Engagement-free and Contactless Bed Occupancy and Vital Signs Monitoring

Area of Science:

• Biomedical Engineering
• Health Informatics
• Signal Processing

Background:

• Contactless vital signs monitoring faces challenges from environmental noise and accurate bed occupancy detection.
• Existing systems often lack robust data quality assessment for real-world applications.

Purpose of the Study:

• To develop and evaluate BedDot, an engagement-free system for contactless vital signs and occupancy monitoring.
• To address limitations in existing contactless monitoring by incorporating robust signal quality assessment.
• To achieve accurate estimation of heart rate (HR), respiration rate (RR), and inter-beat interval (IBI) without physical contact.

Main Methods:

• Developed a signal quality assessment algorithm including bed occupancy, movement, and heartbeat detection.
• Utilized advanced signal processing and Bayesian theorem for contactless HR, RR, and IBI estimation.
• Evaluated the system's performance against an FDA-approved device.

Main Results:

• Achieved over 99% accuracy in bed occupancy detection.
• Demonstrated low mean absolute errors (MAE) for vital signs: 1.38 BPM (HR), 1.54 BPM (RR), and 24.84 ms (IBI).
• Extensive testing with 75 subjects over 80 hours confirmed generalizability across diverse conditions.

Conclusions:

• BedDot provides a robust and accurate solution for contactless vital signs and occupancy monitoring.
• The system's signal quality assessment enhances data reliability in real-world environments.
• BedDot shows significant potential for applications requiring continuous, non-invasive patient monitoring.