PREDICTION OF PARKINSON'S DISEASE TREMOR ONSET USING A RADIAL BASIS FUNCTION NEURAL NETWORK BASED ON PARTICLE SWARM OPTIMIZATION

TLDR

Deep Brain Stimulation treats Parkinson’s disease by delivering continuous electrical signals, but its implanted batteries must be replaced every 18–24 months due to constant power draw. This study aims to extend battery life by accurately predicting tremor onset so that stimulation can be delivered on demand. The authors train a radial basis function neural network optimized with particle swarm optimization and reduced via principal component analysis on local field potential recordings from subthalamic nucleus electrodes, and validate its predictions against simultaneous forearm electromyography. The model achieves up to 89 % detection accuracy, and although the PSO‑based network performs slightly worse than a conventional RBFNN, it offers a notable reduction in computational overhead.

Abstract

Deep Brain Stimulation (DBS) has been successfully used throughout the world for the treatment of Parkinson's disease symptoms. To control abnormal spontaneous electrical activity in target brain areas DBS utilizes a continuous stimulation signal. This continuous power draw means that its implanted battery power source needs to be replaced every 18–24 months. To prolong the life span of the battery, a technique to accurately recognize and predict the onset of the Parkinson's disease tremors in human subjects and thus implement an on-demand stimulator is discussed here. The approach is to use a radial basis function neural network (RBFNN) based on particle swarm optimization (PSO) and principal component analysis (PCA) with Local Field Potential (LFP) data recorded via the stimulation electrodes to predict activity related to tremor onset. To test this approach, LFPs from the subthalamic nucleus (STN) obtained through deep brain electrodes implanted in a Parkinson patient are used to train the network. To validate the network's performance, electromyographic (EMG) signals from the patient's forearm are recorded in parallel with the LFPs to accurately determine occurrences of tremor, and these are compared to the performance of the network. It has been found that detection accuracies of up to 89% are possible. Performance comparisons have also been made between a conventional RBFNN and an RBFNN based on PSO which show a marginal decrease in performance but with notable reduction in computational overhead.