Chronic obstructive pulmonary disease (COPD) is a common and life-threatening lung condition responsible for approximately three million deaths worldwide each year. The disease poses a substantial burden not only on individuals but also on healthcare systems. In the European Union, COPD accounts for 56% of annual healthcare costs related to respiratory diseases, equating to 38.6 billion euros.
A significant portion of these costs arises from the worsening of disease symptoms urging frequent (re)hospitalizations. These hospitalizations are typically triggered by flare-ups, also known as acute exacerbations of COPD (AECOPD). Such flare-ups often have a multifactorial origin e.g. bacterial or viral airway infection) and demand timely medical intervention to mitigate their impact.
AECOPD adversely affects the patient's health status, accelerates the decline in lung function, worsens prognosis, and significantly diminishes quality of life. Therefore, early detection of exacerbations is essential to prevent further disease progression and reduce hospital admissions.
Mobile health (mHealth) presents a promising solution for monitoring COPD patients at home remotely. Currently, the health of COPD patients outside of the hospital remains largely unmonitored-a "black box." By using wearable mobile technology to measure multiple parameters (e.g. oxygen saturation, respiratory rate, etc), it may become possible to predict disease worsening early and enable timely intervention. Previous studies have highlighted that monitoring peripheral oxygen saturation (SpO2) and respiratory rate can be useful in predicting AECOPD, but predicting algorithms are still lacking.
In this clinical study, following parameters will be monitored: physical activity, continuous heart rate, respiratory rate \& breaths per minute, SpO2, sleep patterns, and core body temperature using a wearable mobile device. These parameters will be tracked from when patients are admitted to the emergency room (ER) until three months after hospital discharge or until rehospitalization due to AECOPD. The data collected will be used to gain insight in the COPD progression following an AECOPD event and construct a prediction model capable of forecasting disease deterioration. This model could enable timely medical intervention in the future, potentially preventing hospitalizations and improving patient outcomes.
