A new artificial intelligence algorithm has been found to detect epileptic seizures accurately. The AI algorithm has the potential to access and analyze the electroencephalograph (EEG) electrodes, detect a seizure and accurately pinpoint its origin, says a study published in Scientific Reports.
— TechCheckNews (@TechCheckNN) July 1, 2020
According to previous scientific evidence, the brain and neurological research has paid much attention to develop machine learning-based techniques for the accurate detection and prediction of epileptic seizures with electroencephalogram (EEG). In the current study, the researchers introduces a novel dynamic learning method that first infers a time-varying network that consists of the multivariate EEG signals and which represents the overall dynamics of the brain network, and subsequently quantifies its location using graph theory.
The researchers stated that epilepsy is one of the most common central nervous system disorders that affects nearly 4% of individuals with all age groups. According to the present understanding of the epileptic seizures, normal brain activity disruption by a strong and sudden hyper-synchronized firing of a cluster of neurons result in an epileptic seizure. It further states that at the time of seizure, if a person is hooked up to an EEG, a device that measures electrical, then output of the abnormal brain activity is presented as amplified spike-and-wave discharges. However, when temporal EEG signals are used, it can be difficult to accurately detect a seizure.
In the study, scientists have introduced a newly developed network inference technique that would facilitates seizure detection as well as pinpoints its location with improved accuracy.
“We treated EEG electrodes as nodes of a network. Using the recordings (time-series data) from each node, we developed a data-driven approach to infer time-varying connections in the network or relationships between nodes. We want to infer how a brain region is interacting with others,” said Walter Bomela, a postdoctoral fellow in the Preston M. Green Department of Electrical & Systems Engineering at the University of Texas at Arlington.
In general, the new ICON method developed by researchers provides an innovative angle, through constructing a complex dynamic brain network, to detect epileptic seizures. This bridges the occurrence of seizures with its cause and effects, which in turn enables future research studies on treating neuronal disorders like epileptic seizures. This method does not require prior information for data processing, and hence it can be applied to the entire dataset.
Currently, the system works for an individual patient. The next step is to integrate machine learning to generalize the technique for identifying different types of seizures across patients. Researchers are seeking to take advantage of various parameters characterizing the network and use them as features to train the machine learning algorithm.
The team’s overall aim is to one day design a device for people with epilepsy that is analogous to an insulin pump. As the neurons begin to synchronize, the device will provide medication or electrical interference to stop the seizure. However, for this to happen, researchers need a better understanding of the neural network.