Feasibility study of a sensor-based autonomous load control exercise training system for COPD patients

Area of Science:

• Pulmonary Rehabilitation
• Medical Decision Support Systems
• Biomedical Engineering

Background:

• Chronic Obstructive Pulmonary Disease (COPD) rehabilitation traditionally occurs in clinical settings.
• Automated Decision Support Systems (DSSs) offer a novel approach to supervised physical exercise training.
• Integrating DSSs into rehabilitation can enhance patient autonomy and accessibility.

Purpose of the Study:

• To evaluate the feasibility of a rule-based DSS for autonomous bicycle ergometer training in COPD patients.
• To assess the safety and patient satisfaction with automated exercise load control.
• To explore the potential of DSSs for facilitating home-based COPD rehabilitation.

Main Methods:

• A rule-based DSS was developed for autonomous bicycle ergometer training.
• Real-time sensor data (oxygen saturation, heart rate) informed load control.
• Ten COPD patients completed 18 training sessions, with system performance and patient feedback recorded.

Main Results:

• The DSS successfully managed training loads (31-47 W) based on physiological parameters.
• An average of 7.4 rules were activated per session, indicating dynamic system response.
• Patients reported high satisfaction and a mean Borg value of 12.6±2.4, with 45.9% and 41.6% of heart rate readings within target zones.

Conclusions:

• The rule-based DSS is a feasible tool for autonomous bicycle ergometer training in COPD patients.
• Automated control based on physiological data appears safe and well-tolerated.
• This technology holds promise for enabling COPD rehabilitation in home environments, potentially improving long-term adherence and outcomes.