Faculty of Medicine-Center for Applied Research on Environment and Health (CIAAS), Autonomous University of San Luis Potosí, Avenida Sierra Leona No. 550, CP 78210, Colonia Lomas Segunda Sección, San Luis Potosí, Mexico.
Department of Pharmacy, Health Sciences Division. University of Quintana Roo, Quintana Roo, Mexico.
Talanta. 2023 May 1;256:124299. doi: 10.1016/j.talanta.2023.124299. Epub 2023 Jan 20.
The objective of this work was to evaluate the use of an electronic nose and chemometric analysis to discriminate global patterns of volatile organic compounds (VOCs) in breath of postCOVID syndrome patients with pulmonary sequelae. A cross-sectional study was performed in two groups, the group 1 were subjects recovered from COVID-19 without lung damage and the group 2 were subjects recovered from COVID-19 with impaired lung function. The VOCs analysis was executed using a Cyranose 320 electronic nose with 32 sensors, applying principal component analysis (PCA), Partial Least Square-Discriminant Analysis, random forest, canonical discriminant analysis (CAP) and the diagnostic power of the test was evaluated using the ROC (Receiver Operating Characteristic) curve. A total of 228 participants were obtained, for the postCOVID group there are 157 and 71 for the control group, the chemometric analysis results indicate in the PCA an 84% explanation of the variability between the groups, the PLS-DA indicates an observable separation between the groups and 10 sensors related to this separation, by random forest, a classification error was obtained for the control group of 0.090 and for the postCOVID group of 0.088 correct classification. The CAP model showed 83.8% of correct classification and the external validation of the model showed 80.1% of correct classification. Sensitivity and specificity reached 88.9% (73.9%-96.9%) and 96.9% (83.7%-99.9%) respectively. It is considered that this technology can be used to establish the starting point in the evaluation of lung damage in postCOVID patients with pulmonary sequelae.
本研究旨在评估电子鼻和化学计量分析在鉴别伴有肺后遗症的新冠后综合征患者呼出气中挥发性有机化合物（VOC）的全球模式中的应用。本研究进行了一项横断面研究，共纳入两组受试者，第 1 组为新冠康复且无肺部损伤的患者，第 2 组为新冠康复且肺功能受损的患者。采用 32 个传感器的 Cyranose 320 型电子鼻进行 VOCs 分析，应用主成分分析（PCA）、偏最小二乘判别分析（PLS-DA）、随机森林、典型判别分析（CAP），并通过 ROC 曲线评估测试的诊断效能。共纳入 228 例受试者，新冠组 157 例，对照组 71 例。化学计量分析结果表明，PCA 可解释 84%的组间变异性，PLS-DA 显示组间存在明显分离，有 10 个传感器与这种分离相关。随机森林分类错误率为对照组 0.090，新冠组 0.088。CAP 模型的正确分类率为 83.8%，模型的外部验证显示正确分类率为 80.1%。敏感性和特异性分别达到 88.9%（73.9%-96.9%）和 96.9%（83.7%-99.9%）。综上所述，该技术可用于评估伴有肺后遗症的新冠后患者的肺部损伤。
