China 
Africa 
Explore chapters and articles related to this topic
Automated Processing of Big Data in Sleep Medicine
Published in Ervin Sejdić, Tiago H. Falk, Signal Processing and Machine Learning for Biomedical Big Data, 2018
Sara Mariani, Shaun M. Purcell, Susan Redline
Sleep is a naturally occurring, periodic decreased state of consciousness, characterized by distinct changes in brain wave frequency and amplitude, often accompanied by a decrease in heart rate and blood pressure. Sleep is a multiorgan phenomenon, which can be evaluated from a number of possible perspectives, as schematically shown in Figure 22.1. Sleep-related disorders have a major effect on quality of life and can impact daily performance and cognition, including memory, learning, concentration, and productivity. Healthy sleep is also critical for cardiometabolic health. Sleep medicine defines the diagnosis and treatment of sleep-related disorders, such as sleep-disordered breathing (SDB), narcolepsy, nocturnal frontal lobe epilepsy, periodic limb movements, rapid eye movement (REM) behavior disorder, and others, while also encompassing the research on the relationship of sleep-related traits with other pathologies, such as cardiovascular disease and psychiatric disorders.
The Diagnosis Of Epilepsy
Published in Anthony N. Nicholson, The Neurosciences and the Practice of Aviation Medicine, 2017
Simple partial seizures are the result of localized epileptic activity during which consciousness is fully preserved. The symptoms depend upon the localization of the seizure activity, but characteristically the symptoms are distinct and stereotypical. Typical simple partial seizures include focal motor (often occurring as a Jacksonian march evolving, as predicted, by spread along the motor cortex), autonomic symptoms (vomiting, pallor, flushing, sweating), somatosensory or special sensory symptoms (seeing flashing lights, experiencing unpleasant odours or tastes, vertigo, parasthesia, pain), and psychic/dysmnestic symptoms (strong feelings of déjà vu, depersonalization, fear, illusions, hallucinations). Probably the commonest aura in temporal lobe epilepsy is a rising epigastric feeling. Occasionally (especially with frontal lobe epilepsy), people have problems describing their aura, but will recognize the feeling as distinct and stereotypical.
Feature ranking chi-square method to improve the epileptic seizure prediction by employing machine learning algorithms
Published in Waves in Random and Complex Media, 2023
Lal Hussain, Eatedal Alabdulkreem, Kashif Javed Lone, Fahd N. Al-Wesabi, Mohamed K. Nour, Anwer Mustafa Hilal, Radwa Marzouk, Shafqat Aziz
The Bonn EEG dataset is a widely used publicly available dataset of EEG signals for research in the field of seizure detection and epilepsy diagnosis. The dataset was created by the University of Bonn in Germany and consists of five sets of EEG recordings, each containing 100 single-channel EEG recordings sampled at 173.61 Hz with a duration of 23.6 s. The recordings were obtained from five subjects with different types of epilepsy, including temporal lobe epilepsy, frontal lobe epilepsy, and primary generalized epilepsy. Each recording is labeled as either containing a seizure or being an interictal recording (i.e. a recording obtained during a period of normal brain activity between seizures). The dataset also includes annotations of the onset and end times of the seizures. The EEG signals were recorded using a TMSi Porti system with a Ag/AgCl electrode attached to the scalp at the location of the Cz electrode according to the international 10–20 system. The signals were preprocessed to remove any artifacts and baseline drifts and were then downsampled to 173.61 Hz. The Bonn EEG dataset has been widely used in research on seizure detection, epilepsy diagnosis, and machine-learning techniques for EEG signal analysis. The dataset is freely available for download and can be used for non-commercial research purposes with proper attribution to the original authors.
Analyzing the dynamics of sleep electroencephalographic (EEG) signals with different pathologies using threshold-dependent symbolic entropy
Published in Waves in Random and Complex Media, 2021
Lal Hussain, Saeed Arif Shah, Wajid Aziz, Syed Nadeem Haider Bukhari, Kashif Javed Lone, Quratul-Ain Chaudhary
The cyclic alternating pattern (CAP) [6] is a durable recurring activity which consists of two subdivided substitutes electroencephalogram (EEG) patterns. The greater amount of CAP is frequently observed in isonomia, as well as in sleep disorder breathing (SDB), periodic leg movement (PLM), parasomnias like REM behavior disorder and epileptic diseases like nocturnal frontal lobe epilepsy (NFLE). It can also be found in hypersomnias of central origins like narcolepsy [6].