Personalized Detection of Motion Artifacts for Telemonitoring Applications
Noemi Giordano1, Samanta Rosati1, Daniele Fortunato1
1Department of Electronics and Telecommunication, Politecnico di Torino, Italy.
Studies in Health Technology and Informatics
|May 24, 2024
Summary
This study introduces a new method for detecting motion artifacts in wearable device data, improving the accuracy of chronic disease monitoring. The personalized approach enhances the reliability of cardiac time interval assessments.
Area of Science:
- Biomedical Engineering
- Signal Processing
- Remote Patient Monitoring
Background:
- Telemonitoring offers personalized chronic disease management through signal-derived biomarkers.
- Ensuring data reliability requires rigorous quality assessment, especially concerning motion artifacts in wearable recordings.
Purpose of the Study:
- To develop a fully automated and personalized method for detecting motion artifacts in multimodal recordings for Cardiac Time Intervals (CTIs) monitoring.
- To enhance the robustness and reliability of telemonitoring systems for chronic disease management.
Main Methods:
- Utilized template matching with a personalized template for motion artifact detection.
- Applied the method to multimodal recordings for assessing Cardiac Time Intervals (CTIs).
Main Results:
- Achieved a balanced accuracy of 86% in detecting motion artifacts.
- Demonstrated a reduction in the variability of estimated CTIs by at least 17%.
Conclusions:
- The proposed personalized motion artifact detection method significantly improves the robustness of CTI assessment.
- This approach supports the reliable use of telemonitoring in wearable systems for chronic disease management.
