Mieloszyk Rebecca J, Verghese George C, Deitch Kenneth, Cooney Brendan, Khalid Abdullah, Mirre-Gonzalez Milciades A, Heldt Thomas, Krauss Baruch S
IEEE Trans Biomed Eng. 2014 Dec;61(12):2882-90. doi: 10.1109/TBME.2014.2332954. Epub 2014 Jun 24.
We develop an approach to quantitative analysis of carbon dioxide concentration in exhaled breath, recorded as a function of time by capnography. The generated waveform--or capnogram--is currently used in clinical practice to establish the presence of respiration as well as determine respiratory rate and end-tidal CO 2 concentration. The capnogram shape also has diagnostic value, but is presently assessed qualitatively, by visual inspection. Prior approaches to quantitatively characterizing the capnogram shape have explored the correlation of various geometric parameters with pulmonary function tests. These studies attempted to characterize the capnogram in normal subjects and patients with cardiopulmonary disease, but no consistent progress was made, and no translation into clinical practice was achieved. We apply automated quantitative analysis to discriminate between chronic obstructive pulmonary disease (COPD) and congestive heart failure (CHF), and between COPD and normal. Capnograms were collected from 30 normal subjects, 56 COPD patients, and 53 CHF patients. We computationally extract four physiologically based capnogram features. Classification on a hold-out test set was performed by an ensemble of classifiers employing quadratic discriminant analysis, designed through cross validation on a labeled training set. Using 80 exhalations of each capnogram record in the test set, performance analysis with bootstrapping yields areas under the receiver operating characteristic (ROC) curve of 0.89 (95% CI: 0.72-0.96) for COPD/CHF classification, and 0.98 (95% CI: 0.82-1.0) for COPD/normal classification. This classification performance is obtained with a run time sufficiently fast for real-time monitoring.
我们开发了一种对呼出气中二氧化碳浓度进行定量分析的方法，该浓度通过二氧化碳描记法记录为时间的函数。所生成的波形——即二氧化碳图——目前在临床实践中用于确定呼吸是否存在以及测定呼吸频率和呼气末二氧化碳浓度。二氧化碳图的形状也具有诊断价值，但目前是通过目视检查进行定性评估。先前对二氧化碳图形状进行定量表征的方法探讨了各种几何参数与肺功能测试之间的相关性。这些研究试图对正常受试者和心肺疾病患者的二氧化碳图进行表征，但未取得一致进展，也未转化为临床实践。我们应用自动定量分析来区分慢性阻塞性肺疾病（COPD）和充血性心力衰竭（CHF），以及区分COPD和正常人。从30名正常受试者、56名COPD患者和53名CHF患者中收集了二氧化碳图。我们通过计算提取了四个基于生理的二氧化碳图特征。在一个留出测试集上的分类是由一组采用二次判别分析的分类器进行的，该分析是通过在一个有标签的训练集上进行交叉验证设计的。在测试集中使用每个二氧化碳图记录的80次呼气，通过自举法进行性能分析，对于COPD/CHF分类，受试者操作特征（ROC）曲线下面积为0.89（95%置信区间：0.72 - 0.96），对于COPD/正常分类，该面积为0.98（95%置信区间：0.82 - 1.0）。这种分类性能是在运行时间足够快以进行实时监测的情况下获得的。
