Use of the neural network for hypothesis generation in fetal surveillance

Artificial intelligence for diagnostic purposes: principles, procedures and limitations

BACKGROUND

Back propagation (BP) artificial neural networks are a distribution-free method for data analysis based on layers of artificial neurons that transduce imputed information. It has been recognized as having a number of advantages compared to traditional methods including the possibility to process imperfect data, and complex non-linear data. The objective of this study was to review the principles, procedures, and limitations of BP artificial neural networks for a non-mathematical readership.

METHODS

A real data sample of weight, height and measured body surface area from 90 individuals was used as an example. SPSS 17.0 with neural network add-on was used for the analysis. The predicted body surface from a two hidden layer BP neural network was compared to the body surface calculated by the Haycock equation.

RESULTS

Both the predicted values from the neural network and from the Haycock equation were close to the measured values. A linear regression analysis with neural network as predictor produced an r(2)-value of 0.983, while the Haycock equation produced an r(2)-value of 0.995 (r(2)>0.95 is a criterion for accurate diagnostic testing).

CONCLUSIONS

BP neural networks may, sometimes, predict clinical diagnoses with accuracies similar to those of other methods. However, traditional statistical procedures, such as regression analyses need to be added for testing their accuracies against alternative methods. Nonetheless, BP neural networks have great potential through their ability to learn by example instead of learning by theory.

A review of evidence of health benefit from artificial neural networks in medical intervention

The purpose of this review is to assess the evidence of healthcare benefits involving the application of artificial neural networks to the clinical functions of diagnosis, prognosis and survival analysis, in the medical domains of oncology, critical care and cardiovascular medicine. The primary source of publications is PUBMED listings under Randomised Controlled Trials and Clinical Trials. The rĵle of neural networks is introduced within the context of advances in medical decision support arising from parallel developments in statistics and artificial intelligence. This is followed by a survey of published Randomised Controlled Trials and Clinical Trials, leading to recommendations for good practice in the design and evaluation of neural networks for use in medical intervention.

The development of a hybrid expert system for the interpretation of fetal acid-base status

This article presents the development of an expert system for the interpretation of fetal scalp acid-base status. The system consists of logistic transformations, back-propagation neural networks and decision algorithms connected in series. It checks for out-of-range errors and the physiological coherence between measurements. It then determines whether acidosis should be diagnosed, and if so, whether it is more likely to be metabolic, respiratory or mixed. It will also flag those cases where it is difficult to interpret the data in physiological terms. The system was tested on a database of 2174 scalp blood samples collected at the Queens Medical Centre, Nottingham. Of these 88 samples were rejected as erroneous; 13 because of an out-of-range pH alone (> or = 7.48); 73 because more than one measurement was marginally out of range, and two because the relationship between measurements did not make sense. A total of 527 cases (24.2%) were diagnosed as being acidotic; of these, 139 were respiratory, 114 mixed and 274 metabolic. We were unable to fault the system's interpretation when the cases at the margins between diagnostic categories were reviewed clinically.