Assessing Velocity and Directionality of Uterine Electrical Activity for Preterm Birth Prediction Using EHG Surface Records

Abstract

The aim of the present study was to assess the capability of conduction velocity amplitudes and directions of propagation of electrohysterogram (EHG) waves to better distinguish between preterm and term EHG surface records. Using short-time cross-correlation between pairs of bipolar EHG signals (upper and lower, left and right), the conduction velocities and their directions were estimated using preterm and term EHG records of the publicly available Term–Preterm EHG DataSet with Tocogram (TPEHGT DS) and for different frequency bands below and above 1.0 Hz, where contractions and the influence of the maternal heart rate on the uterus, respectively, are expected. No significant or preferred continuous direction of propagation was found in any of the non-contraction (dummy) or contraction intervals; however, on average, a significantly lower percentage of velocity vectors was found in the vertical direction, and significantly higher in the horizontal direction, for preterm dummy intervals above 1.0 Hz. The newly defined features—the percentages of velocities in the vertical and horizontal directions, in combination with the sample entropy of the EHG signal recorded in the vertical direction, obtained from dummy intervals above 1.0 Hz—showed the highest classification accuracy of 86.8% (AUC=90.3%) in distinguishing between preterm and term EHG records of the TPEHGT DS.

Changes in uterine electromyography according to cervical dilatation in the first stage of labor

“…These changes can be detected non-invasively by recording uterine EMG from the abdominal surface. Our results are in accordance with previously published studies on accuracy of uterine EMG in predicting labor at term and preterm [9,12,13]. Maner et al [9,24,25] showed high sensitivity and specificity of EMG for predicting onset of labor at term.…”

“…Several uterine EMG parameters have been studied so far and found to indicate onset of true labor [10]. Moreover, various EMG signal processing techniques focusing on different frequency bands have been shown to yield important information on uterine contractility [13,[32][33][34]. For the purpose of the present study, we chose to focus on the PDS peak frequency, as this has been one of the most studied uterine EMG parameters in both human and animal studies so far [9,10,25].…”

“…In addition, EMG yields important information on changes in electrical properties of the myometrium characteristic of labor [7,8]. Several studies demonstrated that uterine EMG predicts onset of labor at term and preterm more accurately than other methods in clinical use today [9][10][11][12][13]. Uterine EMG properties have also been shown to differentiate active vs. latent labor in women presenting with regular contraction at term [7,14].…”

Prediction of Preterm Delivery from Unbalanced EHG Database

“…While the mentioned investigations showed satisfactory results for the prediction of preterm labor, the majority of them employed synthetic data generation to overcome the imbalance problem, which may cause misleading results [11,29,30], i.e., if an algorithm detects preterm labor cases with a sensitivity of 90% after data balancing, it is not clear how much of that 10% of misclassified preterm cases are related to real data. Indeed, if such a misclassification is strongly related to the real data, not the synthetically genereated ones, the performance may not be reliable.…”

“…Despite adequate performance, the mentioned measurements are either subjective or invasive [10]. Recently, the analysis of electrical representation of uterus contractions collected from the abdominal surface of pregnant women, known as electrohysterography (EHG), has been evidenced as a reliable tool for the prediction of premature delivery, as it is a non-invasive procedure that can be automated to reduce human intervention [11][12][13].…”