Probabilistic R-Peek Detection in Noisy ECG Signals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for R-peak detection in electrocardiogram (ECG) signals, particularly from wearable textile sensors, face challenges due to low signal-to-noise ratio and motion artifacts, leading to reduced accuracy in detecting R-peaks, which are crucial for heart rate monitoring and disease detection.
Innovation Solution
The probabilistic search method involves signal pre-processing using band-pass filtering and Gaussian kernel smoothing to enhance the signal-to-noise ratio, followed by R-peak detection using a History Dependent Inverse Gaussian distribution to predict the next R-peak and adaptive searching intervals, improving detection accuracy in noisy conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional R-peak detection methods are used on wearable ECG signals, then the detection process is simple, but the detection accuracy is reduced due to low signal-to-noise ratio and motion artifacts
Solution Approach 1:
The patent applies preliminary action by performing signal pre-processing (band-pass filtering and Gaussian kernel smoothing) before R-peak detection to remove motion artifacts and noise. This prepares the signal in advance, making the subsequent detection more accurate despite the presence of harmful factors in wearable ECG signals.
Solution Approach 2:
The patent introduces an intermediary probabilistic search mechanism based on History Dependent Inverse Gaussian distribution between the raw signal and final R-peak detection. This intermediary model predicts probable R-peak locations and guides the search process, improving detection accuracy in noisy conditions by filtering through a probabilistic framework.
2Measurement precision
If probabilistic search method with HDIG distribution is used, then R-peak detection accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent applies local quality by implementing adaptive searching intervals that concentrate computational resources around predicted R-peak locations based on the HDIG distribution. Instead of uniformly processing the entire signal, the method focuses computational effort locally where R-peaks are most likely to occur, improving accuracy while managing complexity.
Solution Approach 2:
The patent uses parameter changes by dynamically adjusting the searching interval parameters based on the probabilistic HDIG distribution. The searching interval adapts its width and position according to the predicted R-peak probability, allowing the system to maintain high detection accuracy while reducing unnecessary computational operations in low-probability regions.
3Measurement precision
If signal pre-processing with filtering and smoothing is applied, then signal-to-noise ratio is enhanced, but processing time increases
Solution Approach 1:
The patent applies partial action by selectively applying pre-processing operations only to signal segments where R-peaks are likely to occur, as predicted by the HDIG distribution. Instead of processing the entire signal uniformly, the method applies filtering and smoothing selectively, enhancing the signal-to-noise ratio where needed while reducing overall processing time.
Data Source
AI summary
According to an aspect there is provided systems, methods, and non-transitory computer readable mediums with instructions for R-peak detection from electrocardiogram (ECG) stored thereon. The method includes pre-processing and smoothing a data stream, detecting R-peaks in an initial time interval, generating a predicted time point of a first new R-peak by predicting a probabilistic distribution of the new R-peak following a last R-peak in the initial time interval with History Dependent Inverse Gaussian (HDIG) distribution, detecting the first new R-peak by searching for the first new R-peak around the predicted time point of the first new R-peak in an adaptive searching interval, detecting remaining R-peaks iteratively, computing heart rate metrics using the detected R-peaks. Peaks with largest amplitudes passing the varying adaptive threshold are detected as the R-peaks. The heart rate metrics being one or more of average heart rate, accuracy, F1-score, sensitivity, precision, and heart rate variability.