PPG-based algorithm achieves 98.93% accuracy in detecting device wear status with negligible battery impact, eliminating the critical problem of misclassifying patient stillness as non-compliance in continuous monitoring applications.
Simulation evidence supporting continuous, automated monitoring as a superior approach for clinical research.
A study demonstrating the use of synchronized wearables to determine when a cough monitor detects non-user coughs
Addressing privacy risks in clinical trials - edge computing and on-device cough analytics safeguard participant privacy, ensure regulatory compliance, and optimize clinical trial scalability.
16.10.2024
This paper presents a data-driven argument for extending the standard cough monitoring period to seven days, significantly longer than the conventional 24-hour period. This conclusion is grounded in statistical analysis derived from large-scale continuous cough monitoring, which offers insights into the frequency and variability of coughing over time.
The document addresses the significant limitations of historic cough research, which could not rely on comprehensive data due to technological constraints. With the advent of advanced cough monitoring tools, researchers now have access to vast datasets of coughs, which allow for more detailed analyses of coughing patterns.
A key insight is that daily cough rates, traditionally used in studies, do not conform to standard statistical distributions. However, hourly cough counts exhibit more predictable behavior. This breakthrough allows for realistic simulations of cough patterns, which are used to model 504 hours of coughing for over 20 million simulated subjects.
Through this simulation, the study determined that for most subjects, a seven-day monitoring period provides reliable estimates of hourly cough averages and variances.
The paper emphasizes that the variability in cough frequency both across and within individuals makes seven days a more accurate standard for most cases.
Key Insights:
