Neural networks in the diagnosis of malignant neoplasms by exhaled air | Vestnik Tomskogo gosudarstvennogo universiteta. Upravlenie, vychislitelnaja tehnika i informatika – Tomsk State University Journal of Control and Computer Science. 2025. № 73. DOI: 10.17223/19988605/73/14

Neural networks in the diagnosis of malignant neoplasms by exhaled air

The results of a study the set of neural network architectures with variable learning parameters for processing data from gas-analytical medical devices designed for noninvasive diagnosis of lung and upper respiratory tract cancer are considered. The algorithm provides structuring of the input pattern format for the neural network, taking into account the criterion of maximum information in the input data. Diagnostic data from gas-analytical medical devices are arrays of integer values of codes from analog-to-digital converters. The neural network data processing algorithm is implemented in the Python programming language. The study used digitized exhaled air samples from 154 people. For cases of separate differentiation of healthy volunteers, patients with lung and upper respiratory tract cancers, the neural network data processing algorithm showed an average accuracy exceeding 86%. Contribution of the authors: the authors contributed equally to this article. The authors declare no conflicts of interests.

Download file

Counter downloads: 12

Keywords

data processing, classifier, artificial neural network, neural network architecture, input data format, input data optimization, learning parameters, differentiation feature, classifier efficiency

Authors

Name	Organization	E-mail
Obkhodskiy Artem V.	National Research Tomsk Polytechnic University	art707@yandex.ru
Kulbakin Denis E.	Cancer Research Institute, Tomsk National Research Medical Center of the Russian Academy of Sciences	kulbakin_d@mail.ru
Obkhodskaya Elena V.	National Research Tomsk State University	fil330a@yandex.ru
Lakonkin Vladislav S.	National Research Tomsk Polytechnic University; Cancer Research Institute, Tomsk National Research Medical Center of the Russian Academy of Sciences	vsl13@tpu.ru
Rodionov Evgeniy O.	Cancer Research Institute, Tomsk National Research Medical Center of the Russian Academy of Sciences; Siberian State Medical University	rodionov_eo@oncology.tomsk.ru
Sachkov Victor I.	National Research Tomsk State University	vicsachkov@gmail.com
Chernov Vladimir I.	Cancer Research Institute, Tomsk National Research Medical Center of the Russian Academy of Sciences	chernov@tnimc.ru
Choynzonov Evgeny L.	Cancer Research Institute, Tomsk National Research Medical Center of the Russian Academy of Sciences	choynzonov@tnimc.ru

Всего: 8

References

Kumar A. et al. Revolutionizing healthcare with 5G and AI: Integrating emerging technologies for personalized care and cancer management // Intelligent Hospital. 2025. V. 1 (1). Art. 100005. P. 1-10. doi: 10.1016/j.inhs.2025.100005.

Peng K. et al. Image Segmentation Network for Laparoscopic Surgery // Biomimetic Intelligence and Robotics. 2025. V. 5. P. 1-12 doi: 10.1016/j.birob.2025.100236.

Paithankar V., Devnani D., Nimburkar T.A. A Review Article on “AI-Guided Discovery of Novel Antiinflammatory Agents for Cancer Therapy: A New Era in Drug Development” // Intelligent Hospital. 2025. V. 1 (1). Art. 100007. doi: 10.1016/j.inhs.2025.100007.

Feng S., Yin X., Shen Y. Artificial intelligence powered precision: Unveiling the tumor microenvironment for a new frontier in personalized cancer therapy // Intelligent Medicine. 2025. V. 5. P. 95-98. doi: 10.1016/j.imed.2025.02.001.

Zhang L. et al. Osteosarcoma knowledge graph question answering system: deep learning-based knowledge graph and large language model fusion // Intelligent Medicine. 2025. V. 5. P. 99-110. doi: 10.1016/j.imed.2024.12.001.

Asadi O., Hajihosseini M., Shirzadi S. et al. Improvement of classification accuracy of functional near-infrared spectroscopy signals for hand motion and motor imagery using a common spatial pattern algorithm // Intelligent Medicine. 2025. V. 5. P. 123-131. doi: 10.1016/j.imed.2024.05.004.

Feng Y. et al. Application of artificial intelligence-based computer vision methods in liver diseases: a bibliometric analysis // Intelligent Medicine. 2025. V. 5. P. 111-122. doi: 10.1016/j.imed.2024.09.008.

Li T. et al. Application of multimodal deep learning in the auxiliary diagnosis and treatment of dermatological diseases // Intelligent Medicine. 2025. V. 5. P. 132-140. doi: 10.1016/j.imed.2024.10.002.

Ram U.S., Pogue J.A., Soike M. et al. Assessing quantitative performance and expert review of multiple deep learning-based frameworks for computed tomography-based abdominal organ auto-segmentation // Intelligent Oncology. 2025. V. 1. P. 160-171. doi: 10.1016/j.intonc.2025.03.003.

Wang S., Guo X., Ma J. et al. AWCDL: Automatic weight calibration deep learning for detecting HER2 status in whole-slide breast cancer image // Intelligent Oncology. 2025. V. 1. P. 128-138. doi: 10.1016/j.intonc.2025.03.008.

Adeoye J., Su Y. Deep learning with data transformation improves cancer risk prediction in oral precancerous conditions // Intelligent Medicine. 2025. V. 5. P. 141-150. doi: 10.1016/j.imed.2024.11.003.

Chen X., Xiang J., Lu S. et al. Evaluating large language models and agents in healthcare: key challenges in clinical applications // Intelligient Medicine. 2025. V. 5. P. 151-163. doi: 10.1016/j.imed.2025.03.002.

Wei M., Teh B.S., Xu B. The new paradigm for global oncologists in the era of generative AI // Intelligent Oncology. 2025. V. 1. P. 189-192. doi: 10.1016/j.intonc.2025.06.002.

Cai W. DeepSeek AI: Transforming medical AI with cost-efficiency, transparency, and privacy preservation // Intelligent Oncology. 2025. V. 1. P. 172-175. doi: 10.1016/j.intonc.2025.03.006.

Chernov V.I., Choynzonov E.L., Kulbakin D.E., Obkhodskaya E.V., Obkhodskiy A.V., Popov A.S., Sachkova A.S., Sachkov V.I. Cancer Diagnosis by Neural Network Analysis of Data from Semiconductor Sensors // Diagnostics. 2020. V. 10 (9). Art. 677. doi: 10.3390/diagnostics10090677.

Обходский А.В., Обходская Е.В., Кульбакин Д.Е., Чойнзонов Е.Л., Родионов Е.О., Сачков В.И., Чернов В.И., Попов А.С. Программный комплекс нейросетевой классификации данных газоаналитического обследования дыхательной системы // Вестник Томского государственного университета. Управление, вычислительная техника и информатика. 2024. № 69. С. 112-123. doi: 10.17223/19988605/69/12.

Сорокоумова Д.А., Корелин О.Н., Сорокоумов А.В. Построение и обучение нейронной сети для решения задачи распознавания речи // Труды Нижегородского государственного технического университета им. Р. Е. Алексеева. 2015. № 3 (110). С. 77-84.

Maaten van der L.J.P., Hinton G.E. Visualizing High-Dimensional Data Using t-SNE // J. of Machine Learning Research. 2008. V. 9. P. 2579-2605.

Sokolova М., Japkowicz N., Szpakowicz S. Beyond Accuracy, F-Score and ROC: A Family of Discriminant Measures for Performance Evaluation // Advances in Artificial Intelligence. 2006. V. 4304. P. 1015-1021.