New Algorithm Detects Epilepsy

Electroencephalograms give lots of information, and processing every single one requires a long period of time and many resources. To improve efficiency, scientists have developed an algorithm that highlights the most pertinent features of epileptic signals. This allows them to identify and classify epileptic seizures faster, and also see which parts of the brain are the most affected.

One of the researchers from the Department of Signal and Communications Theory (Departamento de Teoría de la Señal y Comunicaciones) at UC3M, Carlos Guerrero Mosquera states: “The advantage of this method is that it allows us to detect, classify or identify neurological diseases with a small amount of information. Electroencephalograms contain a lot of information and what we are looking for is to try to improve the efficiency of the tasks carried out by analyzing small amounts of information through the use of the most important data received from the signals.”

The researchers working on this project are engineers and doctors from Universidad Carlos III de Madrid (UC3M), the Clínica Universitaria de Navarra and Universidad Pública de Navarra. Their collaboration began as a project to discover and analyze the bioelectric phenomenon inside the cerebral cortex, in order to better understanding neurodegenerative diseases like Alzheimer's, Parkinson's or epilepsy.

The best way of getting answers concerning these pathologies was to use electroencephalography, as it allowed observing cerebral signals. For this technique, electrodes that measure and record bioelectric signals of the brain are placed upon the patient's scalp. The most difficult part comes afterward, when doctors and scientists have too much information to analyze and might risk missing certain signals.

The new method is easier and quite simple: a signal is captured on an electroencephalogram and a computer cleans or pre-processes the signal by eliminating the noise, establishing disease's characteristics at the end. It basically extracts information about the time and frequency pattern of the signal, allowing the detection and classification of epilepsy segments. Carlos Guerrero says: “The detection of data should follow a linear procedure but for the moment, we use databases. At a later date, when the application shows positive results, we will try to reduce processing costs by the selection of specific characteristics.”

The innovating algorithm has been published in the journal Medical & Biological Engineering & Computing. It will be compared with other techniques and the final results will be presented at the International Conference of the IEEE Engineering in Medicine and Biology Society, from 31st August until 4th September in Buenos Aires, Argentina.

“Initially this method was developed to classify and detect epileptic seizures, but in the future we wish to apply it to other neurodegenerative diseases such as Parkinson’s, Alzheimer or the analysis of different sleep disorders,” Guerrero added.