EPILEPSY is a neurological condition that affects one in every 100 people in the UK. One in three patients cannot be treated using drugs alone and treatment methods for these individuals include surgery removing the tissue causing the seizures. Surgeons drill holes into the skull to place electrodes in the brain to record the neural activity and record factors such as the size of the seizure, where the seizure is located, and how long it takes for seizure to occur.
The current surgical treatment methods are invasive, expensive, and inconvenient for patients as they usually have to stay in hospital for days or weeks at a time. However, this may be a thing of the past, as a new technique is being developed using a novel network analysis technique to locate exactly where in the brain the seizure originates from and predict seizure outcomes. Instead of taking weeks, the procedure will take minutes.
This new technique uses information flowing through the electrodes to predict all the essential factors from seizure size to location. The study was tested on a group of patients (N=27) to determine the accuracy of localising seizure onset brain regions. Bin He, Professor of Biomedical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA, explained the methods of the study: “We use machine learning and network analysis to analyse a 10-minute resting state recording to predict where the seizure will come out. While this method is still invasive, it is to a significantly decreased degree, because we’ve taken the recording timeline from multiple days or even weeks down to 10 minutes.”
By minimising the invasiveness of treatment, this would not only benefit the patient but also healthcare as it would save time, free up hospital beds, and be less expensive than current treatment methods. The researchers concluded that this research would help understand the mechanisms behind seizures using a less invasive procedure, and could help inform patients on whether they should get surgery and how successful it is likely to be.