A New Approach to Extract Fetal Electrocardiogram Using Affine Combination of Adaptive Filters

TL;DR

This paper introduces a novel affine combination method of adaptive filters, specifically combining LMS and RLS, to improve the extraction of fetal ECG signals from noisy abdominal recordings, outperforming existing techniques.

Contribution

The paper proposes a new affine combination approach of adaptive filters, notably the CRLS filter, for more accurate fetal ECG extraction from noisy signals, demonstrating superior performance over state-of-the-art methods.

Findings

CRLS filter outperforms other combinations in FECG extraction.

CRLS is more effective with low SNR abdominal signals.

Performance metrics improved: sensitivity by 3.58%, accuracy by 2.39%, F1 score by 1.36%.

Abstract

The detection of abnormal fetal heartbeats during pregnancy is important for monitoring the health conditions of the fetus. While adult ECG has made several advances in modern medicine, noninvasive fetal electrocardiography (FECG) remains a great challenge. In this paper, we introduce a new method based on affine combinations of adaptive filters to extract FECG signals. The affine combination of multiple filters is able to precisely fit the reference signal, and thus obtain more accurate FECGs. We proposed a method to combine the Least Mean Square (LMS) and Recursive Least Squares (RLS) filters. Our approach found that the Combined Recursive Least Squares (CRLS) filter achieves the best performance among all proposed combinations. In addition, we found that CRLS is more advantageous in extracting FECG from abdominal electrocardiograms (AECG) with a small signal-to-noise ratio (SNR). Compared with the state-of-the-art MSF-ANC method, CRLS shows improved performance. The sensitivity, accuracy, and F1 scores improved by 3.58%, 2.39%, and 1.36%, respectively.