Data Analytics in Healthcare Applications Usi...

Data Analytics in Healthcare Applications Using Physiological Signals

Author Name : M.R. Sumalatha, Nandakumar C, Aditya Narayanan B, Vishnu A, Yukan A S

ABSTRACT

Epilepsy is a serious chronic neurological disorder, can be detected by analyzing the brain signals produced by brain neurons. Neurons are connected to each other in a complex way to communicate with human organs and generate signals. The monitoring of these brain signals is commonly done using Electroencephalogram (EEG) and Electrocorticography (ECoG) media. These signals are complex, noisy, non-linear, non-stationary and produce a high volume of data. Hence, the detection of seizures and discovery of the brain-related knowledge is a challenging task. Machine learning classifiers are able to classify EEG data and detect seizures along with revealing relevant sensible patterns without compromising performance. As such, various researchers have developed a number of approaches to seizure detection using machine learning classifiers and statistical features. The main challenges are selecting appropriate classifiers and features. The aim of this paper is to present an overview of the wide varieties of these techniques over the last few years based on the taxonomy of statistical features and machine learning classifiers. The presented state-of-the-art methods and ideas will give a detailed understanding about seizure detection and classification, and research directions in the future.

In the brain, neurons exploit chemical reactions to generate electricity to control different bodily actions and this ongoing electrical activity can be recorded graphically which is popularly known as Electroencephalogram (EEG). EEG is a well accepted tool for epileptic seizure prediction/detection that can measure the voltage fluctuations of the brain. Feature extraction, analysis, and classification of EEG signals are still challenging issues for researchers due to the variations of the brain signals. Variations of EEG signals depend on different brain locations, number of channels, and different patterns of signals from different people. Another challenge for detection/prediction of EEG signals is to get reasonable accuracy for real time applications. Medical data is projected to double in volume every two years. This rapid increase in the generation of physiological data, alongside the development of big data intelligence, has enabled us to extract new insights from massive physiological signals. These include bioelectrical signals, biomagnetic signals, biochemical signals, and bioacoustics signals. Applications that utilize big data intelligence in healthcare have the potential to help reduce treatment costs, avoid preventable diseases, and improve quality of life.

Epilepsy is a disorder of the central nervous system (CNS)that affects more than 65 million people globally according to the World Health Organization. Additionally, about 1 in 26 people will develop epilepsy at some point during their lifetime. Seizures are much harder to detect visually; the patients will usually exhibit symptoms such as not responding or staring blankly for a brief period. Seizures can happen unexpectedly and can result in injuries such as falling, biting of the tongue, or losing control of one’s urine or stool. Hence, these are some of the reasons why seizure detection is of utmost importance for patients under medical supervision that are suspected to be seizure prone.

While EEG plays important roles in monitoring the brain activity of patients. Where there is clinical uncertainty, paraclinical evidence from the EEG can allow earlier diagnosis and treatment for epilepsy which is essential to initiate antiepileptic drug therapy and subsequently reduce the risk of future seizures and seizure-related complications. This project will use binary classification methods to predict whether an individual is having a seizure or not.

Keywords: EEG Signals, Machine learning, Deep learning, Epilepsy