Abstract
Our goal is to use existing and to propose new time-frequency entropy measures that objectively evaluate the improvement on epileptic patients after medication by studying their resting state electroencephalography (EEG) recordings. An increase in the complexity of the signals would confirm an improvement in the general state of the patient. We review the Rényi entropy based on time-frequency representations, along with its time-varying version. We also discuss the entropy based on singular value decomposition computed from a time-frequency representation, and introduce its corresponding time-dependant version. We test these quantities on synthetic data. Friedman tests are used to confirm the differences between signals (before and after proper medication). Principal component analysis is used for dimensional reduction prior to a simple threshold discrimination. Experimental results show a consistent increase in complexity measures in the different regions of the brain. These findings suggest that extracted features can be used to monitor treatment. When combined, they are useful for classification purposes, with areas under ROC curves higher than 0.93 in some regions. Here we applied time-frequency complexity measures to resting state EEG signals from epileptic patients for the first time. We also introduced a new time-varying complexity measure. We showed that these features are able to evaluate the treatment of the patient, and to perform classification. The time-frequency complexities, and their time-varying versions, can be used to monitor the treatment of epileptic patients. They could be applied to a wider range of problems.
Highlights
E LECTROENCEPHALOGRAPHY (EEG) is a technique that records variations of the electrical potentials along time between 2 electrodes placed over the scalp
The application of entropy to EEG is widespread nowadays [8], [9], [10], [11], even with examples of entropies computed from time-frequency representations [12]. Some of these entropy measures can have some limitations to discriminate signals of different complexity, which will be illustrated. It is the purpose of the present work to propose new time-varying complexity measures useful to better distinguish signal complexities and to apply them to the study of EEG recordings from children with benign childhood epilepsy with centrotemporal spikes (BECTS)
We propose here to define a time-varying version of this complexity measure by taking the singular value decomposition of a slice of width ∆t of the time-frequency representation:
Summary
E LECTROENCEPHALOGRAPHY (EEG) is a technique that records variations of the electrical potentials along time between 2 electrodes placed over the scalp. Some of these entropy measures can have some limitations to discriminate signals of different complexity, which will be illustrated Because of that, it is the purpose of the present work to propose new time-varying complexity measures useful to better distinguish signal complexities and to apply them to the study of EEG recordings from children with benign childhood epilepsy with centrotemporal spikes (BECTS). It is the purpose of the present work to propose new time-varying complexity measures useful to better distinguish signal complexities and to apply them to the study of EEG recordings from children with benign childhood epilepsy with centrotemporal spikes (BECTS) This form of epilepsy is the most common epileptic syndrome of childhood and has usually a favorable evolution with full recovery expected at adolescence and absence or mild cognitive deficits.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
