Title :
Intelligent fetal heart rate analysis
Author :
Skinner, J.F. ; Garibaldi, J.M. ; Curnow, J. ; Ifeachor, E.C.
Author_Institution :
Plymouth Univ., UK
Abstract :
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 roles 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. The 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
Keywords :
cardiology; fuzzy logic; medical expert systems; obstetrics; uncertainty handling; CTG; CTG interpretation; cardiotocogram; clinical audit; clinical experience; clinical intervention; complete CTG traces; continuous recording; crisp expert system; fetal compromise; fetal condition; fetal heart rate pattern; fuzzification; fuzzy logic; intelligent fetal heart rate analysis; labour; litigation; maternal contractions; retrospective analysis;
Conference_Titel :
Advances in Medical Signal and Information Processing, 2000. First International Conference on (IEE Conf. Publ. No. 476)
Conference_Location :
Bristol
Print_ISBN :
0-85296-728-4
DOI :
10.1049/cp:20000311