Showing papers by "Lionel Tarassenko published in 1996"

A new approach to the analysis of the human sleep/wakefulness continuum.

Abstract: The conventional approach to the analysis of human sleep uses a set of pre-defined rules to allocate each 20 or 30-s epoch to one of six main sleep stages. The application of these rules is performed either manually, by visual inspection of the electroencephalogram and related signals, or, more recently, by a software implementation of these rules on a computer. This article evaluates the limitations of rule-based sleep staging and then presents a new method of sleep analysis that makes no such use of pre-defined rules and stages, tracking instead the dynamic development of sleep on a continuous scale. The extraction of meaningful features from the electroencephalogram is first considered, and for this purpose a technique called autoregressive modelling was preferred to the more commonly-used methods of band-pass filtering or the fast Fourier transform. This is followed by a qualitative investigation into the dynamics of the electroencephalogram during sleep using a technique for data visualization known as a self-organizing feature map. The insights gained using this map led to the subsequent development of a new, quantitative method of sleep analysis that utilizes the pattern recognition capabilities of an artificial neural network. The outputs from this network provide a second-by-second quantification of the sleep/wakefulness continuum with a resolution that far exceeds that of rule-based sleep staging. This is demonstrated by the neural network's ability to pinpoint micro-arousals and highlight periods of severely disturbed sleep caused by certain sleep disorders. Both these phenomena are of considerable clinical value, but neither are scored satisfactorily using rule-based sleep staging.

Effect of short term graded withdrawal of nasal continuous positive airway pressure on systemic blood pressure in patients with obstructive sleep apnoea.

Abstract: It is debated whether obstructive sleep apnoea (OSA) is a significant independent risk factor for sustained hypertension or cardiovascular morbidity and mortality. In an attempt to avoid the problem of confounding variables we have investigated whether withdrawing nasal continuous positive airway pressure (NCPAP) from patients with OSA for different proportions of the night leads to a subsequent rise in their morning blood pressures. Six patients with treated OSA had their NCPAP automatically varied between 3 cms H2O and a therapeutic pressure over 5 successive nights. The proportion of therapeutic NCPAP given was kept constant over the 5 nights and blood pressure measured the morning after the 5th night. Each patient had 5 different levels of sleep disruption, from no therapeutic NCPAP at all, through to 100% NCPAP. The nocturnal consequences of these different proportions of NCPAP were quantified both by oximetry and by a new EEG analysis that provides an objective estimate of the periodicity (fluctuations in the EEG depth) of the time course seen in patients with OSA. Increasing degrees of nocturnal hypoxic dipping and EEG periodicity were positively correlated with the subsequent morning systolic and diastolic blood pressures (p < 0.02). About 20% of the variance in systolic and diastolic blood pressure could be accounted for by the amount of either hypoxic dipping or EEG periodicity. The results of this study suggest that acute changes in awake blood pressure can be caused by sleep apnoea. It agrees with other data suggesting that OSA can have an independent influence on morning BP, but that this effect may have worn off by the afternoon and evening. Some of the discrepancies between the numerous studies in this area may be due to the timing of blood pressure measurements.

Neural Network Prediction of Relapse in Breast Cancer Patients

Abstract: When a woman diagnosed as having breast cancer has a tumour removed, it is important to try and predict whether she is likely to relapse within, say, the next three years. In this paper, the performance of a neural network classifier trained on a number of prognostic indicators is shown to be better than that of the clinical experts working with the same information. To obtain meaningful statistics with the relatively small dataset available, the network is trained using a modified form of the leave-one-out method. A procedure is also introduced for investigating how much independentinformation each input parameter contributes. This shows that, in this type of retrospective study, the type of therapy given to the woman does not significantly affect the network's prediction of whether or not she will relapse within three years. Finally, since this problem, in common with many other medical problems, is plagued by a shortage of data, the final section of the paper reports on an investigation of whether or not multi-centre databases might be feasible.

Perturbation techniques for on-chip learning with analogue VLSI MLPs

Abstract: Microelectronic neural network technology has become sufficiently mature over the past few years that reliable performance can now be obtained from VLSI circuits under carefully controlled conditions (see Refs. 8 or 13 for example). The use of analogue VLSI allows low power, area efficient hardware realisations which can perform the computationally intensive feed-forward operation of neural networks at high speed, making real-time applications possible. In this paper we focus on important issues for the successful operation and implementation of on-chip learning with such analogue VLSI neural hardware, in particular the issue of weight precision. We first review several perturbation techniques which have been proposed to train multi-layer perceptron (MLP) networks. We then present a novel error criterion which performs well on benchmark problems and which allows simple integration of error measurement hardware for complete on-chip learning systems.

Contact lens oximetry: a valid concept?

Abstract: Although it has been shown that the technique of contact lens pulse oximetry has severe limitations, the authors' imaging study showed that the technology now exists with which to develop a compact imaging system which could perform oximetry on the blood in the retinal fundus. Individual vessels could be segmented from the images in order to determine blood oxygen saturation in either arteries or veins. This would provide valuable information for an anaesthetist during surgery and would neatly circumvent one of the main limitations of pulse oximetry, namely the need to detect a pulse before analysis can begin. Perhaps most importantly, this instrument could be used with cardiac patients in the hope that it would significantly improve their level of care in the operating theatre.