Detection of COPD exacerbations with continuous monitoring of breathing rate and inspiratory amplitude under oxygen therapy.

Abstract

Background: Chronic Obstructive Pulmonary Disease (COPD) is one of the main causes of morbidity and mortality worldwide. Its management represents real economic and public health burdens, accentuated by periods of acute disease deterioration, called exacerbations. Some researchers have studied the interest of monitoring patients' breathing rate as an indicator of exacerbation, although achieving limited sensitivity and/or specificity. In this study, we look to improve the previously described method, by combining breathing variables, using multiple daily measures, and using an artificial intelligence-based novelty detection approach.

Methods: Patients with COPD were monitored with a telemedicine device during their stay in a rehabilitation care center. Daily measures are compared to individually trained reference models based on: i. oxygen therapy duration ii. mean breathing rate, iii. mean inspiratory amplitude, iv. mean breathing rate and mean inspiratory amplitude, v. average distribution of breathing rate and inspiratory amplitude, vi. hidden Markov model (HMM) from a time series of breathing rate and inspiratory amplitude.

Results: A set of 16 recordings with exacerbation and 23 recordings without exacerbation was obtained. When using a daily measure of breathing rate, pre-exacerbation periods were identified with a specificity of 50% and a sensitivity of 55.6%. The method based on daily oxygen therapy usage and the method based on time series obtain a sensitivity of 76.8% and 73.2%, respectively, for a fixed specificity of 50%.

Conclusion: A single daily measure of breathing rate alone is not sufficient for the detection of pre-exacerbation periods. More complete models also achieve limited performance, equivalent to models based on changes in the duration of therapy usage.