Neural networks for recognizing patterns in cardiotocograms

Ulbricht, Claudia; Dorffner, Georg; Lee, Andreas

doi:10.1016/s0933-3657(97)00052-3

Cited by 37 publications

(19 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The work by Kukar et al [14] on diagnosing isachaemic heart disease uses 10-fold cross validation as does the work by Ulbricht et al on analysing cardiotocograms [22]. Indeed Ulbricht et al provide details of the range of performance they observe across the 10 networks and that analysis supports the findings presented here.…”

Section: Evaluating the Performance Of An Ann For Ivfsupporting

confidence: 73%

Stability problems with artificial neural networks and the ensemble solution

Cunningham

Carney

Jacob

2000

Artificial Intelligence in Medicine

177

View full text Add to dashboard Cite

Artificial Neural Networks (ANNs) are very popular as classification or regression mechanisms in medical decision support systems despite the fact that they are unstable predictors. This instability means that small changes in the training data used to build the model (i.e. train the ANN) may result in very different models. A central implication of this is that different sets of training data may produce models with very different generalisation accuracies. In this paper we show in detail how this can happen in a prediction system for use in In-Vitro Fertilisation. We argue that claims for the generalisation performance of ANNs used in such a scenario should only be based on k-fold cross validation tests. We also show how the accuracy of such a predictor can be improved by aggregating the output of several predictors.

show abstract

Section: Evaluating the Performance Of An Ann For Ivfsupporting

confidence: 73%

Stability problems with artificial neural networks and the ensemble solution

Cunningham

Carney

Jacob

2000

Artificial Intelligence in Medicine

177

View full text Add to dashboard Cite

show abstract

“…NNW analysis has been used for objective, definitive or quick decision making in a wide range of fields such as traveling sales [27], business, and in the medical field for applications including electroencephalography [28], histology [29], brain function analysis [30], brain tumor detection [31], smear categorization [32], visual field studies [33], response to fault [34], coronary artery disease [35], HIV studies [36], prediction of the duration of the first stage of labor [37], fetal weight estimation [38], and fetal monitoring [12][13][14][15]23].…”

Section: Discussionmentioning

confidence: 99%

“…The idea of global fetal monitoring with the aim of improving outcome was the inspiration for Maeda to create an experts' knowledge system program for FHR analysis and diagnosis in 1980 [9]. Other computer systems including the System 8000, an antenatal automated fetal diagnosis created by Dawes [10], the Porto system [11] to analyze CTG signals and others [12][13][14][15] have been studied for fetal monitoring.…”

Section: Introductionmentioning

confidence: 99%

Neural Network Analysis and Evaluation of the Fetal Heart Rate

et al. 2009

View full text Add to dashboard Cite

Abstract:The aim of the present study is to obtain a highly objective automatic fetal heart rate (FHR) diagnosis. The neural network software was composed of three layers with the back propagation, to which 8 FHR data, including sinusoidal FHR, were input and the system was educated by the data of 20 cases with a known outcome. The output was the probability of a normal, intermediate, or pathologic outcome. The neural index studied prolonged monitoring. The neonatal states and the FHR score strongly correlated with the outcome probability. The neural index diagnosis was correct. The completed software was transferred to other computers, where the system function was correct.

show abstract

“…As a result, many computerised systems have been developed to encapsulate expert interpretation of the CTG (3)(4)(5)(6)(7)(8)(9)(10). These range from simple feature extraction and classification systems to intelligent expert systems that assess the CTG along with clinical information to provide management advice.…”

Section: Introductionmentioning

confidence: 99%

Intelligent fetal heart rate analysis

Skinner

Garibaldi²,

Curnow³

et al. 2000

First International Conference on Advances in Medical Signal and Information Processing

View full text Add to dashboard Cite

The cardiotocogram (CTG) consists of a continuous recording of fetal heart rate and maternal contractions during labour. Changes in the fetal heart rate pattern relative to contractions provide an indication of fetal condition. There are two r6les in which the CTG can be used. The first is to identify cases of fetal compromise during labour, used by clinicians to determine the need for clinical intervention. The second is as a retrospective record of how labour was managed, used for clinical audit and potentially in litigation. CTG interpretation is a difficult task, requiring clinical experience and significant expertise. A crisp expert system for assessment of the CTG during labour had previously been developed. This paper describes the findings of a research project with two main aims: to investigate whether fuzzy logic could offer an improvement in CTG analysis over the crisp expert system; and to investigate whether retrospective analysis of complete CTG traces could be automated. Two studies are presented and the findings of each are summarised and discussed. It was found that fuzzification of the crisp expert system improved system performance and that, although fuzzy logic methodology is promising, retrospective analysis of the CTG requires considerably more work before reaching the status of a useful clinical tool.

show abstract

Neural networks for recognizing patterns in cardiotocograms

Cited by 37 publications

References 8 publications

Stability problems with artificial neural networks and the ensemble solution

Stability problems with artificial neural networks and the ensemble solution

Neural Network Analysis and Evaluation of the Fetal Heart Rate

Intelligent fetal heart rate analysis

Contact Info

Product

Resources

About