Automated Spike Detection Using Neural Networks

A computerized instrument will be develop for automated spike and seizure detection. The objectivemethods to increase the effectiveness of monitoring and to increase the quality and reduce the costThe spike detector will utilize a combination of methods. These will include parametric descriptionLaplacian derivatives, an artificial neural network (ANN) producing likelihood estimates for each evrules to select candidate events for the ANN, further rules to select events based on the ANN outputA graphical user interface will allow the investigator to review results quickly and to retrain theneeds. In Phase I, software for the proposed detector will be developed along with tools to measureparameters on the sensitivity and selectivity of the system. A database of spikes and non-epilepticestablished to train and test the detector, to demonstrate its performance, and to optimize detectiostudies will employ a larger data base and will include seizure as well as interictal and non- epile