Prediction of exacerbation onset in chronic obstructive pulmonary disease patients

Abstract

The objective of this study was to develop an algorithm for prediction of exacerbation onset in Chronic Obstructive Pulmonary Disease (COPD) patients based on continuous self-monitoring of physiological parameters from telehome-care monitoring. 151 physiological parameters of COPD patients were monitored on a daily/weekly basis for up to 2 years. Data were segmented in 30-day periods leading up to an exacerbation (exacerbation episode) and starting from a 14-day recovery period post-exacerbation (control episode) and tested in 6 intervals to predict exacerbation onset using k-nearest neighbour (k = 1, 3, 5). A classifier with sensitivity of 73%, specificity of 74%, positive predictive value of 69%, negative predictive value of 78% and an accuracy of 74% was achieved using data intervals consisting of 5 days. Intelligent processing of physiological recordings have potential for predicting exacerbation onset.

Keywords:

• Chronic obstructive pulmonary disease
• disease exacerbation
• decision modelling
• telehome-care

Acknowledgements

We would like to thank the Department of Pulmonary Medicine, Aalborg University Hospital, the COPD patients and their relatives for providing data. We also thank Lone Mylund for assistance and for her work as contact person after the project period ended.

Disclosure statement

The authors report no conflicts of interest. The authors alone are responsible for the content and writing of the paper.

Funding information

This research received no specific grant from any funding agency in the public, commercial or not-for-profit sectors.