Screening and Early Warning of Chronic Obstructive Pulmonary Disease Combined With Sleep Respiratory Disease Based on Medical Internet of Things

Summary

Participation Requirements

Description

This study is a multi-center joint study, which mainly consists of two parts. First, a cross-sectional observational study was adopted to recruit patients with stable COPD in multiple centers. The COPD's diagnostic criteria follow diagnostic guidelines in China, and the patients were selected among ...

This study is a multi-center joint study, which mainly consists of two parts. First, a cross-sectional observational study was adopted to recruit patients with stable COPD in multiple centers. The COPD's diagnostic criteria follow diagnostic guidelines in China, and the patients were selected among 40-80 years old. Note that we excluded patients who cannot use IoT's mobile applications and cannot complete sleep monitoring and follow-up visits. All patients collect sleep monitoring information through wearable devices, together with demographic characteristics, pulmonary function tests, blood routines, biochemistry, electrocardiogram, chest radiograph, COPD assessment scale, modified British Medical Research Association dyspnea index, St. George's Quality of Life Questionnaire, Sleep Apnea Clinical Score, Berlin Questionnaire, Epworth Sleepiness Scale, Etc. This study estimates patient health status from the collected information, then diagnoses sleep apnea and calculates sleep apnea prevalence. Specifically, we build standards from the analysis of sleep monitoring information, and we form an OSA screening model by applying machine learning algorithms. Second, we establish a COPD cohort joined with sleep breathing disease, where we select COPD patients meeting the diagnostic criteria for sleep breathing disease. All patients use wearable devices and IoT technology for information collection and data management. We also build the early warning platform, and it allows flexible adjustment on the COPD plan according to individual differences and community differences. This tudy requires followed up visit once a month. By observing the number of hospitalizations, the incidence of acute exacerbations, and other secondary observation indicators of COPD patients, the early warning platform can analyze COPD's acute exacerbations combined with sleep respiratory disease. We develop the disease and prognosis model for COPD patients with SAO by applying machine learning algorithms on the previous platform.

Tracking Information