Decoding kinetic features of hand motor preparation from single-trial EEG using convolutional neural networks.

Building accurate movement decoding models from brain signals is crucial for many biomedical applications. Predicting specific movement features, such as speed and force, before movement execution may provide additional useful information at the expense of increasing the complexity of the decoding problem. Recent attempts to predict movement speed and force from the electroencephalogram (EEG) achieved classification accuracies at or slightly above chance levels, highlighting the need for more accurate prediction strategies. Thus, the aims of this study were to accurately predict hand movement speed and force from single-trial EEG signals and to decode neurophysiological information of motor preparation from the prediction strategies. To these ends, a decoding model based on convolutional neural networks (ConvNets) was implemented and compared against other state-of-the-art prediction strategies, such as support vector machines and decision trees. ConvNets outperformed the other prediction strategies, achieving an overall accuracy of 84% in the classification of two different levels of speed and force (four-class classification) from pre-movement single-trial EEG (100 ms and up to 1,600 ms prior to movement execution). Furthermore, an analysis of the ConvNet architectures suggests that the network performs a complex spatiotemporal integration of EEG data to optimize classification accuracy. These results show that movement speed and force can be accurately predicted from single-trial EEG, and that the prediction strategies may provide useful neurophysiological information about motor preparation.

Optimization of the KNN Supervised Classification Algorithm as a Support Tool for the Implantation of Deep Brain Stimulators in Patients with Parkinson's Disease.

Deep Brain Stimulation (DBS) of the Subthalamic Nuclei (STN) is the most used surgical treatment to improve motor skills in patients with Parkinson's Disease (PD) who do not adequately respond to pharmacological treatment, or have related side effects. During surgery for the implantation of a DBS system, signals are obtained through microelectrodes recordings (MER) at different depths of the brain. These signals are analyzed by neurophysiologists to detect the entry and exit of the STN region, as well as the optimal depth for electrode implantation. In the present work, a classification model is developed and supervised by the K-nearest neighbour algorithm (KNN), which is automatically trained from the 18 temporal features of MER registers of 14 patients with PD in order to provide a clinical support tool during DBS surgery. We investigate the effect of different standardizations of the generated database, the optimal definition of KNN configuration parameters, and the selection of features that maximize KNN performance. The results indicated that KNN trained with data that was standardized per cerebral hemisphere and per patient presented the best performance, achieving an accuracy of 94.35% (p < 0.001). By using feature selection algorithms, it was possible to achieve 93.5% in accuracy in selecting a subset of six features, improving computation time while processing in real time.

Selection of the Optimal Algorithm for Real-Time Estimation of Beta Band Power during DBS Surgeries in Patients with Parkinson's Disease.

Deep Brain Stimulation (DBS) is a surgical procedure for the treatment of motor disorders in patients with Parkinson's Disease (PD). DBS involves the application of controlled electrical stimuli to a given brain structure. The implantation of the electrodes for DBS is performed by a minimally invasive stereotactic surgery where neuroimaging and microelectrode recordings (MER) are used to locate the target brain structure. The Subthalamic Nucleus (STN) is often chosen for the implantation of stimulation electrodes in DBS therapy. During the surgery, an intraoperative validation is performed to locate the dorsolateral region of STN. Patients with PD reveal a high power in the ß band (frequencies between 13 Hz and 35 Hz) in MER signal, mainly in the dorsolateral region of STN. In this work, different power spectrum density methods were analyzed with the aim of selecting one that minimizes the calculation time to be used in real time during DBS surgery. In particular, the results of three nonparametric and one parametric methods were compared, each with different sets of parameters. It was concluded that the optimum method to perform the real-time spectral estimation of beta band from MER signal is Welch with Hamming windows of 1.5 seconds and 50% overlap.