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

Abstract

In this work, an attempt has been made to analyze the influence of the frequencies bands in uterine electromyography (uEMG) signals on the detection of preterm birth. The signals recorded from the women’s abdomen during pregnancy are considered in this study. The signals are subjected to preprocessing using digital bandpass Butterworth filter and decomposed into different frequency bands namely, 0.3-1.0 Hz (F1), 1.0-2.0 Hz (F2) and 2.0-3.0Hz (F3). Spectral features namely, peak magnitude, peak frequency, mean frequency and median frequency are extracted from the power spectrum. Classification models namely, k-nearest neighbor, support vector machine and random forest are employed to distinguish the term and preterm conditions. The results show that the features extracted from these frequency bands are able to differentiate term and preterm condition. Particularly, the frequency band F3 performs better than other frequency bands. The features associated with these frequencies along with random forest classification model achieves a maximum accuracy of 75.2%. Thus, these measures could be used to accurately detect the preterm birth well in advance.

Enhancing classification of preterm-term birth using continuous wavelet transform and entropy-based methods of electrohysterogram signals

“…Given that there is no convention about the EHG bandwidth, three pass-band IIR filters were applied to each raw EHG channel in the following subbands: F1 (0.3 – 1 Hz), F2 (1 – 2 Hz), and F3 (2 – 3 Hz) conducting the procedure suggested by Selvaraju et al. ( 16 ). This filtering step evaluated the best frequency content to classify between P and T groups.…”

Preterm Birth Risk Stratification through Longitudinal Heart Rate and HRV Monitoring in Daily Life

“…Among these methods, the EHG is a frequently employed technique for recording the electrical activity of the uterine muscle 55 . Some studies have harnessed frequency and statistical features derived from EHG signals, employing various ML models to detect PTB [19][20][21] . However, the utility of the EHG signal is limited in high-risk individuals with comorbid conditions such as obesity and factors like fetal and placental position 56,57 , recognized contributors to PTB.…”

“…However, leveraging patient data from EHRs faces challenges, including incomplete records for pregnant women due to socio-economic barriers 18 . Some studies have adopted biomedical signal acquisition methods to predict PTB, such as electrohysterogram (EHG) signals, which indicate uterine electrical activity from the pregnant woman's abdominal surface and have been utilized in various investigations [19][20][21] .…”