What You Should Know
- The Research: A new study published in Mayo Clinic Proceedings: Digital Health by researchers at the Kern Center for the Science of Health Care Delivery reveals that wearable data may help predict patient engagement in remote COPD rehabilitation
- The Core Problem: Patients with Chronic Obstructive Pulmonary Disease (COPD) frequently drop out of remote, 12-week pulmonary rehabilitation programs. Because COPD severely impacts sleep, patients often lack the energy to complete their prescribed exercises.
Decoding the ‘Composite Sleep Health Score’
The study focused on patients with Chronic Obstructive Pulmonary Disease (COPD). COPD causes inflamed, narrowed airways and mucus buildup, making it incredibly difficult to breathe—and by extension, incredibly difficult to sleep. When these patients are sleep-deprived, their energy levels plummet, making them highly unlikely to participate in the rigorous exercise and education required by a 12-week pulmonary rehab program.
“As a scientist and engineer, I wanted to explore how wearable data could improve the drop-out rates of remote pulmonary rehabilitation programs,” noted Dr. Stephanie Zawada, a Mayo Clinic research associate and first author of the study.
To test this, Dr. Zawada and her team strapped wrist activity monitors to patients for a single week prior to the start of their home-based rehab. They used this data to generate a “Composite Sleep Health Score.”
When this wearable-derived score was combined with traditional clinical data and fed into a machine learning model, the predictive accuracy of the algorithm spiked. The model could accurately forecast how engaged a patient would be over the subsequent three months.
