Search

Background The objectives of this study were to analyze the clinical features and laboratory profiles and risk factors associated with critical illness of children with severe acute respiratory syndrome coronavirus 2 (SARS‐CoV‐2). Methods One hundred and sixty‐six coronavirus disease 2019 (COVID‐19) Iranian pediatric patients were recruited through a collaborative research network between March and May 2020. Demographics, clinical, laboratory, and radiological results were obtained from patient files. Results Of 166 patients, 102 (61%) and 64 (39%) were males and females, respectively. Ninety‐six (57.8%) and 70 (42.2%), had moderate and severe conditions, respectively. Thirty (18%) of patients died. The common symptoms were fever (73%), cough (54%), and shortness of breath, headache decrease in neutrophil and platelet counts; increase values in lactate dehydrogenase, decrease in the blood pH and HCO3 were significantly associated with the disease severity. 54% and 56% of patients showed abnormal radiographic appearance in Chest X‐ray and in chest computed tomography scan, respectively. Sixty‐one (36.7%) of patients were referred to intensive care unit (ICU). The coexistence of comorbidity was the main factor associated with ICU admission, shock, arrhythmia, acute kidney injury, acute respiratory distress syndrome, acute cardiac injury, and death. Conclusions We describe a higher than previously recognized rate of COVID‐19 mortality in Iranian pediatric patients. Epidemiological factors, such as the relatively high case fatality rate in the country and the presence of underlying diseases were the main factors for the high death rate.

To affirm the short-term safety of the BBIBP-CorV (Sinopharm) COVID-19 vaccine among people with multiple sclerosis (pwMS), 517 vaccinated and 174 unvaccinated pwMS were interviewed. 16.2% of the vaccinated pwMS reported at least one neurological symptom in their respective at-risk periods (ARP) – a period from the first until two weeks after the second vaccine dose. In a multivariable logistic regression model, presence of comorbidities (P = 0.01), being on natalizumab (P = 0.03), and experiencing post-vaccination myalgia (P < 0.01) predicted the development of post-vaccination neurological symptoms. One MS relapse, one COVID-19 contraction, and one ulcerative colitis flare after the first, and four MS relapses after the second dose, were the only reported serious adverse events during the ARPs. A multivariable Poisson regression model accounting for possible confounders failed to show any statistically-significant increase in relapse rates during the ARPs of vaccinated, compared to the prior year of unvaccinated pwMS (P = 0.78). Hence, the BBIBP-CorV vaccine does not seem to affect short-term MS activity. Furthermore, as 83.33% of the unvaccinated pwMS reported fear of possible adverse events to be the reason of their vaccination hesitancy, provision of misinformed pwMS with evidence-based consultations in this regard is encouraged.

We propose an efficient seizure prediction model based on a two-layer LSTM using the Swish activation function. The proposed structure performs feature extraction based on the time and frequency domains and uses the minimum distance algorithm as a post-processing step. The proposed model is evaluated on the Melbourne dataset and achieves the highest Area Under Curve (AUC) score of 0.92 and the lowest False Positive Rate (FPR) of 0.147 compared to previous work while having sensitivity and accuracy of 86.8 and 85.1, respectively. The proposed system has a low number of trainable parameters, and thus reducing the complexity of resource-constrained applications.

This paper provides a comprehensive analysis of the available EEG datasets that are used for epilepsy prediction systems, including Melbourne, CHB-MIT, American Epilepsy Society, Bonn, and European Epilepsy datasets. These datasets are compared in terms of the sampling rate, number of patients, recording time, number of channels, artifacts, and types of EEG signals. We also provide details on the challenges of using one dataset over the others in predicting epilepsy. Subsequently, we compare the performance of various machine learning models that use these datasets for epileptic seizure prediction. This is the first work that provides a comprehensive analysis of various EEG datasets and should be of great importance for researchers in EEG-based systems for epileptic seizure prediction.