PubMed Health⌕ Search

Biomedical subjects

N A Gough

Publications and source records attributed to N A Gough.

11 recordsLinked to original sources
PubMed1999

Artificial neural network analysis of common femoral artery Doppler shift signals: classification of proximal disease.

The aim of this study was to apply artificial neural networks (ANNs) to the problem of the diagnosis of aorto-iliac arterial disease on the basis of the profile of the common femoral artery (CFA) Doppler flow velocity waveform. The maximum frequency envelopes obtained from the CFA of 180 subjects were used to create sets of training and testing vectors for a back-propagation ANN. The ANN had three outputs: one representing the absence of significant aorto-iliac disease (i.e., < 50% diameter stenosis), one representing the presence of a hemodynamically significant aorto-iliac stenosis (i.e., 50-99% stenosis), and the other representing the presence of an aorto-iliac occlusion. After training, the ANN correctly classified 80% of "no significant disease" testing data, 45% of "significant stenosis" data and 85% of "occlusion" data. This work, thus, demonstrated the ability of an ANN to identify the severity of aorto-iliac disease from the CFA waveform. Although the ANN outperformed standard univariate methods and visual classification of the data, it would appear that further work is needed to increase the accuracy of the ANN to a clinically acceptable standard.

Adult↗
PubMed1997

Neural network analysis of Doppler ultrasound blood flow signals: a pilot study.

It has been hypothesised that each artery in the human body has its own characteristic "signature" -a unique Doppler flow profile which can identify the artery and which may also be modified by the presence of disease. To test this hypothesis an artificial neural network (ANN) was trained to recognise three groups of maximum frequency envelopes derived from Doppler ultrasound spectrograms; these were the common carotid, common femoral and popliteal arteries. Data were collected from 24 subjects known to have no significant atheromatous disease. The maximum frequency envelopes were used to create sets of training and testing vectors for a backpropagation ANN. The ANN demonstrated a high success rate for appropriate classification of the test vectors: 100% for the carotid; 92% for the femoral; and 96% for the popliteal artery. This work has demonstrated the ability of the ANN to differentiate accurately between different and similar flow profiles, outlining the potential of this technology to identify subtle changes induced by the onset of arterial disease within a specific vessel. It should be noted that the ANN not only models the maximum frequency envelope but also, unlike standard indices, makes a decision as to which artery the maximum frequency envelope belongs to, thus providing the potential to obviate human subjective classification.

Adult↗
PubMed1993

Fractal analysis of foetal heart rate variability.

Current methods for analysing foetal heart rate (FHR) patterns have yet to meet their full potential in the recognition of hypoxia in the foetus. Following the recent suggestion that fractal analysis can be applied to FHR recordings, the current paper describes a method for distinguishing two simultaneous fractal dimensions in FHR variation. An irregular line was plotted from 2500 consecutive foetal heart beat to beat intervals derived from an ultrasound source. A window of 500 intervals was moved along the line in steps of 20 intervals. At each step the Richardson technique was used to make estimates of the length of the line within the window using 40 different ruler lengths. When the estimates were plotted against the ruler lengths on log-log axes the resulting curve exhibited two distinct linear regions, each demonstrating an inverse power relationship. From the two slopes the fractal dimensions were derived for unspecified low- and high-frequency FHR variation in the current window. The values of both fractal dimensions were plotted simultaneously with the irregular FHR line and were found to accord with perceived changes in FHR variation. The method described is simply a measure of the irregularity in a series of foetal heart beat to beat intervals: the existence of fractal properties in the irregular line does not of itself imply underlying deterministic dynamics (e.g. chaos). This new method of observing FHR variability requires no preprocessing of the measured data, which are all taken into account. Not only does it represent a method for studying normal foetal behaviour but also has potential as a sensitive indicator of impending foetal compromise.

Female↗
PubMed1989

A randomized study of a domiciliary antenatal care scheme: the effect on hospital admissions.

