CARDIOVASCULAR RISK ASSESSMENT IN THE ARAL SEA REGION USING ARTIFICIAL INTELLIGENCE MODELS
DOI:
https://doi.org/10.5281/zenodo.23364087Abstract
This study addresses intelligent cardiovascular risk assessment in cardiology inpatients from the Aral Sea region under incomplete and heterogeneous clinical-data conditions and proposes the CR-MRA algorithm as a solution. A retrospective analysis was conducted using anonymized clinical records of 2,039 patients treated at the Nukus City Medical Association during 2024–2026. The data demonstrated a substantial cardiorenal comorbidity burden together with irregular monitoring and heterogeneous clinical documentation. To reduce the influence of noisy clinical data on model decisions, a quality-aware adaptive formalization of CR-MRA (Cardio-Renal Medical Risk-Aware) was proposed. The algorithm combines, for each feature, a data-quality coefficient, data-driven relevance, and a regularized medical prior. The decision threshold is selected on validation data according to the F2-score. Recalculation of the available confusion matrix yielded a test size of N=35,077, with Recall=0.9747, Precision=0.6690, Accuracy=0.7433, Specificity=0.5066, F1=0.7934, and F2=0.8931. The findings indicate promising potential for sensitivity-oriented screening, while multicenter validation is planned to strengthen the evidence.Keywords
artificial intelligence, cardiovascular diseases, patients from the Aral Sea region, CR-MRA algorithm, noisy clinical data, missing data, data quality, Recall, F2-score, screeningReferences
1. Uzokov, J., Alyavi, A., Alyavi, B., & Abdullaev, A. (2024). How artificial intelligence can assist with ischaemic heart disease. European Heart Journal, 45(21), 1866–1868. https://doi.org/10.1093/eurheartj/ehae030
2. Azimova, N. D., Ashirbaev, S. P., & Vikhrov, I. P. (2020). The first steps in artificial intelligence development in medicine in Uzbekistan. Health Problems of Civilization, 14(4), 314–319. https://doi.org/10.5114/hpc.2020.98086
3. Dehkordi, P., Tavakolian, K., Rocco, T., Fozilov, K., Yuldashov, A., Zareba, W., Yuldashov, B., Atamuratov, B., et al. (2026). Electromechanical risk score for coronary artery disease risk estimation using seismocardiography. European Heart Journal. ztag139. DOI: 10.1093/ehjdh/ztag139. https://doi.org/10.1093/ehjdh/ztag139
4. Ronco, C., Haapio, M., House, A. A., et al. (2008). Cardiorenal syndrome. Journal of the American College of Cardiology, 52(19), 1527–1539.
5. Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016:785–794.
6. Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems. 2017;30.
7. Pedregosa, F., Varoquaux, G., Gramfort, A., et al. (2011). Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12, 2825–2830.
8. Saytov, K. B., & Uteuliev, N. U. (2026). CardioAI-DSS: artificial-intelligence-based software for cardiovascular disease risk assessment. Software Certificate No. DGU 67189. Tashkent; 2026. [Original certificate title in Uzbek].
9. Collins, G. S., Moons, K. G. M., Dhiman, P., et al. (2024). TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ. 2024;385:e078378. DOI: 10.1136/bmj-2023-078378. https://doi.org/10.1136/bmj-2023-078378
10. Moons, K. G. M., Damen, J. A. A., Kaul, T., et al. (2025). PROBAST+AI: an updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods. BMJ. 2025;388:e082505. DOI: 10.1136/ bmj-2024-082505. https://doi.org/10.1136/
11. Ulianova, S. (n.d.). Cardiovascular Disease dataset. Kaggle. Dataset containing 70,000 records, 11 features, and a binary cardio target.
Downloads
Published
How to Cite
Issue
Section
