Analysis of daily oxygen saturation for detecting deterioration in the condition of COPD patients

Gokalp H., Clarke M.

37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015, Milan, Italy, 25 - 29 August 2015, vol.2015-November, pp.6840-6843 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 2015-November
  • Doi Number: 10.1109/embc.2015.7319964
  • City: Milan
  • Country: Italy
  • Page Numbers: pp.6840-6843
  • Ondokuz Mayıs University Affiliated: No


This study presents a novel threshold algorithm that is applied to daily self-measured SpO2 data for management of COPD patients in remote patient monitoring to improve accuracy of detection of exacerbation. Conventional approaches based on a fixed threshold applied to a single SpO2 reading result in high false alarm rates. We model the SpO2 time series data as a combination of a trend and a stochastic component (residual) and use the standard deviation of residuals to identify exacerbations. Deterioration in the condition of a patient results in an increase in the standard deviation of the residual (σres), from 2% or less when the patient is in a healthy condition to 4% or more when the condition deteriorates. We present results from retrospective analysis of SpO2 data measured in patients with COPD as part of a long term project to monitor frail elderly, and compare results from the new approach with those from the conventional approach.