Fetal ECG Extraction via Diffusion-Based Channel Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current fetal heart rate monitoring technologies face limitations due to low sampling rates, which fail to capture faster temporal fluctuations of vagal modulations, leading to inaccuracies in detecting early fetal academia and inflammatory responses, and existing methods for non-invasive fetal ECG signal extraction are costly and not widely accessible.
Innovation Solution
A system using two maternal abdominal leads and an abdominal electrocardiogram (aECG) device with a processor and computer-readable medium that creates linear combinations of signals to determine rough fetal ECGs, selects a channel, and measures heartbeat characteristics, employing modern time-frequency analysis and diffusion-based channel selection criteria.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If low sampling rates are used in fetal HR monitoring, then device simplicity and ease of use are improved, but measurement precision and detection accuracy deteriorate due to inability to capture faster temporal fluctuations of vagal modulations
Solution Approach 1:
The patent changes the sampling rate parameter from traditional low rates (e.g., 100-200 Hz) to high sampling rates (e.g., 1000 Hz or higher) to capture fast temporal fluctuations in fetal HR variability. This parameter change enables accurate detection of vagal modulations while maintaining device simplicity through automated processing algorithms.
2Measurement precision
If multi-lead ECG recordings are used to obtain high quality fetal ECG signals, then measurement precision is improved, but device complexity and cost increase making it inaccessible for widespread clinical use
Solution Approach 1:
The patent extracts the fetal ECG signal from the composite maternal-abdominal ECG recording by removing the dominant maternal ECG component. This extraction approach enables high-quality fetal ECG acquisition from simple two-lead abdominal recordings without requiring complex multi-lead fetal ECG systems, thereby reducing device complexity and cost.
Solution Approach 2:
The patent uses the maternal ECG signal as an intermediary to facilitate fetal ECG extraction. By identifying and removing the maternal ECG component (which serves as the intermediary), the fetal ECG signal can be isolated from the composite abdominal recording, enabling simple yet effective fetal monitoring.
3Measurement precision
If high sampling rates around 1000 Hz are used to capture vagal influences, then measurement precision is improved, but loss of energy and data processing requirements increase
Solution Approach 1:
The patent performs preliminary processing by extracting the fetal ECG signal and removing maternal ECG components before detailed HRV analysis. This preliminary action reduces the complexity of subsequent processing steps, enabling efficient analysis of high sampling rate data without excessive energy consumption.
Solution Approach 2:
The patent replaces complex mechanical multi-lead ECG systems with a simplified computational approach using automated algorithms for fetal ECG extraction and HRV analysis from two-lead abdominal recordings. This substitution reduces hardware complexity and associated energy requirements while maintaining measurement precision.
Data Source
AI summary
In some embodiments, techniques capable of obtaining high-quality fetal ECG (fECG) information using as few as two composite (maternal and fetal) maternal abdominal ECG (aECG) signals to derive the fetal ECG information are provided. In some embodiments, maternal ECG information and fetal ECG information are both obtained from the aECG signals, and are either presented or stored. The techniques may use novel proposed diffusion-based channel selection criteria. To validate the proposed techniques, analysis results of two publicly available databases are described, and compared with other available techniques in the literature.