Seismocardiography-based estimation of hemodynamic parameters during submaximal ergometer test.

Area of Science:

• Biomedical Engineering
• Cardiovascular Physiology
• Wearable Technology

Background:

• Seismocardiography (SCG) records chest vibrations caused by cardiac activity.
• Estimating hemodynamic parameters non-invasively is crucial for cardiovascular health monitoring.
• Previous SCG studies primarily focused on resting conditions, limiting applicability during physical activity.

Purpose of the Study:

• To assess the feasibility of SCG for estimating hemodynamic parameters (SV, HR, CO, cardiac index) during submaximal exercise.
• To evaluate SCG performance across different Body Mass Index (BMI) groups.
• To compare SCG estimation accuracy during exercise, baseline, and post-exercise recovery phases.

Main Methods:

• Sixty healthy adults across four BMI groups underwent a YMCA submaximal cycling test.
• SCG signals were captured using a chest-mounted accelerometer, with transthoracic bioimpedance as reference.
• Subject-specific random forest models utilized SCG time-domain features for hemodynamic parameter estimation.

Main Results:

• SCG signals were successfully acquired throughout all exercise phases.
• Hemodynamic estimation showed condition-dependent reliability, with optimal performance during post-exercise recovery (median R²=0.75 for HR/CO, 0.42 for SV).
• SCG demonstrated limited sensitivity to BMI variations, potentially impacting personalized accuracy.

Conclusions:

• While SCG acquisition is feasible during exercise, reliable hemodynamic estimation is hindered by motion artifacts and physiological variability.
• Post-exercise recovery presents the most suitable phase for SCG-based cardiovascular monitoring.
• SCG shows potential for low-motion or recovery scenarios, requiring further validation with gold-standard methods for active exercise applications.