Antenatal fetal risk assessment using a neurofuzzy technique

Abstract

This study defines an intelligent neurofuzzy system for antepartum fetal evaluation, The task is to investigate the Doppler ultrasound measurements of the umbilical artery (UA) and the cerebral artery (CA) to relate the health conditions of fetuses. We thus use the UA blood flow velocity waveforms [pulsality index, resistance index, and systolic/diastolic ratio] and the ratios of cerebral-umbilical resistance indices in terms of weeks. We then make a decision on the basis of a fuzzy-rule-based system combined with data-based learning strategies such as a radial basis function network and a multilayer perceptron for assessing the hypoxia suspicion. A fuzzy grade of membership is used for the evaluation of the seriousness of the situation of the fetus, and the diagnostic interpretations for doctors such as good, suspicious, and alarming conditions of fetus are derived.