Related Experiment Video
Updated: Jul 8, 2026
08:07
Electromyometrial Imaging of Uterine Contractions in Pregnant Women
Published on: May 26, 2023
Analysis of electrohysterogram signals for predicting obstetric outcome using machine learning methods: a scoping
Rubana H Chowdhury1,2, Roma Sultana3, Mithila Arman4
1Department of Electrical and Electronic Engineering, Chittagong University of Engineering & Technology, Chattogram, 4349, Bangladesh. rubanachy@gmail.com.
BMC Pregnancy and Childbirth
|July 6, 2026
Summary
Electrohysterography (EHG) shows promise for predicting obstetric outcomes like preterm birth. This review highlights EHG
Area of Science:
- Biomedical Engineering
- Obstetrics
- Machine Learning
Background:
- Accurate prediction of obstetric outcomes is vital for maternal and newborn health.
- Early identification of risk factors for preterm birth and Cesarean delivery is crucial.
Purpose of the Study:
- To review prediction models for obstetric outcomes using electrohysterography (EHG).
- To establish the most effective EHG-based prediction model for clinical decision-making.
Main Methods:
- Systematic literature review of EHG prediction models from December 2000 to February 2025.
- Searched biomedical databases using terms like electrohysterography, uterine electromyography, and EHG in machine learning.
- Analyzed EHG signal acquisition, pre-processing, feature extraction, and model properties.
Main Results:
- Four bipolar electrodes and a 0.1-4 Hz bandpass filter are common for EHG acquisition and pre-processing.
- Studies reported high discriminative performance (AUC 0.93-0.99) for predicting obstetric outcomes using EHG.
- A single classifier may be sufficient, but most studies had a high risk of bias due to small sample sizes and lack of external validation.
Conclusions:
- Academics and obstetricians can use this review to understand EHG analysis.
- EHG holds potential for clinical decision support systems in obstetrics.
