Evaluation of Various Population-Based Techniques for Extracting Non-Invasive Fetal Electrocardiography

Overview

This study compares five population-based algorithms for non-invasive fetal electrocardiogram (NI-fECG) extraction, revealing that gray wolf optimization (GWO), moth flame optimization (MFO), particle swarm optimization (PSO), and whale optimization algorithm (WOA) perform similarly, while artificial bee colony (ABC) shows poor performance. The findings suggest potential for hybrid approaches to improve extraction accuracy.

Background

Non-invasive fetal electrocardiography (NI-fECG) is an emerging technique in prenatal care that allows for the assessment of fetal well-being by capturing the electrical activity of the fetal heart. Compared to traditional cardiotocography (CTG), NI-fECG provides additional diagnostic features, making it a promising alternative for continuous fetal monitoring. However, the presence of noise from maternal signals complicates the extraction of the fetal electrocardiogram (fECG), necessitating the evaluation of various optimization algorithms for effective signal extraction.

Data Highlights

Key Findings

• GWO, MFO, PSO, and WOA algorithms demonstrated comparable extraction accuracy for fECG.
• ABC algorithm exhibited poor performance and instability in extraction tasks.
• All algorithms were tested on two datasets: Labor and Pregnancy.
• Experiments were conducted 30 times independently to assess stability.
• Further research into hybrid approaches may enhance the performance of the ABC algorithm.

Clinical Implications

The findings highlight the effectiveness of certain optimization algorithms in extracting fetal ECG signals, which could improve prenatal monitoring practices. Clinicians may consider integrating these algorithms into existing fetal monitoring systems to enhance the accuracy of fetal distress detection.

Conclusion

This comparative analysis underscores the potential of advanced optimization algorithms in improving non-invasive fetal ECG extraction, with implications for enhancing fetal monitoring techniques in clinical practice.

Related Resources & Content

1. BMC Pregnancy and Childbirth, 2026 -- Feasibility and safety of intrapartum foetal pulse oximetry using a disposable scalp probe
2. Archives of Gynecology and Obstetrics, 2026 -- OPM-based fetal magnetocardiography: fetal cardiac time intervals in healthy pregnancies compared to postnatal ECGs
3. European Radiology, 2023 -- Evaluation of Fetal Myocardial Strain Through Cardiac MRI Utilizing Doppler Ultrasound Gating and Feature Tracking Techniques
4. Clinical Research in Cardiology, 2011 -- Initial Clinical Assessment of an Innovative Capacitive ECG System in Patients Experiencing Acute Myocardial Infarction
5. ACOG Clinical Practice Guideline No. 10, 2025
6. NICE Guideline NG229, 2026 -- Fetal monitoring in labour
7. Computerised interpretation of fetal heart rate during labour (INFANT): a randomised controlled trial
8. A Randomized Trial of Intrapartum Fetal ECG ST-Segment Analysis
9. ST waveform analysis vs cardiotocography alone for intrapartum fetal monitoring: An updated systematic review and meta‐analysis of randomized trials
10. Reliability and agreement in intrapartum fetal heart rate monitoring interpretation: A systematic review
11. ONG-25-1397 583..599
12. History | Fetal monitoring in labour | Guidance | NICE
13. Assessing signal loss, accuracy, and acceptability of an ambulatory fetal electrocardiography with cardiotocography in the antepartum and intrapartum phases - Tan - 2026 - Acta Obstetricia et Gynecologica Scandinavica - Wiley Online Library
14. Review of Non-Invasive Fetal Electrocardiography Monitoring Techniques | MDPI
15. Deep learning-based approach for accurate detection of fetal QRS complexes in abdominal ECG signals | Scientific Reports
16. Intrapartum electronic fetal heart rate monitoring to predict acidemia at birth with the use of deep learning - ScienceDirect