ECG Signal Classification via Bipolar-Unipolar Ratio Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for mapping and imaging electrical signals in the heart, such as the CARTO® 3 System, face challenges in accurately classifying local activation times (LAT) due to interference and complexity in ECG signals, making it difficult to identify key clinical information in a timely manner.
Innovation Solution
A wavefront annotation algorithm that combines bipolar and unipolar ECG signals to detect activation points, using preprocessing stages to remove noise and feature extraction to distinguish between local and far-field activations, followed by a classification algorithm to categorize signals based on activation complexity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional CARTO 3 system methods are used to map and image electrical signals, then the system can process ECG signals, but the accuracy of local activation time classification deteriorates due to interference and signal complexity
Solution Approach 1:
The patent segments the ECG signal analysis into distinct phases: preprocessing stage (noise removal), feature extraction stage (identifying activation points), and classification stage (categorizing signals). This segmentation allows each stage to focus on specific aspects of signal processing, improving overall accuracy by handling complexity in manageable portions.
Solution Approach 2:
The patent extracts key features from the complex ECG signals, specifically identifying activation points through feature extraction algorithms. By taking out and isolating these critical features (activation points, derivatives, ratios), the system can classify signals more accurately without being overwhelmed by the full complexity of the original signals.
2Measurement precision
If manual inspection of ECG signals is performed to identify key clinical information, then accuracy can be maintained, but user time and productivity deteriorate
Solution Approach 1:
The system performs self-service by automatically executing the complete signal processing pipeline: preprocessing, feature extraction, and classification. The algorithm independently identifies activation points and categorizes signals without requiring manual intervention, thereby maintaining accuracy while eliminating the time-consuming manual inspection process.
Solution Approach 2:
The patent replaces the mechanical (manual) inspection process with an automated computational system. The classification algorithm substitutes human analysis with computer-based feature extraction and pattern recognition, achieving both speed and accuracy in identifying clinical information.
3Measurement precision
If complex signal processing algorithms are applied to improve classification accuracy, then measurement precision improves, but device complexity increases
Solution Approach 1:
The complex processing algorithm is segmented into three distinct stages: preprocessing (noise removal), feature extraction (activation point identification), and classification (signal categorization). This segmentation makes the overall complex system more manageable and easier to implement by breaking down complexity into functional modules.
Solution Approach 2:
The patent applies preliminary action through the preprocessing stage, which performs noise removal and signal preparation before the main classification task. By completing these preliminary actions in advance, the subsequent feature extraction and classification stages operate on cleaner, more manageable data, reducing the complexity required for accurate classification.
Data Source
AI summary
A method, including receiving a bipolar signal from a pair of electrodes in proximity to a myocardium of a human subject, and receiving a unipolar signal from a selected one of the pair of electrodes. The method further includes delineating a window of interest (WOI) for the unipolar and bipolar signals, within the WOI computing local unipolar minimum derivatives of the unipolar signal, and times of occurrence of the local unipolar minimum derivatives, and within the WOI computing bipolar derivatives of the bipolar signal at the times of occurrence. The method also includes evaluating ratios of the bipolar derivatives to the local unipolar minimum derivatives, and when the ratios are greater than a preset threshold ratio value, assigning the times of occurrence as times of activation of the myocardium, counting a number of the times of activation; and classifying the unipolar signal according to the number.