Use of capnography for prediction of obstruction severity in non-intubated COPD and asthma patients

摘要: Background Capnography waveform contains essential information regarding physiological characteristics of the airway and thus indicative level obstruction. Our aim was to develop a capnography-based, point-of-care tool that can estimate obstruction in patients with asthma COPD. Methods Two prospective observational studies conducted between September 2016 May 2018 at Rabin Medical Center, Israel, included healthy, COPD patient groups. Each underwent spirometry test continuous capnography, as part of, either methacholine challenge for diagnosis or bronchodilator reversibility routine evaluation. Continuous capnography signal, divided into single breaths waveforms, were analyzed identify features, create predictive model FEV1 using an artificial neural network. The gold standard comparison measured spirometry. Measurements main results Overall 160 analyzed. Model prediction 32/88 features three demographic (age, gender height). showed excellent correlation (R = 0.84), R2 achieved 0.7 mean square error 0.13. Conclusion In this study we have developed evaluate patients. Using model, tool, without reliance on cooperation. Moreover, monitoring disease fluctuations, response treatment guide therapy. Trial registration clinical trials.gov, NCT02805114. Registered 17 June 2016, https://clinicaltrials.gov/ct2/show/NCT02805114.