Neural network analysis of the volumetric capnogram to detect pulmonary embolism.

Abstract

BACKGROUND: Pulmonary embolism (PE) produces ventilation/perfusion mismatch that may be manifested in various variables of the volume-based capnogram (VBC). We hypothesized that a neural network (NN) system could detect changes in VBC variables that reflect the presence of a PE. METHODS: A commercial VBC system was used to record multiple respiratory variables from consecutive expiratory breaths. Data from 12 subjects (n = 6 PE+ and n = 6 PE-) were used as input to a fully connected back-propagating NN for model development. The derived model was tested in a prospective, observational study at an urban teaching hospital. Volumetric capnograms were then collected on 53 test subjects: 30 subjects with PE confirmed by pulmonary angiography or diagnostic scintillation lung scan, and 23 subjects without PE based on pulmonary angiography. The derived NN model was applied to VBC data from the test population. RESULTS: Seventeen VBC variables were used by the derived NN model to generate a numeric probability of PE. When the derived NN model was applied to VBC data from the 53 test subjects, PE was detected with a sensitivity of 100% (95% CI = 89% to 100%) and a specificity of 48% (95% CI = 27% to 69%). The likelihood ratio positive [LR(+)] for the VBC-NN test was 1.82 and the LR (-) was 0.1. CONCLUSION: This study demonstrates the feasibility of developing a rapid, noninvasive breath test for diagnosing PE using volumetric capnography and NN analysis.