Fluctuation Analysis of Uterine Contractions in Term Pregnancies Using Electrohysterography Signals and Empirical Mode Decomposition-Based Multifractal Features

Abstract

Investigating the fluctuations of uterine contractions is an indispensable diagnostic practice to evaluate the onset of labor. This work aims to differentiate the fluctuations associated with Term (gestation ≥ 37 weeks) pregnancies during varied gestational ages using electrohysterography (EHG) signals. The signals in the second and third trimesters are subjected to Multifractal-Empirical Mode Decomposition-based Detrended Fluctuation Analysis (MF-EMDDFA). Multifractal spectrum is estimated and features namely, Holder exponents ([Formula: see text], [Formula: see text]), broadness (BD), root slopes (LS, RS) and tangential slopes (TL, TR) are extracted. Machine learning methods, such as Naïve Bayes, adaptive boosting and random forest (RF) classifiers, are utilized to discriminate the contractions during different weeks of gestation. Results show that five multifractal features, namely [Formula: see text], [Formula: see text], BD, LS and TL, show significant differences between the considered gestational ages. An increase in regularity of the uterine contractions is observed as the gestational age increases. These features along with the RF classifier provide an accuracy, sensitivity, precision, recall and F1-score of greater than 98.30%. As the differentiation of uterine contractions during different weeks of gestation is vital to understanding the pregnancy progress, the proposed multifractal features could be used as potential biomarkers in clinical practices.