Cough Detection Using EGM and Accelerometer Signal Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical devices struggle to accurately detect patient coughs due to noise interference in electrogram signals, which can be misinterpreted as cardiac events, leading to inaccurate monitoring of conditions like COPD.
Innovation Solution
A medical device system that combines electrogram (EGM) signals with accelerometer signals to confirm cough events by analyzing the frontal component of the accelerometer signal, correlating movements with EGM noise to accurately detect coughs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If EGM signal alone is used to detect coughs, then the detection process is simple, but the accuracy is low due to noise interference being misinterpreted as cardiac events
Solution Approach 1:
The patent combines EGM signal analysis with accelerometer signal analysis to detect coughs. The processing circuitry identifies cough-related noise in the EGM signal and cross-references it with corresponding accelerometer data that captures body movements during coughing, thereby improving detection accuracy by merging multiple signal sources.
Solution Approach 2:
The accelerometer signal serves as an intermediary to verify cough events detected in the EGM signal. When cough-related noise is identified in the EGM, the system checks for corresponding movement patterns in the accelerometer data, using the accelerometer as a mediator to confirm whether the EGM noise represents a actual cough or just cardiac activity.
2Reliability
If accelerometer signal analysis is added to confirm coughs, then the accuracy improves, but the processing time and complexity increase
Solution Approach 1:
The system continuously monitors and stores accelerometer data in advance, so when cough-related noise is detected in the EGM signal, the corresponding accelerometer segment is already available for immediate comparison. This preliminary preparation of movement data eliminates the need for additional real-time processing delays.
Solution Approach 2:
Instead of analyzing the entire accelerometer signal continuously, the system only processes and compares the specific time segments that correspond to detected EGM noise events. This partial analysis approach reduces overall processing time while maintaining detection reliability by focusing computational resources only on potential cough events.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
This disclosure is directed to devices, systems, and techniques for detecting one or more coughs in a patient. In some examples, a medical device a medical device includes a plurality of electrodes configured to collect an electrogram (EGM) signal; and an accelerometer configured to collect an accelerometer signal, and processing circuitry. The processing circuitry is configured to identify, in the EGM signal, a segment of the EGM signal, identify, a segment of the accelerometer signal which is collected over a period of time, determine whether a parameter value associated with the segment of the accelerometer signal is greater than a threshold parameter value, and increment, in response to the parameter value associated with the segment of the accelerometer signal being greater than the threshold parameter value, a cough count value.