RESEARCH OF PERSONALIZED MEDICINE METHODS USING BAYESIAN ANALYSIS

The article is devoted to the research of personalized medicine methods using Bayesian analysis. In modern medicine, one of the most important ways is to make effective decisions taking into account the genetic, clinical and lifestyle characteristics of each patient. In this regard, probabilistic approaches to data analysis in conditions of uncertainty have a special application. The research examines the possibilities of assessing the likelihood of developing diseases and optimizing treatment strategies by combining various sources of medical data. The Bayesian method combines preliminary knowledge and new clinical information. Thus, it allows you to increase the accuracy of diagnosis and assess risks. The study analyzes effective ways to support the medical decision-making process using probabilistic models. At the same time, the practical significance of a personalized approach in medicine is revealed. In particular, the issues of early diagnosis and individualization of treatment are considered. The presented method allows you to improve the quality of medical data processing. Aimed at developing the rules of personalized medicine.

1. Stefanicka-Wojtas D. Personalised medicine – Implementation to the healthcare system in Europe (focus group discussions) / D. Stefanicka-Wojtas, D. Kurpas // Journal of Personalized Medicine. – 2023. – № 13(3). – Р. 380. https://doi.org/10.3390/jpm13030380.

2. Precision medicine – Are we there yet? A narrative review of precision medicine’s applicability in primary care / W. Evans et al // Journal of Personalized Medicine. – 2024. – № 14(4). – Р. 418. https://doi.org/10.3390/jpm14040418.

3. Akhoon N. Precision medicine: A new paradigm in therapeutics / N. Akhoon // International Journal of Preventive Medicine. – 2021. – № 12(1). – Р. 12. https://doi.org/10.4103/ijpvm.IJPVM_375_19.

4. Precision medicine needs randomized clinical trials / E.D. Saad et al // Nature Reviews Clinical Oncology. – 2017. – № 14. – Р. 317-323. https://doi.org/10.1038/nrclinonc.2017.8.

5. Bayesian networks for the diagnosis and prognosis of diseases: A scoping review / K. Polotskaya et al // Machine Learning and Knowledge Extraction. – 2024. – № 6(2). – Р. 1243-1262. https://doi.org/10.3390/make6020058.

6. A comprehensive scoping review of Bayesian networks in healthcare: Past, present and future / E. Kyrimi et al // Artificial Intelligence in Medicine. – 2021. – № 117. – Р. 102108. https://doi.org/10.1016/j.artmed.2021.10210.

7. Collins F.S. A new initiative on precision medicine / F.S. Collins, H. Varmus // New England Journal of Medicine. – 2015. – № 372. – Р. 793-795. https://doi.org/10.1056/NEJMp1500523.

8. Artificial intelligence, healthcare, clinical genomics, and pharmacogenomics approaches in precision medicine / H. Abdelhalim et al // Frontiers in Genetics. – 2022. – № 13. – Р. 929736. https://doi.org/10.3389/fgene.2022.929736.

9. Bayesian Monte Carlo simulation based on systematic review for personalized risk stratification of contralateral lymph node metastasis in oral squamous cell carcinoma / K.N. Rao et al // Diagnostics. – 2025. – № 15(21). – Р. 2668. https://doi.org/10.3390/diagnostics15212668.

10. Ngartera L. Application of Bayesian neural networks in healthcare: Three case studies / L. Ngartera, M.A. Issaka, S. Nadarajah // Machine Learning and Knowledge Extraction. – 2024. – № 6(4). – Р. 2639-2658. https://doi.org/10.3390/make6040127.

11. Improving individualized treatment decisions: A Bayesian multivariate hierarchical model for developing a treatment benefit index using mixed types of outcomes / D. Wu et al // medRxiv (Preprint). – 2024. https://doi.org/10.1101/2023.11.17.23298711.

12. Vinnat V. Bayesian sequential design for identifying and ranking effective patient subgroups in precision medicine in the case of counting outcome data with inflated zeros / V. Vinnat, D. Annane, S. Chevret // Journal of Personalized Medicine. – 2023. – № 13(11). – Р. 1560. https://doi.org/10.3390/jpm13111560.

13. Advancing personalized medicine through the application of whole exome sequencing and big data analytics / P. Suwinski et al // Frontiers in Genetics. – 2019. – № 10. – Р. 49. https://doi.org/10.3389/fgene.2019.00049.

14. From real-world data to causally interpretable models: A Bayesian network to predict cardiovascular diseases in adolescents and young adults with breast cancer / A. Bernasconi et al // Cancers. – 2024. – № 16(21). – Р. 3643. https://doi.org/10.3390/cancers16213643.

15. AI-driven Bayesian deep learning for lung cancer prediction: Precision decision support in big data health informatics / N. Amasiadi et al // BioMedInformatics. – 2025. – № 5(3). – Р. 39. https://doi.org/10.3390/biomedinformatics5030039.

16. Collet P. Potential impact of updated Bayesian deduction in medicine: Application to colonoscopy prioritization / P. Collet, F. Quezada-Diaz, C. Taramasco // Cancers. – 2025. – № 17(23). – Р. 3845. https://doi.org/10.3390/cancers17233845.

17. Application of Bayesian network and regression method in treatment cost prediction / L.-L. Tong et al // BMC Medical Informatics and Decision Making. – 2021. – № 21. – Р. 284. https://doi.org/10.1186/s12911-021-01647-y.

18. Qiu Y. A randomized Bayesian phase I–II dose optimization design for combination cancer therapies with progression-free survival end point / Y. Qiu, M. Li // BMC Medical Research Methodology. – 2025. – № 25(1). – Р. 214. https://doi.org/10.1186/s12874-025-02665-4.