Fetal heart rate extraction from abdominal electrocardiograms through multivariate empirical mode decomposition

Area of Science:

• Biomedical Engineering
• Signal Processing
• Maternal-Fetal Medicine

Background:

• Fetal heart rate (FHR) and variability (fHRV) are crucial for assessing fetal well-being, especially in high-risk pregnancies.
• Abdominal electrocardiogram (abdECG) offers a non-invasive approach to capture fetal electrocardiograms.

Purpose of the Study:

• To propose and validate a novel methodology for extracting FHR from abdECG recordings.
• To utilize the multivariate empirical mode decomposition (MEMD) technique for improved FHR signal extraction.

Main Methods:

• Applied MEMD to decompose abdECG signals into intrinsic mode functions (IMFs).
• Developed a channel selection and denoising strategy based on IMF analysis.
• Implemented a wavelet-based approach for fetal R-peak detection after removing maternal QRS complexes.

Main Results:

• The proposed methodology successfully extracted FHR signals from abdECG recordings.
• Achieved a high cross-correlation value of 0.983 between detected and true FHR signals.
• Demonstrated effective noise reduction and maternal signal elimination.

Conclusions:

• The MEMD-based technique provides an accurate and reliable method for FHR extraction from abdECG.
• This approach enhances the assessment of fetal well-being in clinical settings.
• The validated methodology shows significant potential for non-invasive fetal monitoring.