University of Malaya

About: University of Malaya is a education organization based out in Kuala Lumpur, Malaysia. It is known for research contribution in the topics: Population & Fiber laser. The organization has 25087 authors who have published 51491 publications receiving 1036791 citations. The organization is also known as: UM & Universiti Malaya.

Relapsed and late-onset Nipah encephalitis.

Abstract: An outbreak of infection with the Nipah virus, a novel paramyxovirus, occurred among pig farmers between September 1998 and June 1999 in Malaysia, involving 265 patients with 105 fatalities. This is a follow-up study 24 months after the outbreak. Twelve survivors (7.5%) of acute encephalitis had recurrent neurological disease (relapsed encephalitis). Of those who initially had acute nonencephalitic or asymptomatic infection, 10 patients (3.4%) had late-onset encephalitis. The mean interval between the first neurological episode and the time of initial infection was 8.4 months. Three patients had a second neurological episode. The onset of the relapsed or late-onset encephalitis was usually acute. Common clinical features were fever, headache, seizures, and focal neurological signs. Four of the 22 relapsed and late-onset encephalitis patients (18%) died. Magnetic resonance imaging typically showed patchy areas of confluent cortical lesions. Serial single-photon emission computed tomography showed the evolution of focal hyperperfusion to hypoperfusion in the corresponding areas. Necropsy of 2 patients showed changes of focal encephalitis with positive immunolocalization for Nipah virus antigens but no evidence of perivenous demyelination. We concluded that a unique relapsing and remitting encephalitis or late-onset encephalitis may result as a complication of persistent Nipah virus infection in the central nervous system.

SleepEEGNet: Automated sleep stage scoring with sequence to sequence deep learning approach.

Abstract: Electroencephalogram (EEG) is a common base signal used to monitor brain activities and diagnose sleep disorders. Manual sleep stage scoring is a time-consuming task for sleep experts and is limited by inter-rater reliability. In this paper, we propose an automatic sleep stage annotation method called SleepEEGNet using a single-channel EEG signal. The SleepEEGNet is composed of deep convolutional neural networks (CNNs) to extract time-invariant features, frequency information, and a sequence to sequence model to capture the complex and long short-term context dependencies between sleep epochs and scores. In addition, to reduce the effect of the class imbalance problem presented in the available sleep datasets, we applied novel loss functions to have an equal misclassified error for each sleep stage while training the network. We evaluated the performance of the proposed method on different single-EEG channels (i.e., Fpz-Cz and Pz-Oz EEG channels) from the Physionet Sleep-EDF datasets published in 2013 and 2018. The evaluation results demonstrate that the proposed method achieved the best annotation performance compared to current literature, with an overall accuracy of 84.26%, a macro F1-score of 79.66% and κ = 0.79. Our developed model can be applied to other sleep EEG signals and aid the sleep specialists to arrive at an accurate diagnosis. The source code is available at https://github.com/SajadMo/SleepEEGNet.