLE and unilateral TLE (UTLE) remains challenging. Surgery is often the treatment of choice for drug-resistant UTLE, whereas its use is more controversial in BTLE. It is currently unclear whether neuropsychological assessment can contribute to the differential diagnosis. We retrospectively reviewed the neuropsychological evaluation of 46 consecutive patients with refractory TLE. Eighteen patients were diagnosed with BTLE on the basis of ictal electro-clinical data, in particular a video EEG recording of at least one seizure simultaneously involving the two temporal lobes without the possibility of lateralizing its onset or at least two different seizures independently arising from the two temporal lobes. Twenty-eight patients were classified as UTLE. Presurgery evaluation data were used in this study. Compared with UTLE, BTLE was associated with a lower intelligence quotient (IQ) and more severe impairment in long-term memory, the latter remaining significant even after controlling for IQ. No significant differences were found between right and left UTLE. In conclusion, BTLE and UTLE are associated with relatively distinct neuropsychological profiles, further supporting their classification as different disorders within the TLE spectrum.

Investigation of dynamic functional connectivity of the source reconstructed epileptiform discharges in focal epilepsy: A graph theory approach.

OBJECTIVE: The aim of the present study is to investigate with noninvasive methods the modulation of dynamic functional connectivity during interictal epileptiform discharge (IED). METHOD: We reconstructed the cortical source of the EEG recorded IED of 17 patients with focal epilepsy. We then computed dynamic connectivity using the time resolved phase locking value (PLV). We derived graph theory indices (i.e. degree, strength, local efficiency, clustering coefficient and global efficiency). Finally, we selected the atlas node with the maximum activation as the IED cortical source investigating the graph indices dynamics in theta, alpha, beta and gamma frequency bands. RESULTS: We observed IED-locked modulations of the graph indexes depending on the frequency bands. We detected a modulation of the strength, clustering coefficient, local and global efficiency both in theta and in alpha bands, which also displayed modulations of the degree index. In the beta band only the global efficiency was modulated by the IED, while no effects were detected in the gamma band. Finally, we found a correlation between alpha and theta local efficiency, as well as alpha global efficiency, and the epilepsy duration. SIGNIFICANCE: Our findings suggest that the neural synchronization is not limited to the IED cortical source, but implies a phase synchronization across multiple brain areas. We hypothesize that the aberrant electrical activity originating from the IED locus is spread amongst the other network nodes throughout the low frequency bands (i.e. theta and alpha). Moreover, IED-dependent increase in the global efficiency indicates that the IED interfere with the whole network functioning. We finally discussed possible application of this methodology for future investigation.

Clinical implications of interictal epileptiform discharges in cognitive functioning in CEC syndrome with evolution into epileptic encephalopathy.

In epileptic encephalopathies (EE), interictal epileptiform discharges (IEDs) contribute to cognitive impairment. The EE process has been studied in a patient affected by epilepsy with occipital calcification and celiac disease (CEC syndrome) by combining the administration of brain area stimulus specific (visual and auditory) reaction times (RT) during continuous EEG monitoring with the off-line reconstruction of auditory and visual evoked potentials (EP). Visual RT and VEP were abnormal only if recorded concomitantly to the IEDs. Auditory RT and EP were normal. When the EE process is going on, IEDs transiently disrupt aspects of cortical functioning, contributing to the cognitive impairment.

Nocturnal frontal lobe epilepsy in mucopolysaccharidosis.

Nocturnal frontal lobe epilepsy (NFLE) is an epileptic syndrome that is primarily characterized by seizures with motor signs occurring almost exclusively during sleep. We describe 2 children with mucopolysaccharidosis (MPS) who were referred for significant sleep disturbance. Long term video-EEG monitoring (LT-VEEGM) demonstrated sleep-related hypermotor seizures consistent with NFLE. No case of sleep-related hypermotor seizures has ever been reported to date in MPS. However, differential diagnosis with parasomnias has been previously discussed. The high frequency of frontal lobe seizures causes sleep fragmentation, which may result in sleep disturbances observed in at least a small percentage of MPS patients. We suggest monitoring individuals with MPS using periodic LT-VEEGM, particularly when sleep disorder is present. Moreover, our cases confirm that NFLE in lysosomal storage diseases may occur, and this finding extends the etiologic spectrum of NFLE.