Development of Expert-Level Automated Detection of Epileptiform Discharges During Electroencephalogram Interpretation.

Importance: Interictal epileptiform discharges (IEDs) in electroencephalograms (EEGs) are a biomarker of epilepsy, seizure risk, and clinical decline. However, there is a scarcity of experts qualified to interpret EEG results. Prior attempts to automate IED detection have been limited by small samples and have not demonstrated expert-level performance. There is a need for a validated automated method to detect IEDs with expert-level reliability. Objective: To develop and validate a computer algorithm with the ability to identify IEDs as reliably as experts and classify an EEG recording as containing IEDs vs no IEDs. Design, Setting, and Participants: A total of 9571 scalp EEG records with and without IEDs were used to train a deep neural network (SpikeNet) to perform IED detection. Independent training and testing data sets were generated from 13 262 IED candidates, independently annotated by 8 fellowship-trained clinical neurophysiologists, and 8520 EEG records containing no IEDs based on clinical EEG reports. Using the estimated spike probability, a classifier designating the whole EEG recording as positive or negative was also built. Main Outcomes and Measures: SpikeNet accuracy, sensitivity, and specificity compared with fellowship-trained neurophysiology experts for identifying IEDs and classifying EEGs as positive or negative or negative for IEDs. Statistical performance was assessed via calibration error and area under the receiver operating characteristic curve (AUC). All performance statistics were estimated using 10-fold cross-validation. Results: SpikeNet surpassed both expert interpretation and an industry standard commercial IED detector, based on calibration error (SpikeNet, 0.041; 95% CI, 0.033-0.049; vs industry standard, 0.066; 95% CI, 0.060-0.078; vs experts, mean, 0.183; range, 0.081-0.364) and binary classification performance based on AUC (SpikeNet, 0.980; 95% CI, 0.977-0.984; vs industry standard, 0.882; 95% CI, 0.872-0.893). Whole EEG classification had a mean calibration error of 0.126 (range, 0.109-0.1444) vs experts (mean, 0.197; range, 0.099-0.372) and AUC of 0.847 (95% CI, 0.830-0.865). Conclusions and Relevance: In this study, SpikeNet automatically detected IEDs and classified whole EEGs as IED-positive or IED-negative. This may be the first time an algorithm has been shown to exceed expert performance for IED detection in a representative sample of EEGs and may thus be a valuable tool for expedited review of EEGs.

Interrater Reliability of Experts in Identifying Interictal Epileptiform Discharges in Electroencephalograms.

Importance: The validity of using electroencephalograms (EEGs) to diagnose epilepsy requires reliable detection of interictal epileptiform discharges (IEDs). Prior interrater reliability (IRR) studies are limited by small samples and selection bias. Objective: To assess the reliability of experts in detecting IEDs in routine EEGs. Design, Setting, and Participants: This prospective analysis conducted in 2 phases included as participants physicians with at least 1 year of subspecialty training in clinical neurophysiology. In phase 1, 9 experts independently identified candidate IEDs in 991 EEGs (1 expert per EEG) reported in the medical record to contain at least 1 IED, yielding 87 636 candidate IEDs. In phase 2, the candidate IEDs were clustered into groups with distinct morphological features, yielding 12 602 clusters, and a representative candidate IED was selected from each cluster. We added 660 waveforms (11 random samples each from 60 randomly selected EEGs reported as being free of IEDs) as negative controls. Eight experts independently scored all 13 262 candidates as IEDs or non-IEDs. The 1051 EEGs in the study were recorded at the Massachusetts General Hospital between 2012 and 2016. Main Outcomes and Measures: Primary outcome measures were percentage of agreement (PA) and beyond-chance agreement (Gwet κ) for individual IEDs (IED-wise IRR) and for whether an EEG contained any IEDs (EEG-wise IRR). Secondary outcomes were the correlations between numbers of IEDs marked by experts across cases, calibration of expert scoring to group consensus, and receiver operating characteristic analysis of how well multivariate logistic regression models may account for differences in the IED scoring behavior between experts. Results: Among the 1051 EEGs assessed in the study, 540 (51.4%) were those of females and 511 (48.6%) were those of males. In phase 1, 9 experts each marked potential IEDs in a median of 65 (interquartile range [IQR], 28-332) EEGs. The total number of IED candidates marked was 87 636. Expert IRR for the 13 262 individually annotated IED candidates was fair, with the mean PA being 72.4% (95% CI, 67.0%-77.8%) and mean κ being 48.7% (95% CI, 37.3%-60.1%). The EEG-wise IRR was substantial, with the mean PA being 80.9% (95% CI, 76.2%-85.7%) and mean κ being 69.4% (95% CI, 60.3%-78.5%). A statistical model based on waveform morphological features, when provided with individualized thresholds, explained the median binary scores of all experts with a high degree of accuracy of 80% (range, 73%-88%). Conclusions and Relevance: This study's findings suggest that experts can identify whether EEGs contain IEDs with substantial reliability. Lower reliability regarding individual IEDs may be largely explained by various experts applying different thresholds to a common underlying statistical model.

Preoperative MRI findings and prediction of diagnostic utility of foramen ovale electrodes.

