Classification of fetal pathologies through fuzzy inference systems based on a multiparametric analysis of fetal heart rate

Proposes new classifiers based on fuzzy inference systems (FISs) for the Fetal Heart Rate (FHR) signal analysis. They include standard cardiotocographic (CTG) parameters together with a set of frequency domain and nonlinear indices. The goal is the identification of two very common fetal pathological conditions: Intra-Uterine Growth Retardation (IUGR) and Diabetes type I. The FHR signals obtained from 104 CTG recordings were analyzed (75 Normal, 11 IUGR and 18 Diabetic). Fuzzy classifiers combine the set. Of 10 input data into the S-output set (Normal, IUGR, Maternal Diabetes) by fuzzy relies. Results show FISs predict normal and pathological fetal states even with 100% of correct classifications. Their performance however is always higher than 80% in the whole population, depending on the rule number. This approach can strongly help the automatic CTG signal analysis improving the early discrimination among normal and pathological fetal conditions.