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

Abstract

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.