EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Diagnosis and correlation analysis of lung cancer based on multi-parameter regression of respiratory volatile organic compounds

Lishan Qin, Yunzhen Wang, Fei Wang, Ziyi Zhu, Raojun Luo, Guojun Lv, Haibin Cui

Molecular & Cellular Biomechanics · 2024

DOI: 10.62617/mcb.v21.105 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Molecular & Cellular Biomechanics, 2024. Verfasst von Lishan Qin und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Lung cancer is a prevalent and life-threatening disease worldwide. The primary diagnostic approach for lung cancer is the utilization of low-dose spiral CT scans. However, repeated scans can expose patients to harmful radiation. Consequently, there is growing interest in exploring alternative methods such as the analysis of exhaled volatile organic compounds (VOCs) for lung cancer detection. In this study, we employed a gas chromatography-mass spectrometry analyzer to identify and quantify a total of 108 VOCs of lung cancer patients. Our objective is to investigate the correlation between VOCs in exhaled breath and lung cancer. Through the application of orthogonal partial least squares-discriminant analysis and correlation analysis, we identified several VOCs, including acetone, ethanol, isopropanol, and ethyl acetate, which exhibited a strong association with lung cancer. Unlike the use of a single marker, our study employed a multi-parameter regression method, resulting in superior accuracy. A diagnostic model based on the neural network algorithm was established, demonstrating an accuracy of 93.5% after screening, surpassing the accuracy before screening at 81%. Furthermore, we optimize the model by incorporating the gender factor, leading to an accuracy exceeding 96%. Numerous studies have demonstrated that the analysis of VOCs in exhaled breath holds significant potential for effectively distinguishing lung cancer patients from healthy individuals. These findings emphasize the potential of respiratory analysis as a novel diagnostic tool for early detection of lung cancer.

Zitieren

APA

Qin, L., Wang, Y., Wang, F., Zhu, Z., Luo, R., Lv, G., & Cui, H. (2024). Diagnosis and correlation analysis of lung cancer based on multi-parameter regression of respiratory volatile organic compounds. Molecular & Cellular Biomechanics. https://doi.org/10.62617/mcb.v21.105

Vancouver

Qin L, Wang Y, Wang F, Zhu Z, Luo R, Lv G, et al. Diagnosis and correlation analysis of lung cancer based on multi-parameter regression of respiratory volatile organic compounds. Molecular & Cellular Biomechanics. 2024. doi:10.62617/mcb.v21.105

BibTeX
@article{Qin2024,
  author = {Qin, Lishan and Wang, Yunzhen and Wang, Fei and Zhu, Ziyi and Luo, Raojun and Lv, Guojun and Cui, Haibin},
  title = {Diagnosis and correlation analysis of lung cancer based on multi-parameter regression of respiratory volatile organic compounds},
  journal = {Molecular & Cellular Biomechanics},
  year = {2024},
  doi = {10.62617/mcb.v21.105}
}
Kostenlos starten →