Segmentation and classification of capnograms: application in respiratory variability analysis

Abstract

Variability analysis of respiratory waveforms has been shown to provide key insights into respiratory physiology and has been used successfully to predict clinical outcomes. The current standard for quality assessment of the capnogram signal relies on a visual analysis performed by an expert in order to identify waveform artifacts. Automated processing of capnograms is desirable in order to extract clinically useful features over extended periods of time in a patient monitoring environment. However, the proper interpretation of capnogram derived features depends upon the quality of the underlying waveform. In addition, the comparison of capnogram datasets across studies requires a more practical approach than a visual analysis and selection of high-quality breath data. This paper describes a system that automatically extracts breath-by-breath features from capnograms and estimates the quality of individual breaths derived from them. Segmented capnogram breaths were presented to expert annotators, who labeled the individual physiological breaths into normal and multiple abnormal breath types. All abnormal breath types were aggregated into the abnormal class for the purpose of this manuscript, with respiratory variability analysis as the end-application. A database of 11,526 breaths from over 300 patients was created, comprising around 35% abnormal breaths. Several simple classifiers were trained through a stratified repeated ten-fold cross-validation and tested on an unseen portion of the labeled breath database, using a subset of 15 features derived from each breath curve. Decision Tree, K-Nearest Neighbors (KNN) and Naive Bayes classifiers were close in terms of performance (AUC of 90%, 89% and 88% respectively), while using 7, 4 and 5 breath features, respectively. When compared to airflow derived timings, the 95% confidence interval on the mean difference in interbreath intervals was ± 0.18 s. This breath classification system provides a fast and robust pre-processing of continuous respiratory waveforms, thereby ensuring reliable variability analysis of breath-by-breath parameter time series.

New volumetric capnography-derived parameter: a potentially valuable tool for detecting hyperventilation during cardiopulmonary resuscitation in a porcine model

“…Second, we used healthy animals, which may not represent the conditions leading to CA, since in clinical resuscitation, most patients with CA have underlying pathologies. Third, a clean capnogram was difficult to obtain during CPR because of numerous issues (device malfunction, leakage/occlusion of ventilation circuit, and ongoing CC effort) (9,25). The accuracy of our results may be related to the analysis of data from an animal model.…”

“…Hyperventilation may be caused by an excessive respiratory rate (RR), high tidal volume (VT), or a combination of both. However, capnography focuses on RR monitoring, both visually and automatically (9,10).…”

Current methodological and technical limitations of time and volumetric capnography in newborns

“…3. In healthy adult lungs, CO 2 concentration rapidly increases during phase II because the upper airways contribute negligibly to gas exchange and sophisticated techniques were developed to evaluate and classify time-based and volumetric capnograms [39, 40]. In neonates, airway diameters are much smaller and the ratios of inner surface area and volume per unit length are much higher than in adults, resulting in gas exchange between gas and tissue in the airways.…”

Waveform Capnography for Monitoring Ventilation during Cardiopulmonary Resuscitation: The Problem of Chest Compression Artifact

“…All phases of the respiratory cycle must by identifiable during CPR, and the measurement of ETCO 2 should be possible. However, issues related to the capnograph as well as to the ongoing resuscitation efforts may distort the waveform capnography [29,31,32]. Moreover, the appearance of fast oscillations induced in the waveform capnography at different rates and with varying amplitude has been reported in several studies [33][34][35], often completely distorting the real tracing of the respiratory cycle as shown in Figure 4b.…”