Fetal ECG Signal Separation via Maternal Subtraction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for monitoring fetal cardiac activity during pregnancy face challenges in accurately distinguishing fetal ECG signals from maternal ECG signals, especially during fetal movement, leading to noise contamination and reduced signal quality.

Innovation Solution

A computer-implemented method using ECG sensors positioned on the abdomen of a pregnant woman, which involves digital signal filtering, non-linear subtraction procedures, and Blind-Source-Separation algorithms to isolate and enhance fetal ECG signals, improving signal-to-noise ratio and allowing for real-time detection of fetal heart rate and variability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If non-invasive ECG sensors are used to monitor fetal cardiac activity, then fetal health monitoring is achieved, but maternal ECG signals contaminate the fetal ECG signals reducing measurement precision

Engineering Contradiction:
Improvefetal ECG signal detection accuracyVSAvoidmaternal ECG signal contamination
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent segments the composite ECG signal into distinct maternal and fetal components through digital signal processing. The method divides the signal processing into separate stages: maternal ECG detection, maternal ECG subtraction, and fetal ECG extraction. This segmentation allows independent optimization of each component's detection algorithm, improving overall measurement precision by treating the contamination problem as a separable signal decomposition task.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent extracts the maternal ECG signal from the composite signal and removes it to isolate the fetal ECG signal. The system detects maternal ECG peaks, reconstructs the maternal ECG waveform, and subtracts it from the composite signal. This extraction approach directly eliminates the harmful contamination effect, allowing clear fetal ECG detection without invasive procedures.

Inventive Principle:
Principle #2Taking out (Extraction)

2Measurement precision

If signal processing algorithms are applied to separate fetal ECG from maternal ECG, then fetal signal detection accuracy improves, but device complexity increases

Engineering Contradiction:
Improvefetal ECG signal separation accuracyVSAvoidsignal processing algorithm complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent performs preliminary detection and characterization of maternal ECG signals before attempting fetal ECG extraction. The system first identifies maternal ECG peaks, determines maternal heart rate, and reconstructs the maternal ECG waveform template. This preliminary action simplifies subsequent fetal ECG detection by pre-removing the dominant maternal signal component, reducing the complexity of the overall separation algorithm.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent uses an adaptive template matching approach as an intermediary step between raw signal acquisition and fetal ECG detection. The maternal ECG template serves as a mediator that bridges the composite signal and the isolated fetal signal. This intermediary representation simplifies the mathematical operations required for signal separation compared to direct blind source separation methods.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Productivity

If real-time fetal ECG monitoring is implemented, then continuous fetal health assessment is achieved, but computational processing time increases

Engineering Contradiction:
Improvereal-time fetal monitoring capabilityVSAvoidsignal processing time
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The patent applies partial processing by focusing computational resources on detecting and removing only the maternal ECG component rather than processing the entire composite signal for fetal ECG detection. By performing selective maternal ECG subtraction and then using simplified fetal peak detection on the cleaned signal, the system achieves real-time processing with reduced computational burden compared to full-signal analysis methods.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The patent uses periodic maternal ECG cycle detection to structure the signal processing in rhythmic intervals. By detecting maternal R-peaks and processing signals in cardiac cycle segments, the system transforms continuous processing into periodic batches. This approach allows efficient use of computational resources and enables real-time monitoring by processing signals in manageable periodic segments rather than continuous streams.

Inventive Principle:
Principle #19Periodic action

Data Source

PatentEP3267884B1Systems, apparatus and methods for sensing fetal activity
Publication Date: 2021.07.28 NUVO GROUP
  • EP3267884B1 patent drawingFigure 1A~1B
  • EP3267884B1 patent drawingFigure 2
  • EP3267884B1 patent drawingFigure 3

AI summary

The invention provides systems and methods for monitoring the wellbeing of a fetus by the invasive detection and analysis of fetal cardiac electrical activity data.