Artificial intelligence

Abstract: Modern medical analytical systems powered by artificial intelligence (AI) require enhanced reliability, stability, and reproducibility of analytical outcomes. Conventional validation techniques are insufficient for complex hybrid architectures that combine machine learning algorithms, expert-based reasoning, and statistical inference modules. This paper proposes a multi-agent concept for automated validation of medical analytical systems, in which the validation process is realized through the interaction of autonomous agents – Generator, Validator, Evaluator, Data, and Coordinator. The use of generative models as active agents enables the creation of synthetic clinical scenarios, expanding the testing space and allowing evaluation of systems under rare or critical conditions. A mathematical model of the proposed multi-agent dynamics is developed to describe the information exchange and coordination mechanisms among agents, and the convergence of the system toward informational equilibrium is analytically demonstrated. Experimental verification confirms that the proposed approach reduces entropic uncertainty by a factor of three, increases decision stability by 20–25%, and decreases validation time by more than 15 times compared to traditional methods. The obtained results demonstrate the effectiveness of the multi-agent validation framework as a foundation for developing adaptive, self-learning, and transparent quality-control environments for AI-based medical systems.

Keywords: multi-agent systems, validation, artificial intelligence, generative models, medical analytical systems, testing, intelligent agents, digital medicine.

References:

1. Topol, E. (2019). Deep medicine: How artificial intelligence can make healthcare human again. Basic Books.
2. Razzak, M. I., Naz, S., & Zaib, A. (2018). Deep learning for medical image processing: Overview, challenges and the future. Springer, Cham, 323 – 350.
3. Esteva, A. (2018). Artificial intelligence in healthcare and medicine. 239 p.
4. Mahmud, T., Barua, K., Habiba, S. U., Sharmen, N., Hossain, M. S., & Andersson, K. (2024). An explainable AI paradigm for Alzheimer’s diagnosis using deep transfer learning. Diagnostics. https://doi.org/10.3390/diagnostics14030345.
5. Fawaz, A., Mougharbel, I., Al-Haddad, K., & Kanaan, H. Y. (2025). Energy routing protocols for energy Internet: A review on multi-agent systems, metaheuristics, and artificial intelligence approaches. IEEE Access, 19 p.
6. Symonov, D. I., Zaika, B. Yu., & Symonov, Ye. D. (2024). Multivariate regression models for the management of multicomponent dynamic systems. Tavria Scientific Bulletin. Series: Technical Sciences, (6), 106 – 119.
7. Symonov, D. I. (2025). Identification and control of chaotic processes in complex technical systems. Scientific Bulletin of Uzhhorod University. Series “Mathematics and Informatics”, 46(1), 273 – 284.
8. Jrab, D., Eleyan, D., Eleyan, A., & Bejaoui, T. (2024). Heart disease prediction using machine learning algorithms. International Conference on Smart Communications and Networking. https://doi.org/10.1109/SmartNets61466.2024.10577725.
9. Rainio, O., Teuho, J., & Klen, R. (2024). Evaluation metrics and statistical tests for machine learning. Scientific Reports. https://doi.org/10.1038/s41598-024-56706-x.
10. Ogunpola, A., Saeed, F., Basurra, S., Albarrak, A. M., & Qasem, S. N. (2024). Machine learning-based predictive models for detection of cardiovascular diseases. Diagnostics. https://doi.org/10.3390/diagnostics14020144.
11. Wong, K., Ayoub, M., Cao, Z., Chen, C., Chen, W., Ghista, D., & Zhang, C. W. (2023). The synergy of cybernetical intelligence with medical image analysis for deep medicine: A methodological perspective. Computer Methods and Programs in Biomedicine. https://doi.org/10.1016/j.cmpb.2023.107677.
12. Jaber, H. A., Al-Ghali, B. A., Kareem, M. M., Çankaya, I., & Algın, O. (2024). An overview of medical image segmentation methods. Al-Nahrain Journal for Engineering Sciences. https://doi.org/10.29194/njes.28030420.
13. Guo, X., Wang, C., & Liu, L. (2024). Adaptive fault-tolerant control for a class of nonlinear multi-agent systems with multiple unknown time-varying control directions. Automatisierungstechnik. https://doi.org/10.1016/j.automatica.2024.111802.
14. Ren, H., Liu, R., Cheng, Z., Ma, H., & Li, H. (2024). Data-driven event-triggered control for nonlinear multi-agent systems with uniform quantization. IEEE Transactions on Circuits and Systems II: Express Briefs. https://doi.org/10.1109/TCSII.2023.3305946.
15. Hall, V. A. (2024). Coding with ChatGPT and other LLMs. Birmingham: Packt Publishing Ltd.
16. Bluck, A. S. (2023). Practical Java programming with ChatGPT. Delhi: Orange Education Pvt Limited.
17. Bodungen, C. (2024). ChatGPT for cybersecurity cookbook. Birmingham: Packt Publishing Ltd.
18. Herszfang, H. P., & Henstock, P. V. (2025). Supercharged coding with GenAI. Birmingham: Packt Publishing Ltd.