Lung cancer diagnosis based on the analysis of volatile markers in exhaled breath

Aim. To evaluate the diagnostic accuracy of a developed gas analysis sensor system combined with neural network algorithms for detecting lung cancer based on volatile organic compounds in exhaled breath.

Materials and methods. The study group included 53 exhaled breath samples from patients with morphologically confirmed stage I–IV lung cancer. The control group (n = 47) consisted of individuals with no history or prior diagnostic findings of cancers at the time of enrollment. The study was conducted using the developed Multisensory Gas Analysis System, comprising an array of semiconductor sensors and implementing neural network data processing algorithms.

Results. The experimental results of classifying lung cancer patients and healthy volunteers demonstrated distinct differences in the exhaled breath samples. The system achieved the accuracy of 95.8%, sensitivity of 98.1%, and specificity of 93.6%. In a series of experiments with balanced stage distribution (stages I–II vs. stages III–IV), the mean classification accuracy was 75%, with sensitivity and specificity ranging from 65 to 80%. Both prepped and non-prepped patients showed comparable results, confirming the reproducibility of the method. The accuracy level of 75% allowed for the differentiation between earlyand late-stage disease samples.

Conclusion. The developed system demonstrates high diagnostic performance, surpassing existing methods, including low-dose computed tomography. The findings support the potential of this technology for both early detection and staging of lung cancer.

1. Миллер С.В., Фролова И.Г., Величко С.А., Тузиков С.А., Байдала П.Г., Полищук Т.В. и др. Одиночные округлые образования в легком, тактика ведения. Бюллетень сибирской медицины. 2012;11(S1):80–82.

2. Bray F., Laversanne M., Sung H., Ferlay J., Siegel R.L., Soerjomataram I. et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J. Clin. 2024;74(3):229–263. DOI:10.3322/caac.21834.

3. Binson V.A., Thomas S., Subramoniam M. Non-invasive detection of early-stage lung cancer through exhaled breath volatile organic compound analysis. Med. Gas. Res. 2025;15(2):198– 199. DOI: 10.4103/mgr.MEDGASRES-D-24-00101.

4. Binson V.A., Mathew P., Thomas S., Mathew L. Detection of lung cancer and stages via breath analysis using a self-made electronic nose device. Expert. Rev. Mol. Diagn. 2024;24(4):341–353. DOI: 10.1080/14737159.2024.2316755.

5. Buma A.I.G., Muntinghe-Wagenaar M.B., van der Noort V., de Vries R., Schuurbiers M.M.F., Sterk P.J. et al. Lung cancer detection by electronic nose analysis of exhaled breath: a multicentre prospective external validation study. Ann. Oncol. 2025;31:S0923-7534(25)00125-5. DOI: 10.1016/j.annonc.2025.03.013.

6. Van der Sar I.G., Wijbenga N., Nakshbandi G., Aerts J.G.J.V., Manintveld O.C., Wijsenbeek M.S. et al. The smell of lung disease: a review of the current status of electronic nose technology. Respir. Res. 2021;22(1):246. DOI: 10.1186/s12931-021-01835-4.

7. Лактионов К.К., Артамонова Е.В., Борисова Т.Н., Бредер В.В., Бычков Ю.М., Владимирова Л.Ю. и др. Злокачественное новообразование бронхов и легкого. Современная онкология. 2022;24(3):269–304. DOI: 10.26442/18151434.2022.3.201848.

8. Chernov V.I., Choynzonov E.L., Kulbakin D.E., Menkova E.N., Obkhodskaya E.V., Obkhodskiy A.V. et al. Non-invasive diagnosis of malignancies based on the analysis of markers in exhaled air. Diagnostics. 2020;10(11):934. DOI: 10.3390/diagnostics10110934.

9. Van der Maaten L.J.P., Hinton G.E. Visualizing high-dimensional data using t-SNE. J. Machine Learning Res. 2008;9:2579–2605.

10. Hunger T., Wanka-Pail E., Brix G., Griebel J. Lung Cancer Screening with Low-Dose CT in Smokers: A Systematic Review and Meta-Analysis. Diagnostics. 2021;11(6):1040. DOI: 10.3390/diagnostics11061040.

11. Wolf A.M.D., Oeffinger K.C., Shih T.Y., Walter L.C., Church T.R., Fontham E.T.H. et al. Screening for lung cancer: 2023 guideline update from the American Cancer Society. CA Cancer J. Clin. 2024;74(1):50–81. DOI: 10.3322/caac.21811.

12. Jonas D.E., Reuland D.S., Reddy S.M., Nagle M., Clark S.D., Weber R.P. et al. Screening for Lung Cancer With LowDose Computed Tomography: Updated Evidence Report and Systematic Review for the US Preventive Services Task Force. JAMA. 2021;325(10):971–987. DOI: 10.1001/jama.2021.0377. PMID: 33687468.

13. Rocco G., Pennazza G., Tan K.S., Vanstraelen S., Santonico M., Corba R.J. et al. A real-world assessment of stage i lung cancer through electronic nose technology. J. Thorac. Oncol. 2024;19(9):1272–1283. DOI: 10.1016/j.jtho.2024.05.006.

14. Ng X.J.K., Mohd Khairuddin A.S., Liu H.C., Loh T.C., Tan J.L., Khor S.M. et al. Artificial intelligence-assisted point-of-care devices for lung cancer. Clin. Chim. Acta. 2025;570:120191. DOI: 10.1016/j.cca.2025.120191.