Analysis of Electromyography Burst Signals using Topological Feature Extraction for Diagnosis of Preterm Birth

Preterm birth (gestation ≤ 37 weeks) is the leading cause of neonatal mortality and morbidity worldwide. Early diagnosis of Preterm is crucial for increasing the survival rate of infants [1]. Surface uterine Electromyography (uEMG) records the electrical activity of uterus during contraction. It quantitatively assesses the intensity, duration and frequency of uterine contractions. These contractions are characterized by a slow cyclic pattern of bursts followed by a period of quiescence [2]. Analysis of these bursts using uEMG signals has high sensitivity in detecting Preterm labor sign [3]. Significant information from these complex signals can be obtained using topological data analysis as it extracts the underlying shape characteristics of the signal [4]. Hence, in this study, an attempt has been made to differentiate Term (gestation > 37 weeks) and Preterm conditions using uEMG signals and topological features.