Detection of Alzheimer's Dementia by Using Signal Decomposition and Machine Learning Methods.

Dementia is one of the most common neurological disorders causing defection of cognitive functions, and seriously affects the quality of life. In this study, various methods have been proposed for the detection and follow-up of Alzheimer's dementia (AD) with advanced signal processing methods by using electroencephalography (EEG) signals. Signal decomposition-based approaches such as empirical mode decomposition (EMD), ensemble EMD (EEMD), and discrete wavelet transform (DWT) are presented to classify EEG segments of control subjects (CSs) and AD patients. Intrinsic mode functions (IMFs) are obtained from the signals using the EMD and EEMD methods, and the IMFs showing the most significant differences between the two groups are selected by applying previously suggested selection procedures. Five-time-domain and 5-spectral-domain features are calculated using selected IMFs, and five detail and approximation coefficients of DWT. Signal decomposition processes are conducted for both 1 min and 5 s EEG segment durations. For the 1 min segment duration, all the proposed approaches yield prominent classification performances. While the highest classification accuracies are obtained using EMD (91.8%) and EEMD (94.1%) approaches from the temporal/right brain cluster, the highest classification accuracy for the DWT (95.2%) approach is obtained from the temporal/left brain cluster for 1 min segment duration.

The efficacy of rituximab in patients with neuromyelitis optica spectrum disorder: A real-world study from Turkey.

BACKGROUND: Neuromyelitis optica spectrum disorders (NMOSD) are a group of antibody-mediated chronic inflammatory diseases of the central nervous system. Rituximab is a monoclonal antibody that leads to a reduction in disease activity. OBJECTIVE: To evaluate the efficacy of rituximab as monotherapy in NMOSD and to determine whether the efficacy varies depending on the presence of antibodies in this cohort. METHOD: This multicentre national retrospective study included patients with NMOSD treated with rituximab at least for 12 months from Turkey. The primary outcomes were the change in the annualised relapse rate, the Expanded Disability Status Scale (EDSS), the number of relapse and radiological activity-free patients. RESULTS: A total of 85 patients with NMOSD were included in the study. Of 85 patients, 58 (68.2%) were seropositive for anti-Aquaporin4-IgG (antI-AQP4-IgG). All patients were Anti-Myelin Oligodendrocyte Glycoprotein IgG (anti-MOG-IgG) negative. The median follow-up for rituximab treatment was 21 months (Q1 16-Q3 34.5). During rituximab treatment, the mean annualised relapse rate (ARR) significantly decreased from 1.45 ± 1.53 to 0.15 ± 0.34 (P < .001). In subgroup analyses, the mean ARR decreased from 1.61 ± 1.65 to 0.20 ± 0.39 in the seropositive group and 1.10 ± 1.19 to 0.05 ± 0.13 in the seronegative group. The mean EDSS improved from 3.98 ± 2.04 (prior to treatment onset) to 2.71 ± 1.59 (at follow-up) (P < .001). In the seropositive group, mean EDSS decreased from 3.94 ± 1.98 to 2.67 ± 1.54, and in the seronegative group, mean EDSS decreased from 4.07 ± 2.21 to 2.79 ± 1.73. There was no significant difference between anti-AQP4-IgG (+) and (-) groups in terms of ARR and EDSS. Sixty-four patients (75.2%) were relapse-free after the initiation of treatment. Seventy patients (82.3%) were radiological activity-free in the optic nerve, area postrema and brainstem. Additionally, 78 patients (91.7%) showed no spinal cord involvement after the treatment. CONCLUSION: Rituximab therapy is efficacious in the treatment of Turkish NMOSD patients independent of the presence of the anti-AQP4-IgG antibody.

Epileptic seizure classifications using empirical mode decomposition and its derivative.

BACKGROUND: Epilepsy is one of the most common neurological disorders associated with disruption of brain activity. In the classification and detection of epileptic seizures, electroencephalography (EEG) measurements, which record the electrical activities of the brain, are frequently used. Empirical mode decomposition (EMD) and its derivative, ensemble EMD (EEMD) are recently developed methods used to decompose non-stationary and nonlinear signals such as EEG into a finite number of oscillations called intrinsic mode functions (IMFs). Our main objective in this study is to present a hybrid IMF selection method combining four different approaches (energy, correlation, power spectral distance, and statistical significance measures), and investigate the effect of selected IMFs extracted by EMD and EEMD on the classification. We have applied the proposed IMF selection approach on the classification of EEG signals recorded from epilepsy patients who are under treatment at our collaborator hospital. Multichannel EEG signals collected from epilepsy patients are decomposed into IMFs, and then IMF selection was performed. Finally, time- and spectral-domain, and nonlinear features are extracted and feature sets are created for the classification. RESULTS: The maximum classification accuracies obtained using various combinations of IMFs were 94.56%, 95.63%, 96.8%, and 96.25% for SVM, KNN, naive Bayes, and logistic regression classifiers, respectively, by using EMD analysis; whereas, the EEMD approach has provided maximum classification accuracies of 96.06%, 97%, 97%, and 96.25% for SVM, KNN, naive Bayes, and logistic regression, respectively. Classification performance with the same features obtained using direct EEG signals instead of the decomposed IMFs was worse than the aforementioned 2 approaches for every combination. CONCLUSION: Simulation results demonstrate that the proposed IMF selection approach affects the classification results. Also, EEMD provides a robust method for feature extraction from EEG signals in order to classify pre-seizure and seizure segments.

Surgically Treated Status Epilepticus due to Large Cortical Tuber and Long-Term Follow-Up Results.

We present a case of invasive monitoring of a patient while he was being surgically treated in the status state. Our patient was a 27-year-old male who was hospitalized for frequent seizures, which began after a head trauma at the age of 3 years. Video electroencephalography was performed, and 25 clinical seizures were observed in 24 hours. Cranial magnetic resonance imaging (MRI) revealed a right frontal lesion which was hyperintense in T2-weighted and hypointense in T1-weighted images, and a subependymal nodule. For invasive monitoring, subdural electrodes were placed on the cortex surface via a right frontal craniotomy. The patient was re-operated, and the epileptic zone resection was performed. There was no sign of neurological deficit. Histopathological examination revealed cortical tuber, and the patient was scanned for tuberous sclerosis. There was no sign of tuberous sclerosis in other organs. The diagnosis of our patient was tuberous sclerosis, cortical tuber, subependymal nodule, epilepsy, and intermediate mental retardation. Radiological diagnosis should also be considered. Cortical tuber can be confused with focal cortical dysplasia. Finally, staged resection may be performed as a surgical treatment in some cases.