Assessing the efficiency of the cancer detection algorithms using synthetic data based on machine learning
https://doi.org/10.21122/2309-4923-2025-2-46-53
Abstract
This study analyzes the distribution of real objects and synthetically augmented classes, as well as their impact on machine learning models. The training results of logistic regression, decision trees, random forest, and SVM models on synthetic data were compared with those obtained on a dataset of real objects. Experimental results showe that the use of synthetically augmented data improves the accuracy of classification models, with particularly noticeable improvements observed in some algorithms.
About the Author
Sh. I. Khaydarov
Denau Institute of Entrepreneurship and Pedagogy (DTPI)
Uzbekistan
Uzbekistan
Sherali Islomovich Khaydarov, Lecturer at the Department of Information Technologies.
Republic of Uzbekistan.
References
1. He, H. Learning from imbalanced data / Haibo He, Edwardo A. Garcia // IEEE Transactions on Knowledge and Data Engineering. – 2009. – Vol. 21, Iss. 9. – P. 1263–1284. – DOI: 10.1109/TKDE.2008.239
2. SMOTE: synthetic minority over-sampling technique / N. V. Chawla, K. W. Bowyer, L. O. Hall, W. P. Kegelmeyer // Journal of Artificial Intelligence Research. – 2002. – Vol. 16. – P. 321–357. – DOI: 10.1613/jair.953
3. Generative Adversarial Networks / Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza [et al.] // Proceedings of the 27th International Conference on Neural Information Processing Systems. – 2014. – P. 2672–2680. – DOI: 10.48550/arXiv.1406.2661
4. SMOTE for learning from imbalanced data: progress and challenges, marking the 15-year anniversary / Alberto Fernandez, Salvador Garcia, Francisco Herrera, Nitesh V. Chawla // Journal of Artificial Intelligence Review. – 2018. – Vol. 61. – P. 863–905. – DOI: 10.1613/jair.1.11192
5. Liu, B., Ding, H., & Wang, Y. (2020). "Synthetic Data Augmentation for Medical Diagnosis". IEEE Transactions on Biomedical Engineering.
6. J. Smith, "Medical Classification Systems". Journal of AI in Medicine, 2020.
7. R. Brown, "Heuristic Algorithms in Diagnosis". Medical Informatics Review, 2019.
8. Nishanov, A. Modification of decision rules “ball Apolonia” the problem of classification / A.X. Nishanov, O.B. Ruzibaev, Nguyen H. Tran // 2016 International Conference on Information Science and Communications Technologies (ICISCT). – Tashkent, Uzbekistan, 2016 – DOI: 10.1109/ICISCT.2016.7777382
9. Nishanov, A. Analysis of methodology of rating evaluation of digital economy and e-government development in Uzbekistan / Akhram Khasanovich Nishanov, Saidrasulov Sherzod Norboy o’g’li, Babadjanov Elmurad Satimbaevich // International Journal of Early Childhood Special Education. – 2022. – Vol. 14, iss. 2. – P. 2447–2452. – DOI: 10.9756/INT-JECSE/V14I2.230
10. Algorithm for the selection of informative symptoms in the classification of medical data / A. Kh. Nishanov, O. B. Ruzibaev, J. C. Chedjou [et al.] // Developments of Artificial Intelligence Technologies in Computation and Robotics. – 2020. – P. 647–658. – DOI: 10.1142/9789811223334_0078
11. Nishanov, A.Kh. A decisive rule in classifying diseases of the visual system / A. Kh. Nishanov, A. Kh. Turakulov, Kh. V. Turakhanov // Meditsinskaia tekhnika. – 1999. – Iss. 4, July – August. – P. 16-18. – Article in Russian.
12. Clustering algorithm based on object similarity / A. Kh. Nishanov, V. Kh. Akbarova, A. T. Tursunov [et al.] // Journal of Mathematics, Mechanics and Computer Science. – 2024. – Vol. 123, № 3. – P. 108–120. – DOI: 10.26577/JMMCS2024-v123-i3-4
13. Stages of Preparing Symptoms of Breast Cancer for Machine Learning / Nishanov Akhram Khasanovich, Mamajanov Raxmatilla Yakubjanovich, Xaydarov Sherali Islom o‘g‘li [et al.] // Digital Transformation and Artificial Intelligence. – 2024. – Vol. 2, Iss. 6. – P. 237–249. – DOI: https://dtai.tsue.uz/index.php/dtai/article/view/v2i633
14. Stages of Forming Symptoms Used in the Diagnosis of Endocrine Diseases". / Nishanov Akhram Khasanovich, Mengturayev Farxod Ziyatovich, Allayarov Uktamjon Bektashovich, Xaydarov Sherali Islom o‘g‘li // Digital Transformation and Artificial Intelligence. – 2024. – Vol. 2, № 6. – P. 228–236. – DOI: https://dtai.tsue.uz/index.php/dtai/article/view/v2i632
15. Diagnostic algorithm for early detection of breast cancer based on error minimization approach / Nishanov Akhram Khasanovich, Mamazhanov Rakhmatilla Yakubzhanovich, Khaidarov Sherali Islom o‘g‘li [et al.] // International Journal of Innovative Science and Research Technology (IJISRT). – 2024. – Vol. 9, Iss. 12. – P. 1535–1542. – DOI: 10.5281/zenodo.14565218
16. The Importance of Early Detection of Cancer Diseases and Methods and Algorithms Based on Modern Technologies / Nishanov Akhram Khasanovich, Mamajanov Raxmatilla Yakubjanovich, Xaydarov Sherali Islom o‘g‘li, Mengturayev Farxod Ziyatovich // Digital Transformation and Artificial Intelligence. – 2025. – Vol. 3, № 1. – P. 110–117. – DOI: https://dtai.tsue.uz/index.php/dtai/article/view/v3i117
Review
For citations:
Khaydarov Sh.I. Assessing the efficiency of the cancer detection algorithms using synthetic data based on machine learning. «System analysis and applied information science». 2025;(2):46-53. (In Russ.) https://doi.org/10.21122/2309-4923-2025-2-46-53
Views:
11
Email this article 