OBJECTIVE: Foramen ovale electrodes (FOEs) are a minimally invasive method to localize mesial temporal seizures in cases in which noninvasive methods are inconclusive. The objective of this study was to identify factors predicting the ability of FOEs to yield a diagnosis in order to determine optimal candidates for this procedure. METHODS: All cases of diagnostic investigations performed with FOEs at the authors' institution between 2005 and 2017 were reviewed. FOE investigation was defined as diagnostic if it led to a treatment decision. Demographic and clinical variables for diagnostic and nondiagnostic investigations were compared using a Wilcoxon rank-sum test for continuous variables and Fisher's exact test for categorical variables. RESULTS: Ninety-three patients underwent investigations performed with FOEs during the study period and were included in the study. FOE investigation was diagnostic in 75.3% of cases. Of patients who underwent anterior temporal lobectomy following diagnostic FOE evaluation, 75.9% were Engel class I at last follow-up (average 40.1 months). When the diagnostic and nondiagnostic FOE groups were compared, patients who had diagnostic investigations were more likely to be male (57.1% male vs 26.1% in the nondiagnostic group, p = 0.015). They were also more likely to have temporal lesions on preoperative MRI (p = 0.018). CONCLUSIONS: FOEs are a useful, minimally invasive diagnostic modality resulting in a treatment decision in 75% of cases. Male patients and patients with temporal lesions on MRI may be most likely to benefit from FOE investigation.

Erratum to: Delta rhythmicity is a reliable EEG biomarker in Angelman syndrome: a parallel mouse and human analysis.

[This corrects the article DOI: 10.1186/s11689-017-9195-8.].

Delta rhythmicity is a reliable EEG biomarker in Angelman syndrome: a parallel mouse and human analysis.

BACKGROUND: Clinicians have qualitatively described rhythmic delta activity as a prominent EEG abnormality in individuals with Angelman syndrome, but this phenotype has yet to be rigorously quantified in the clinical population or validated in a preclinical model. Here, we sought to quantitatively measure delta rhythmicity and evaluate its fidelity as a biomarker. METHODS: We quantified delta oscillations in mouse and human using parallel spectral analysis methods and measured regional, state-specific, and developmental changes in delta rhythms in a patient population. RESULTS: Delta power was broadly increased and more dynamic in both the Angelman syndrome mouse model, relative to wild-type littermates, and in children with Angelman syndrome, relative to age-matched neurotypical controls. Enhanced delta oscillations in children with Angelman syndrome were present during wakefulness and sleep, were generalized across the neocortex, and were more pronounced at earlier ages. CONCLUSIONS: Delta rhythmicity phenotypes can serve as reliable biomarkers for Angelman syndrome in both preclinical and clinical settings.

Role of capsid sequence and immature nucleocapsid proteins p9 and p15 in Human Immunodeficiency Virus type 1 genomic RNA dimerization.

HIV-1 genomic RNA (gRNA) dimerization is important for viral infectivity and is regulated by proteolytic processing of the Gag precursor protein (Pr55gag) under the direction of the viral protease. The processing occurs in successive steps and, to date, the step associated with formation of a wild-type (WT) level of gRNA dimers has not been identified. The primary cleavage divides Pr55gag into two proteins. The C-terminal polypeptide is termed NCp15 (NCp7-p1-p6) because it contains the nucleocapsid protein (NC), a key determinant of gRNA dimerization and packaging. To examine the importance of precursor polypeptides NCp15 and NCp9 (NCp7-p1), we introduced mutations that prevented the proteolytic cleavages responsible for the appearance of NCp9 or NCp7. Using native Northern blot analysis, we show that gRNA dimerization was impaired when both the secondary (p1-p6) and tertiary (p7-p1) cleavage sites of NCp15 were abolished, but unaffected when only one or the other site was abolished. Though processing to NCp9 therefore suffices for a WT level of gRNA dimerization, we also show that preventing cleavage at the p7-p1 site abolished HIV-1 replication. To identify the minimum level of protease activity compatible with a WT level of gRNA dimers, we introduced mutations Thr26Ser and Ala28Ser in the viral protease to partially inactivate it, and we prepared composite HIV-1 resulting from the cotransfection of various ratios of WT and protease-inactive proviral DNAs. The results reveal that a 30% processing of Pr55gag into mature capsid proteins (CA/CA-p2) yielded a WT level of gRNA dimers, while a 10% Pr55gag processing hardly increased gRNA dimerization above the level seen in protease-inactive virions. We found that full gRNA dimerization required less than 50% WT NC in complementation asssays. Finally, we show that if we destroy alpha helix 1 of the capsid protein (CA), gRNA dimerization is impaired to the same extent as when the viral protease is inactivated. Cotransfection studies show that this CA mutation, in contrast to the NC-disabling mutations, has a dominant negative effect on HIV-1 RNA dimerization, viral core formation, and viral replication. This represents the first evidence that a capsid mutation can affect HIV-1 RNA dimerization.

Life quality assessment among patients with vitiligo: comparison of married and single patients in Iran.

BACKGROUND AND AIMS: Vitiligo is known to affect the quality of social and personal life in some countries. This study aims to assess the quality of life (QOL) in vitiligo sufferers among the Iranian population and to evaluate its relation with different variables. METHODS: One hundred vitiligo patients answered a questionnaire based on the Dermatology Life Quality Index (DLQI). RESULTS: The mean DLQI score was 8.16. There were statistically significant relationships between DLQI scores and marital status, skin phototype, and disease extension independently. CONCLUSIONS: This study shows that vitiligo has a major impact on the QOL of patients in Iran. Hence dermatologists should pay attention to the psychological effects of this cosmetic disease and try to decrease its extension and disfiguring effects by various treatments.