ECG Signal Analysis with ANN Artifact Detection and SQI Validation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing ECG signal analysis systems face challenges in accurately identifying QRS-complexes and calculating heart rates due to noise contamination from artifact signals, leading to false alarms and reduced precision in cardiac condition detection.
Innovation Solution
An apparatus and method using an artificial neural network (ANN) to detect artifact signals in real-time from ECG leads, combined with a signal quality index (SQI) to validate QRS-complexes, ensuring accurate identification and classification even in the presence of artifacts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional ECG signal analysis methods are used, then the system is simple and easy to operate, but the measurement precision and reliability deteriorate due to noise contamination from artifact signals
Solution Approach 1:
The patent segments the ECG signal processing into distinct functional modules: artifact detection module that identifies artifact-containing segments, QRS-complex detection module that processes clean segments, and signal quality assessment module. This segmentation allows each module to specialize in specific tasks, improving overall measurement precision while managing complexity through modular architecture.
Solution Approach 2:
The patent introduces an intermediary artifact detection and validation mechanism that acts as a mediator between the raw ECG signal and the QRS-complex analysis. This intermediary layer identifies and flags artifact-containing segments before they reach the QRS detection algorithm, preventing false detections and improving measurement accuracy.
2Reliability
If artifact detection and validation mechanisms are implemented, then the reliability of ECG analysis improves, but the device complexity and processing time increase
Solution Approach 1:
The patent implements preliminary artifact detection and segment validation before performing QRS-complex analysis. By pre-identifying and flagging artifact-containing segments upfront, the system prevents wasted processing time on invalid data and ensures that only clean, reliable segments undergo detailed QRS detection, thereby improving overall reliability without excessive time loss.
Solution Approach 2:
The patent incorporates feedback mechanisms where the artifact detection module continuously monitors signal quality and provides feedback to the QRS detection module. This feedback loop allows the system to dynamically adjust processing based on real-time signal conditions, maintaining high reliability while optimizing processing time by avoiding unnecessary analysis of corrupted segments.
3Measurement precision
If comprehensive artifact detection is performed, then false alarms are reduced, but the computational resources and processing complexity increase
Solution Approach 1:
The patent applies local quality assessment by evaluating signal characteristics specifically at potential QRS-complex locations rather than uniformly processing the entire ECG signal. The artifact detection and validation mechanisms focus computational resources on critical segments where QRS complexes are likely to occur, improving heart rate calculation accuracy while reducing overall computational energy consumption.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Apparatuses and methods are disclosed for determining artifact signals (caused e.g. by EM interference, patient motion, or cable/ electrode malfunction) from a plurality of sample signals collected during a pre-determined time window from at least one ECG lead configured to be affixed to a patient. The apparatuses and methods select (402) a plurality of sample points from in the sample signals, extract a plurality of features from the selected sample points, and generate (404) a probability of the existence of the artifact signals by applying a transformation process to at least two of the plurality of features. Furthermore, the apparatuses and methods identify (406) a plurality of QRS-complexes, extract (408) one or more features corresponding to the identified QRS-complexes. The apparatuses and methods further generate (410) a signal quality index SQI by comparing the one or more features corresponding to the identified QRS-complexes and determine the artifact signals based on the SQI and the probability.