Characterization and automatic classification of preterm and term uterine records

Abstract

Predicting preterm birth is uncertain, and numerous scientists are searching for non-invasive methods to improve its predictability. Current researches are based on the analysis of ElectroHysteroGram (EHG) records, which contain information about the electrophysiological properties of the uterine muscle and uterine contractions. Since pregnancy is a long process, we decided to also characterize, for the first time, non-contraction intervals (dummy intervals) of the uterine records, i.e., EHG signals accompanied by a simultaneously recorded external tocogram measuring mechanical uterine activity (TOCO signal). For this purpose, we developed a new set of uterine records, TPEHGT DS, containing preterm and term uterine records of pregnant women, and uterine records of non-pregnant women. We quantitatively characterized contraction intervals (contractions) and dummy intervals of the uterine records of the TPEHGT DS in terms of the normalized power spectra of the EHG and TOCO signals, and developed a new method for predicting preterm birth. The results on the characterization revealed that the peak amplitudes of the normalized power spectra of the EHG and TOCO signals of the contraction and dummy intervals in the frequency band 1.0-2.2 Hz, describing the electrical and mechanical activity of the uterus due to the maternal heart (maternal heart rate), are high only during term pregnancies, when the delivery is still far away; and they are low when the delivery is close. However, these peak amplitudes are also low during preterm pregnancies, when the delivery is still supposed to be far away (thus suggesting the danger of preterm birth); and they are also low or barely present for non-pregnant women. We propose the values of the peak amplitudes of the normalized power spectra due to the influence of the maternal heart, in an electro-mechanical sense, in the frequency band 1.0-2.2 Hz as a new biophysical marker for the preliminary, or early, assessment of the danger of preterm birth. The classification of preterm and term, contraction and dummy intervals of the TPEHGT DS, for the task of the automatic prediction of preterm birth, using sample entropy, the median frequency of the power spectra, and the peak amplitude of the normalized power spectra, revealed that the dummy intervals provide quite comparable and slightly higher classification performances than these features obtained from the contraction intervals. This result suggests a novel and simple clinical technique, not necessarily to seek contraction intervals but using the dummy intervals, for the early assessment of the danger of preterm birth. Using the publicly available TPEHG DB database to predict preterm birth in terms of classifying between preterm and term EHG records, the 1/50 proposed method outperformed all currently existing methods. The achieved classification accuracy was 100% for early records, recorded around the 23rd week of pregnancy; and 96.33%, the area under the curve of 99.44%, for all records of the database. Since the proposed method is cap...

A Critical Look at Studies Applying Over-Sampling on the TPEHGDB Dataset

“…While impressive (near-perfect) results on the TPEHGDB dataset are reported in many studies [10,20,33,2,16,19,12,27,1,34,21,29,18,17,11,15], these results should be interpreted cautiously as their evaluation methodology is based on applying over-sampling strategies before data partitioning. All these studies apply over-sampling in order to make the distribution of classes more uniform.…”

Analysis of Frequency Bands of Uterine Electromyography Signals for the Detection of Preterm Birth

“…These sub-bands used in this study are 0.3 -1.0 Hz (F1), 1.0 -2.0 Hz (F2) and 2.0 -3.0 Hz (F3) which focus on the energy distribution in the different frequency bands. These frequency bands are filtered using Butterworth bandpass filters [8].…”

“…The Anderson-Darling test is utilized to examine the normality of the data and Wilcoxon's rank sum test is performed to analyze the statistical significance. Three classifiers namely, k-nearest neighbor (KNN), support vector machine (SVM) and random forest (RF) are considered [8]. The performance of the classifier is analyzed using metrics namely, accuracy (Acc), F-measure (F) and area under the curve (AUC).…”

“…Most of the studies analyzed uterine burst signals in the frequency range of 0.3-1 Hz [2]. However, few attempts have been made to analyze the different frequency ranges of uEMG signals [8].…”

Overly Optimistic Prediction Results on Imbalanced Data: a Case Study of Flaws and Benefits when Applying Over-sampling

“…When doing this, it is very important to ensure that segments extracted from the same original signal are not divided into both training and testing set [22,23]. Finally, there are many studies applying oversampling before partitioning the data into two mutually exclusive sets in order to make the distribution of classes more uniform [24,25,26,27,28,29,30,31,32,33,34].…”