Analysis of Fluctuations of Uterine Contractions in Preterm Pregnancies using Adaptive Fractal Features of Electromyography Signals

Abstract

Analysis of fluctuations of uterine contractions under varied gestational ages is clinically significant. In this work, fluctuations associated with Preterm pregnancies are analyzed. For this, uterine electromyography (uEMG) signals in Preterm condition with varied gestational ages are considered. The signals are subjected to Adaptive Fractal Analysis (AFA) where a global trend is identified using overlapping windows of varying orders. The signal is detrended and fluctuation function is estimated. Hurst exponent features are extracted and analyzed statistically. Results show that AFA is able to characterize the variations in the fluctuations of Preterm uEMG signals. The feature values are distinct and vary with gestational age. Coefficient of variation is observed to be low, indicating that these features could handle inter-subject variability of Preterm signals. As early diagnosis of premature delivery is imperative for timely medical intervention and treatment, it appears that the proposed features could aid in determining the changes in uterine muscle contractions in Preterm condition.