Sleep spindle detection using artificial neural networks trained with filtered time-domain EEG: a feasibility study.

An artificial neural network (ANN) based on the Multi-Layer Perceptron (MLP) architecture is used for detecting sleep spindles in band-pass filtered electroencephalograms (EEG), without feature extraction. Following optimum classification schemes, the sensitivity of the network ranges from 79.2% to 87.5%, while the false positive rate ranges from 3.8% to 15.5%. Furthermore, due to the operation of the ANN on time-domain EEG data, there is agreement with visual assessment concerning temporal resolution. Specifically, the total inter-spindle interval duration and the total duration of spindles are calculated with 99% and 92% accuracy, respectively. Therefore, the present method may be suitable for investigations of the dynamics among successive inter-spindle intervals, which could provide information on the role of spindles in the sleep process, and for studies of pharmacological effects on sleep structure, as revealed by the modification of total spindle duration.

Autoassociative MLP in sleep spindle detection.

Spindles are one of the most important short-lasting waveforms in sleep EEG. They are the hallmarks of the so-called Stage 2 sleep. Visual spindle scoring is a tedious workload, since there are often a thousand spindles in one all-night recording of some 8 hr. Automated methods for spindle detection typically use some form of fixed spindle amplitude threshold, which is poor with respect to inter-subject variability. In this work a spindle detection system allowing spindle detection without an amplitude threshold was developed. This system can be used for automatic decision making of whether or not a sleep spindle is present in the EEG at a certain point of time. An Autoassociative Multilayer Perceptron (A-MLP) network was employed for the decision making. A novel training procedure was developed to remove inconsistencies from the training data, which was found to improve the system performance significantly.

Possibilities of classification of topographically distributed neurophysiological multi-channel data.

Progress in quantifying states of cerebral function and in the further development of automated EEG processing demands the application of suitable methods for the reduction of neurophysiological multi-channel data as well as their automatic classification. The method used here for reducing multi-channel data was to gain distributions of parametric descriptors from EEG data from computer-aided topographic electroencephalometry (CATEEM), for example the relative and absolute band power in the frequency bands delta, theta, alpha 1, alpha 2, beta 1, beta 2, total power, median and mode frequency, and other parameters. These values were subjected to cluster analysis. The classification of EEG parameters was carried out by means of discrimination analysis and neural networks. The practicability of both procedures was demonstrated in the reduction and classification of EEG data in the context of a normed study involving 104 healthy adults. These data have been used as the basis for a new evaluation study of 60 additional intraoperative EEG recordings obtained with CATEEM. In that newly started study, the effects of sedative and anaesthetic drugs on EEG behavior and psychophysiologic behavior remain to be investigated.