Specific Features Of Developing A Predictive Model For Cancer Probability

Karymsakova I.B.; Bekenova D.B.; Kozhakhmetova D.O.; Shyrynkhanova D.Zh.; Bugubayeva A. Zh.; Karmenova M.A.

doi:10.29284/ijasis.12.1s.2026.136-148

Authors

Karymsakova I.B. Graduate School Digital Technologies and Construction, Department of Automation and Information Technologies, Shakarim University, St. Glinka, 20A, Semey 071412, Republic of Kazakhstan
Bekenova D.B. Department of Information Technologies, Higher School of Business and Digital Technologies, University “Turan-Astana”, Y Dukenuly, 29a Street, Astana 010000, Republic of Kazakhstan
Kozhakhmetova D.O. Graduate School Digital Technologies and Construction, Department of Automation and Information Technologies, Shakarim University, St. Glinka, 20A, Semey 071412, Republic of Kazakhstan
Shyrynkhanova D.Zh. School of Digital Technologies and Artificial Intelligence, D. Serikbayev East Kazakhstan Technical University, Boztaeyv Street 17E, Ust-Kamenogorsk 071410, Republic of Kazakhstan
Bugubayeva A. Zh. Department of Digital Engineering and IT-Analytics, Faculty of Finance, Logistics and Digital Technologies, Karaganda University of Kazpotrebsouz, 9 Academic St., Karaganda 100009, Republic of Kazakhstan
Karmenova M.A. Department of Artificial Intelligence and Information Technology, Non-joint-stock company Sarsen Amanzholov East Kazakhstan University, 34 30th Guards Division St., Ust-Kamenogorsk 070002, Republic of Kazakhstan

DOI:

https://doi.org/10.29284/ijasis.12.1s.2026.136-148

Keywords:

intelligent systems; expert system; early cancer diagnosis; neural network; prediction.

Abstract

Cancer remains one of the most lethal diseases worldwide, which makes its early detection a critical public health priority. The development of early diagnostic systems enables timely identification of individuals with a high risk of developing cancer and supports informed clinical decision-making.

In this study, existing approaches to early cancer diagnosis were systematically analyzed. Neural networks were selected as the methodological foundation for designing the expert system. A knowledge base for the expert system was constructed using domain expertise provided by oncology specialists. Key predictors for building a neural-network model were identified. A mathematical model of the system was implemented in the MATLAB environment using three training algorithms: the Levenberg–Marquardt algorithm, Bayesian regularization, and the conjugate-gradient method.

A structural design of an expert-system-based early cancer diagnostic system is proposed. Future research will focus on developing a deep-learning model to achieve higher accuracy in forecasting cancer probability.

References

[1] Morio S. et al. An expert system for early detection of cancer of the breast // Comput. Biol. Med. 1989. Т. 19, № 5. С. 295–305.

[2] (PDF) Development of a Web-Based Fuzzy Expert System for Breast Cancer Risk Assessment [Electronic resource] // ResearchGate. 2025. URL: https://www.researchgate.net/publication/395466148_Development_of_a_Web-Based_Fuzzy_Expert_System_for_Breast_Cancer_Risk_Assessment

[3] Algehyne E. A. et al. Fuzzy Neural Network Expert System with an Improved Gini Index Random Forest-Based Feature Importance Measure Algorithm for Early Diagnosis of Breast Cancer in Saudi Arabia // Big Data Cogn. Comput. 2022. Т. 6, № 1.

[4] Thani I., Kasbe T. Expert system based on fuzzy rules for diagnosing breast cancer // Health Technol. 2022. Т. 12, № 2. С. 473–489.

[5] Liaqat M. S. Fuzzy Soft Set Theory based Expert System for the Risk Assessment in Breast Cancer Patients: arXiv:2511.02392. arXiv, 2025.

[6] Ali M. et al. Breast Cancer Classification through Meta-Learning Ensemble Technique Using Convolution Neural Networks // Diagnostics. 2023. Т. 13. С. 2242.

[7] Guizani S., Guizani N., Gharsallaoui S. A Hybrid CNN-SVM Prediction Approach for Breast Cancer Ultrasound Imaging // 2023 International Wireless Communications and Mobile Computing (IWCMC). 2023. С. 1574–1578.

[8] S S. K. Breast Cancer Classification Using CNN and SVM: A Hybrid Approach // Int. J. Res. Appl. Sci. Eng. Technol. 2025. Т. 13, № 8. С. 889–894.

[9] Aljuaid H. et al. Computer-aided diagnosis for breast cancer classification using deep neural networks and transfer learning // Comput. Methods Programs Biomed. 2022. Т. 223. С. 106951.

[10] Aidossov N. et al. An Integrated Intelligent System for Breast Cancer Detection at Early Stages Using IR Images and Machine Learning Methods with Explainability // SN Comput. Sci. 2023. Т. 4, № 2.

[11] Sharma B. P., Purwar R. K. Computer-Aided Detection and Diagnosis of Breast Cancer: a Review // ADCAIJ Adv. Distrib. Comput. Artif. Intell. J. 2024. Т. 13. С. e31412–e31412.

[12] Karymsakova I. et al. Development of an Early Lung Cancer Diagnosis Method Based on a Neural Network // Computers. 2025. Т. 14, № 9.

[13] Huang H.-Y. et al. A Review of Recent Advances in Computer-Aided Detection Methods Using Hyperspectral Imaging Engineering to Detect Skin Cancer // Cancers. 2023. Т. 15, № 23. С. 5634.

[14] Chima S. et al. Decision support tools to improve cancer diagnostic decision making in primary care: a systematic review // Br. J. Gen. Pract. J. R. Coll. Gen. Pract. 2019. Т. 69, № 689. С. e809–e818.

[15] Pitt E. et al. The effects of cancer clinical decision support systems on patient-reported outcomes: A systematic review // Eur. J. Oncol. Nurs. Off. J. Eur. Oncol. Nurs. Soc. 2023. Т. 66. С. 102398.

[16] Kim S. Y. et al. Cancer signature ensemble integrating cfDNA methylation, copy number, and fragmentation facilitates multi-cancer early detection // Exp. Mol. Med. 2023. Т. 55, № 11. С. 2445–2460.

[17] Hajjar M. et al. Machine Learning Approaches in Multi-Cancer Early Detection // Information. 2024. Т. 15, № 10.

[18] Km B. et al. Multimodal data integration using machine learning improves risk stratification of high-grade serous ovarian cancer. // Nat. Cancer. 2022. Т. 3, № 6. С. 723–733.

[19] Sun Y., Wen B. Machine-learning diagnostic models for ovarian tumors // Heliyon. Elsevier, 2024. Т. 10, № 19.

[20] Geng X. et al. Development of a diagnostic model for ovarian cancer based on machine learning algorithms and functional analysis of key biomarker SOX17 // J. Ovarian Res. 2025. Т. 18, № 1. С. 237.

[21] Schrag D. et al. Blood-based tests for multicancer early detection (PATHFINDER): a prospective cohort study // The Lancet. Elsevier, 2023. Т. 402, № 10409. С. 1251–1260.

[22] Schrag D. et al. 903O A prospective study of a multi-cancer early detection blood test // Ann. Oncol. Elsevier, 2022. Т. 33. С. S961.

[23] Wade R. et al. Multi-cancer early detection tests for general population screening: a systematic literature review. medRxiv, 2024. С. 2024.02.14.24302576.

[24] Khare S. et al. Case Report: Multi-cancer early detection utilizing blood-based genomics: Single-institution case series of novel cancer screening // Front. Oncol. Frontiers, 2025. Т. 15.