Capnography derived breath variability analysis feasibility and its importance for pulmonary embolism prediction

Dorota Zyśko, Konrad Kluwak, Michał Furdal, Przemysław Skoczyński, Grzegorz Gogolewski, Goutam Chourasia, Waldemar Banasiak, Dariusz Jagielski, Ryszard Klempous, Jerzy Rozenblit

Research output: Contribution to journalArticlepeer-review


Capnography is a method that monitors the concentration of Carbon Dioxide (CO2) in patients’ respiratory gases. Its outcome, i.e., the capnographic curve shows CO2 levels plotted against time. The measurement of the carbon dioxide that is released at the end of an exhaled breath is called end-tidal carbon dioxide (etCO2). Such monitoring provides information about CO2 production and clearance. This paper hypothesizes that the capnographic curve could be useful in everyday clinical practice for differential diagnosis. Specifically, a computational analysis method was developed and a pilot study was conducted to determine if capnography can be used as a predictive indicator for Pulmonary Embolism (PE). To verify whether the respiratory pattern may have clinical significance, an assessment was carried out in patients in whom PE was diagnosed and those in whom PE was suspected but ultimately excluded. The age, gender, end-tidal-CO2 (etCO2), respiratory rate, and symptoms at the admission of patients who had a chest CT angiography were noted. Classification and regression tree analysis were designed and used to identify variables predictive for PE. A total of 120 patients (60 female, 60 males) aged 64.3 +/- 18.0 admitted to the Emergency Department had the computed tomography pulmonary angiography imaging study: 60 with positive PE and 60 with negative PE results. In patients with etCO2>=32 mmHg was a negative predictor for PE. In those with the etCO2 < 32 mmHg was predictive for PE. The developed model indicates that it could assist in predicting PE based on the etCO2 values.

Original languageEnglish (US)
Article number104910
JournalBiomedical Signal Processing and Control
StatePublished - Aug 2023


  • Capnography
  • Classification
  • Non-invasive diagnostic methods
  • Pulmonary embolism
  • Pulmonary embolism prediction
  • Regression trees
  • Syncope/presyncope

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Health Informatics


Dive into the research topics of 'Capnography derived breath variability analysis feasibility and its importance for pulmonary embolism prediction'. Together they form a unique fingerprint.

Cite this