Automated tonic-clonic seizure detection using random forests and spectral analysis on electroencephalography data.

Artificial intelligence (AI) has a potential for impact in the diagnosis of neurological conditions, the academic consensus generally has a positive outlook regarding how AI can improve the care of stroke victims and those who suffer from neuro-degenerative conditions such as dementia. When combined with Internet of Things technology, this could facilitate a new paradigm for epilepsy treatment. These technologies have applications in improving the welfare of epileptics, epilepsy being a common neurological condition that can result in premature death without a quick response. As such it is important for the system to avoid false negatives. This investigation focused on how machine learning algorithms can be utilised to identify these events through Electroencephalography (EEG) data. The UCI/Bonn dataset, a classic benchmark for automated epilepsy detection systems was identified and utilised. This investigation focused on the random forest algorithm. Given that EEG neurological data represents time series data and machine learning excels at this task, automation could be achievable via a wearable device. From there, Fast Fourier Transforms (FFT) were applied to identify if spectral features of EEG signals would aid identification of seizures. This method achieved an accuracy of 99%, precision of 98% and a recall of 100% in 12.2 milliseconds time to classify and one second of EEG data. These results show that random forests combined with FFT are a viable technique for attaining high recall when detecting grand mal epileptic seizures in short periods of time. CHB-MIT dataset was utilized for parity also showing good performance