A preliminary randomized study has been made of a domiciliary management scheme which incorporates telephonic fetal heart rate monitoring for women with high-risk pregnancies. In this paper we report effects of the scheme on the pattern of hospital admissions. Sixty women were randomized 2:1 for domiciliary surveillance or for conventional hospital care, with 40 and 17 records finally available for analysis. The groups were well matched for maternal, obstetric and socio-economic characteristics. In the domiciliary group, 21 (53%) of the women avoided hospital admission altogether, the admission rate was more than halved, and the mean proportion of the time spent in hospital was reduced from 50% to 16% of the observation period. The women who received domiciliary care were generally satisfied with the scheme. Our study confirms expectations that carefully planned domiciliary surveillance can reduce the number and duration of hospital admissions.

Adolescent↗
PubMed1988

A device for measurement of radius of curvature of obstetric forceps.

Details of the design of obstetric forceps are important to ensure that they can be used safely for mother and baby. One of the most important measurements is the radius of the cephalic curve of the blades since if this is inappropriate there will be a poor grip on the baby's head and risk of slippage, superficial injury or even intracranial haemorrhage and brain damage because of undue compression. Because of the complex design of the forceps blades, which have a pelvic curve as well as a cephalic curve and a fenestra, the radius of the cephalic curve is difficult to measure. A device was designed to facilitate this measurement and was found to be accurate and reliable in use. This was the first stage in the study to assess the suitability for modern practice of instruments designed many years ago.

Equipment Design↗
PubMed1988

Fetal heart rate monitoring by telephone. I. Development of an integrated system in Cardiff.

We report the development of a practical dedicated system for domiciliary fetal monitoring integrated in a scheme for its rational application. From experience of 1120 domiciliary recordings in 74 women (64 with high-risk pregnancies), we suggest that domiciliary monitoring applied within a structured clinical context should be as safe as monitoring in hospital.

Female↗
PubMed1986

Antepartum fetal heart rate recording and subsequent fast transmission by a distributed microprocessor-based dedicated system.

Fetal heart rate monitoring in high-risk pregnancies can require admission to hospital over prolonged periods, or the even less satisfactory alternative of routine weekly or sporadic outpatient monitoring. We have developed a digital system for distant fetal heart rate recording with the facility of later rapid transmission by telephone into the hospital. A completed half-hour recording is transmitted to the central computer and permanently stored in less than 30 s, then immediately displayed for verbal reporting. One hundred and seventeen recordings have been made in 27 patients' homes and of these 111 (95%) were easy to interpret. This expandable system meets the major functional requirements for practical and economical antenatal fetal heart rate monitoring at a distance.

Computers↗
PubMed1978

Smoking in hospital: a survey of attitudes of staff, patients, and visitors.

A survey was carried out on attitudes to smoking in hospital. Analysis of 411 interviews showed that the majority (64%) of those questioned approved of some restrictions on patients smoking in the wards. Eighteen per cent would have liked to see a complete ban on smoking, while an identical number favoured no restrictions at all. Smoking habit influenced response; only 8% of smokers, compared with 25% of non-smokers, would have liked to see a total ban on smoking. Attitudes to smoking varied according to the status of the persons interviewed; only 6% of visitors and 7% of nurses approved of a complete ban on smoking, compared with 32% of medical students and 27% of doctors. The results suggest that the introduction of smoking and non-smoking areas in hospital wards would be approved by the majority of patients, staff, and visitors.

Adolescent↗
PubMedDate not supplied

Teleplot: a computing system for objective analysis of fetal heart rate recordings.

In human pregnancies, fetal heart rate recordings are useful both in predicting and in preventing imminent fetal death. Although an objective numerical measurement of such recordings is preferable to visual analysis, few obstetric centres have the computer expertise to implement this. Here we describe the principles of a technique whereby the fetal heart rate versus time trace may be transferred into computer memory for further processing in a numerical and objective fashion. The methodology is valid howsoever the fetal heart rate is detected.

Computers↗