Dynamic Threshold Analysis of Daily Oxygen Saturation for Improved Management of COPD Patients

• Published in: IEEE journal of biomedical and health informatics 2016-09, Vol.20 (5), p.1352-1360
• Main Authors: Clarke, Malcolm, Gokalp, Hulya, Fursse, Joanna, Jones, Russell W.
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Biomedical monitoring; Chronic obstructive pulmonary disease; Deterioration; Dynamic tests; Dynamics; False alarms; Humans; Informatics; Medical treatment; Models, Statistical; Monitoring; Oxygen - blood; Patients; Pulmonary Disease, Chronic Obstructive - diagnosis; Pulmonary Disease, Chronic Obstructive - physiopathology; Pulmonary Disease, Chronic Obstructive - therapy; Remote patient monitoring; Signal Processing, Computer-Assisted; SpO2; telehealth; Telemedicine - methods; Telemetry - methods; Thresholds; Time series analysis; Trends
• ISSN: 2168-2194; 2168-2208
• DOI: 10.1109/JBHI.2015.2464275

This study presents a novel dynamic threshold algorithm that is applied to daily self-measured SpO 2 data for management of chronic obstructive pulmonary disease (COPD) patients in remote patient monitoring to improve accuracy of detection of exacerbation. Conventional approaches based on a fixed threshold applied to a single SpO 2 reading to detect deterioration in patient condition are known to have poor accuracy and result in high false alarm rates. This study develops and evaluates use of a dynamic threshold algorithm to reduce false alarm rates. Daily data from four COPD patients with a record of clinical interventions during the period were selected for analysis. We model the SpO 2 timeseries data as a combination of a trend and a stochastic component (residual). We estimate the long-term trend using a locally weighed least-squares (low-pass) filter over a long-term processing window. Results show that the time evolution of the long-term trend indicated exacerbation with improved accuracy compared to a fixed threshold in our study population. Deterioration in the condition of a patient also resulted in an increase in the standard deviation of the residual (σ res ), from 2% or less when the patient is in a healthy condition to 4% or more when condition deteriorates. Statistical analysis of the residuals showed they had a normal distribution when the condition of the patient was stable but had a long tail on the lower side during deterioration.