Automatic Classification of Antepartum Cardiotocography Using Fuzzy Clustering and Adaptive Neuro-Fuzzy Inference System

Antepartum cardiotocography (CTG) monitoring is a crucial screening tool widely utilized to evaluate fetal wellbeing. However, the complexity and non-linearity of CTG usually result in inter-observer and intra-observer variability in a visual CTG interpretation using clinical guidelines. In this paper, a fuzzy C-means clustering based adaptive neuro-fuzzy inference system (FCM-ANFIS) was proposed to automatically classify CTG for antenatal fetal monitoring. Data visualization and spearman correlation analysis were implemented to select CTG features. Then, the fuzzy space was partitioned by using fuzzy C-means clustering algorithm, and the adjustment parameters were adjusted through the self-learning mechanism of neural networks and least squares algorithm. The experimental results show that the fuzzy space partition based on FCM clustering could improve the performance of ANFIS, and the proposed FCM-ANFIS model outperforms the state-of-the-art automatic classification of CTG models. In conclusion, the proposed FCM-ANIFIS model has promising learning ability and adaptability for the complexity and uncertainty of antenatal CTG interpretation.