John R. Glover

Context-based automated detection of epileptogenic sharp transients in the EEG: elimination of false positives

A description is given of a knowledge-based system for the elimination of false positives in the automated detection of epileptogenic sharp transients in the EEG (electroencephalogram). The system makes comprehensive use of spatial and temporal context information available on 16 channels of EEG. EKG, (electrocardiogram) EMG (electromyogram), and EOG (electrooculogram). A knowledge-based implementation is used because of the ease with which it allows the contextual rules to be expressed and refined. The resulting system is shown to be capable of rejecting a wide variety of artifacts commonly found in EEG recordings that cause numerous false positive detections in systems making less comprehensive use of context.<<ETX>>

Adaptive Control of Blood Pressure

Stochastic adaptive controllers have been developed for automatic control of blood pressure during infusions of cardiostimulatory or vasoactive drugs. An adaptive algorithm based upon a minimum variance control law is presented. A more advanced algorithm obtained by augmenting the performance measure to include the rate of charge of the control signal is also presented. An autoregressive-moving-average (ARMA) model, representing the dynamics of the system, and a recursive least-squares parameter estimation technique are used for both algorithms. A series of experiments was performed in dogs, utilizing an electronically activated drug infuser. Stable control was achieved, even when the circulatory state of the animal underwent major changes, using either algorithm. On the basis of theoretical considerations and experimental results, we expect that these adaptive controllers will significantly improve the performance of drug infusion systems in clinical applications.

A multistage system for the automated detection of epileptic seizures in neonatal electroencephalography.

This paper describes the design and test results of a three-stage automated system for neonatal EEG seizure detection. Stage I of the system is the initial detection stage and identifies overlapping 5-second segments of suspected seizure activity in each EEG channel. In stage II, the detected segments from stage I are spatiotemporally clustered to produce multichannel candidate seizures. In stage III, the candidate seizures are processed further using measures of quality and context-based rules to eliminate false candidates. False candidates because of artifacts and commonly occurring EEG background patterns such as bifrontal delta activity are also rejected. Seizures at least 10 seconds in duration are considered for reporting results. The testing data consisted of recordings of 28 seizure subjects (34 hours of data) and 48 nonseizure subjects (87 hours of data) obtained in the neonatal intensive care unit. The data were not edited to remove artifacts and were identical in every way to data normally processed visually. The system was able to detect seizures of widely varying morphology with an average detection sensitivity of almost 80% and a subject sensitivity of 96%, in comparison with a team of clinical neurophysiologists who had scored the same recordings. The average false detection rate obtained in nonseizure subjects was 0.74 per hour.

Detection of pseudosinusoidal epileptic seizure segments in the neonatal EEG by cascading a rule-based algorithm with a neural network

This paper presents an approach to detect epileptic seizure segments in the neonatal electroencephalogram (EEG) by characterizing the spectral features of the EEG waveform using a rule-based algorithm cascaded with a neural network. A rule-based algorithm screens out short segments of pseudosinusoidal EEG patterns as epileptic based on features in the power spectrum. The output of the rule-based algorithm is used to train and compare the performance of conventional feedforward neural networks and quantum neural networks. The results indicate that the trained neural networks, cascaded with the rule-based algorithm, improved the performance of the rule-based algorithm acting by itself. The evaluation of the proposed cascaded scheme for the detection of pseudosinusoidal seizure segments reveals its potential as a building block of the automated seizure detection system under development.

A Multichannel Signal Processor for the Detection of Epileptogenic Sharp Transients in the EEG

A high-speed multichannel signal processing system is described which is capable of performing automated detection of epileptogenic sharp transients (ST) in the electroencephalogram (EEG). The system is implemented with individually programmable microprocessors on the input channels, followed by a single-board microcomputer which correlates results obtained from each channel, and can process data played back from a tape recorder at a speed eight times the realtime recording speed. A multichannel correlation algorithm is used to enhance the performance of the system in the presence of muscle artifact (EMG). Results are presented showing that the multichannel correlation is capable of reducing, in some cases, both missed detections due to poorly defined STs and false alarms due to EMG.

An automated system for epileptogenic focus localization in the electroencephalogram.

This paper describes an automated system for the detection and localization of foci of epileptiform activity in the EEG. The system detects sharp EEG transients (STs) in the process, but the emphasis is on epileptic focus localization. A combination of techniques involving signal processing, pattern recognition, and the expert rules of an experienced electroencephalographer, involving considerable spatiotemporal context information, is applied to multichannel EEG data. An overall emphasis on minimizing the number of false-positive sharp transient detections drives the system design. Tested on data from 13 subjects with epileptiform activity and 5 controls, all areas of focal epileptiform activity were detected by the system, although not all of the contributing foci were reported separately. Two false-positive foci were detected as well due to nonfocal spike activity and normal spike-like activity not present in the training set. The system detected 95.7% of the epileptiform events constituting the correctly detected foci, with a false detection rate of 11.1%.

Integrating Hardware and Software in a Computer Engineering Laboratory

A systematic approach to the design of a multipurpose computer engineering laboratory is presented. An essential ingredient of a successful computer engineering program, and of an effective laboratory servicing that program, is that the hardware and software aspects of the curriculum be truly integrated. The laboratory described here is designed around a central resource-sharing minicomputer to which are connected minimal microcomputer stations. This configuration is proposed as the most cost-effective and the most educationally effective approach to the integration of hardware and software in a microcomputer curriculum.

An evaluation of quantum neural networks in the detection of epileptic seizures in the neonatal electroencephalogram

This paper presents the results of an experimental study that evaluated the ability of quantum neural networks (QNNs) to capture and quantify uncertainty in data and compared their performance with that of conventional feedforward neural networks (FFNNs). In this work, QNNs and FFNNs were trained to classify short segments of epileptic seizures in neonatal EEG. The experiments revealed significant differences between the internal representations created by trained QNNs and FFNNs from sample information provided by the training data. The results of this experimental study also confirmed that the responses of trained QNNs are more reliable indicators of uncertainty in the input data compared with the responses of trained FFNNs.

Adaptive line enhancement and spectrum analysis

The notion that adaptive filters may estimate and track the frequency of a phase-modulated sinusoid in noise better than a spectrum analyzer is examined. It is argued, using both theoretical and experimental results, that spectrum analysis performs better than adaptive filtering. In addition, the method of spectrum analysis can be improved for such applications by the use of frequency-slope processing, or by the generation of a partially coherent reference waveform by maximum posterior probability estimation of the phase function.

Comments on "Digital Filters for Real-Time ECG Signal Processing Using Microprocessors"

In an earlier paper1 an adaptive filtering algorithm was proposed for the elimination of 60 Hz interference in the ECG. It is shown here that this algorithm is not truly adaptive, but is approximately equivalent to a fixed 60 Hz notch filter.