Loading...
Comparative performance analysis of AFM, TS, and BSS methods for non-invasive fetal ECG extraction
Crowley, Cara Amphone, Dara
Crowley, Cara
Amphone, Dara
Citations
Altmetric:
Files
Authors
Other Names
Location
Time Period
Advisors
Original Date
Digitization Date
Issue Date
2026-04-24
Type
Abstract
Genre
Keywords
Subjects (LCSH)
Citation
Crowley, Cara; Amphone, Dara; Lee, Kyoungnae. 2026. Comparative performance analysis of AFM, TS, and BSS methods for non-invasive fetal ECG extraction. -- In Proceedings: 25th Annual Undergraduate Research and Creative Activity Forum. Wichita, KS: Wichita State University.
Abstract
Reliable fetal heart monitoring is critical for the early detection of fetal health conditions such as myocardial ischemia and intrapartum hypoxia. Unlike invasive fetal electrocardiography (fECG), non-invasive fetal electrocardiography (NI-fECG) utilizes abdominal electrodes to capture fetal cardiac signals, providing a safer and more practical clinical alternative. However, robust extraction of the fetal signal remains challenging due to its low amplitude relative to the maternal ECG and the presence of physiological and environmental noise. In this study, simulated abdominal ECG (aECG) data from the open-source FECGSYN database were used to benchmark three primary categories of extraction algorithms: Blind Source Separation (BSS), Template Subtraction (TS), and Adaptive Filtering Methods (AFM). Evaluations were conducted under multiple noise conditions, with Signal-To-Noise Ratios (SNR) ranging from -12 dB to 8 dB. Performance was quantified using the F1 score – defined as the harmonic mean of sensitivity and positive predictive value – across five trials to assess extraction accuracy. Results indicate that AFM approaches (including LMS, RLS, and ESN) and TS methods (specifically CER and PCA) consistently outperform BSS techniques, which showed lower F1 scores across the tested SNR range. These findings provide important technical guidance for selecting robust extraction frameworks for continuous fetal monitoring. Ultimately, this study lays the groundwork for advancing NI-fECG techniques by demonstrating reliable fetal heartbeat detection, a critical step toward enabling morphological analysis that could enhance prenatal care and facilitate early identification of fetal complications.
Table of Contents
Description
Presented to the 25th Undergraduate Research and Creative Activity Forum (URCAF) held in Woolsey Hall, Wichita State University, April 24, 2026.
Publisher
Wichita State University
Journal
Book Title
Series
URCAF;v.25