Real-Time LAT Annotation Correction for Noisy Intra-Cardiac Signals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Intra-cardiac electrocardiogram (iECG) signals are often noisy and prone to errors due to low Signal to Noise Ratio (SNR) and pathological conditions like atrial flutter or atrial fibrillation, complicating the measurement of Local Activation Time (LAT) values.
Innovation Solution
A system that uses signal acquisition circuitry and processing units to analyze intra-cardiac signals from multiple electrodes, employing statistical characteristics to identify and correct statistically deviant LAT values by recalculating using alternative estimates based on predefined deviation measures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If multiple intra-cardiac signals are acquired by multiple electrodes to improve measurement coverage, then the quantity of data increases, but the noise and errors increase due to low Signal to Noise Ratio
Solution Approach 1:
The patent combines multiple intra-cardiac signals from multiple electrodes to generate an ensemble average signal. By merging the signals and averaging them, the system improves the signal-to-noise ratio while maintaining comprehensive measurement coverage across multiple cardiac locations.
Solution Approach 2:
The system implements quality assessment of individual signal annotations and uses this feedback to determine whether to accept or reject specific annotations. Deviant annotations are identified and corrected by replacing them with ensemble average values, creating a feedback loop that continuously improves annotation reliability.
2Productivity
If automatic annotation methods are used to process signals and reduce noise, then processing efficiency increases, but annotation errors occur due to pathological conditions like atrial flutter or fibrillation
Solution Approach 1:
The system automatically assesses the quality of each annotation by comparing it to the ensemble average signal. Annotations that deviate beyond a predefined threshold are automatically identified as erroneous and replaced with corrected values from the ensemble average, providing continuous quality control without manual intervention.
Solution Approach 2:
The system performs self-correction by automatically detecting deviant annotations and replacing them with corrected values derived from the ensemble average. This self-service mechanism allows the system to maintain high annotation accuracy without requiring constant external validation or manual review.
3Reliability
If statistical deviation analysis is applied to identify erroneous annotations, then annotation reliability improves, but processing time increases
Solution Approach 1:
The system pre-calculates the ensemble average signal and its statistical parameters (mean and standard deviation) before performing annotation validation. This preliminary preparation allows for rapid comparison and identification of deviant annotations during real-time processing, minimizing additional processing time.
Solution Approach 2:
The system dynamically adjusts the threshold for identifying deviant annotations based on the statistical characteristics of the ensemble average signal. By adapting the deviation threshold to the specific signal conditions, the system maintains high reliability while optimizing processing efficiency for different pathological states.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A system includes signal acquisition circuitry and a processing unit. The signal acquisition circuitry is configured to receive multiple intra-cardiac signals acquired by multiple electrodes of an intra-cardiac probe in a heart of a patient. The processing unit is configured to select a group of the intra-cardiac signals, extract a respective most-likely annotation value from each of the intra-cardiac signals in the group, in accordance with a likelihood criterion, identify in the group an intra-cardiac signal whose most-likely annotation value is statistically deviant in the group by more than a predefined measure of deviation, extract, from the intra-cardiac signal having the statistically deviant annotation value, at least a second-most-likely annotation value in accordance with the likelihood criterion, and, responsive to a statistical deviation of the second-most-likely annotation value, select a valid annotation value for the corresponding intra-cardiac signal.