Coronary heart disease (CHD) remains one of the leading causes of mortality worldwide. The strategy of early detection of patients with high risk of coronary artery atherosclerosis using machine learning (ML) methods to develop predictive models of CHD is a promising one. The aim of the study: to investigate the association of serum concentrations of a complex of laboratory markers with the severity of atherosclerotic lesion in patients with CHD by developing and optimizing an ML model. Material and Methods. 220 patients with confirmed CHD (according to coronary angiography with SYNTAX Score calculation) were included in the study. The following biomarkers were evaluated: CRP, TNF-α, ESM-1, sEng, Bcl2, Bax, p53, TRAIL, GDF-15, NRG1. Model development was performed with Statistica software (Statsoft, Inc., USA) using the Automated Neural Networks module. Results. The best prediction accuracy was demonstrated by the multilayer perseptron (MLP) 12-5-3 model (training accuracy – 98.71%, testing accuracy – 93.75%, validation score – 93.75%). Sensitivity analysis showed that GDF-15, p53, Bcl2/Bax, and ESM-1 were the most significant predictors of significant and severe atherosclerosis. Discussion. The results confirm the efficacy of MLP in the diagnosis of coronary artery atherosclerosis, allowing us to take into account nonlinear biomarker interactions. The use of biomarkers specific to key aspects of atherosclerosis pathogenesis allowed us to achieve higher classification accuracy, to estimate the significance of each of the indicators in the context of prognostic accuracy. Conclusion. ML methods, in particular MLP, can be an effective tool for predicting coronary artery atherosclerosis severity. Future research will focus on increasing the amount of data, testing the model on heterogeneous patient cohorts.
coronary heart disease, coronary artery atherosclerosis, biomarkers, artificial neural networks, machine learning, multilayer perseptron, risk prediction, apoptosis, inflammation.
1. Federal State Statistics Service. official statistics. Healthcare in Russia, 2023. URL: https://rosstat.gov.ru/storage/mediabank/Zdravoohran-2023. pdf (Accessed February 24, 2025). (In Russ.).
2. World Health Organization. World Health Statistics 2016. URL: https://www.who.int/ publications/i/item/9789241565264 (Accessed February 24, 2025).
3. Haruna A. A., Muhammad L. J., Yahaya B. Z., Garba E. J., Oye N. D., Jung L. T. An improved C4.5 data mining driven algorithm for the diagnosis of coronary artery disease. 2019 International Conference on Digitization (ICD);
4. Ravi D., Wong C., Deligianni F., et al. Deep Learning for Health Informatics. IEEE J Biomed Health Inform. 2017;21(1):4-21. doihttps://doi.org/10.1109/JBHI.2016.2636665
5. Battineni G., Sagaro G.G., Chinatalapudi N., Amenta F. Applications of Machine Learning Predictive Models in the Chronic Disease Diagnosis. Journal of Personalized Medicine. 2020;10(2):21. doihttps://doi.org/10.3390/jpm10020021.
6. Onishchenko P. S., Klyshnikov K. U., Ovcharenko E. A. Artificial Neural Networks in Cardiology: Analysis of Numerical and Text Data Mathematical Biology and Bioinformatics 2020;15(1):40-56. (In Russ.).
7. Sun X., Yin Y., Yang Q., et al. Artificial intelligence in cardiovascular diseases: diagnostic and therapeutic perspectives. Eur J Med Res. 2023;28(1):242. doihttps://doi.org/10.1186/s40001-023-01065-y.
8. Krittanawong C., Virk H.U.H, Bangalore S., et al. Machine learning prediction in cardiovascular diseases: a meta-analysis. Sci Rep. 2020;10(1):16057. doihttps://doi.org/10.1038/s41598-020-72685-1.
9. Mohd Faizal A. S., Thevarajah T. M., Khor S. M., Chang S. W. A review of risk prediction models in cardiovascular disease: conventional approach vs. artificial intelligent approach. Comput Methods Programs Biomed. 2021
10. Dipto I., Islam T., Rahman H., Rahman M. Comparison of different machine learning algorithms for the prediction of coronary artery disease. J Data Anal Inf Process. 2020;8(2):41-68. doi:10.4236/ jdaip.2020.82003.
11. Kurt I., Ture M., Kurum A.T. Comparing performances of logistic regression, classification and regression tree, and neural networks for predicting coronary artery disease. Expert Syst Appl. 2008;34(1):366-374.
12. Zakharyan E. A., Gritskevich O. Yu., Ibragimova R. E., Grigoriev P. E. Correlation of Serum Endocan Level With Apoptosis Indicators and Severity of Atherosclerotic Lesions of Coronary Arteries in Patients With Coronary
13. Zakharyan E. A. Interrelation of growth/ differentiation factor-15 level with laboratory and clinical and functional parameters of patients with coronary artery disease. Cardiovascular Therapy and Prevention. 2023;22(5):3549.
14. Zakharyan E. A., Fomochkina I. I. Relationship between apoptosis markers and the severity of coronary atherosclerosis and clinical and paraclinical characteristics of patients with coronary artery disease. Russian Journal of
15. Vadlamudi A., Talasila S., Althaph B., Challa N.P., Vadlamudi G.A. Optimizing Multilayer Perceptron classifiers for predictive heart disease diagnosis: A hyperparameter tuning approach. 2024 8th International Conference on
16. Gavrilov D. V., Serova L. M., Korsakov I. N., et al. Cardiovascular diseases prediction by integrated risk factors assessment by means of machine learning. The Doctor. 2020;31(5):41-6. doihttps://doi.org/10.29296/25877305-2020-05-08.
17. Atkov O. Y., Gorokhova S. G., Sboev A. G., et al. Coronary heart disease diagnosis by artificial neural networks including genetic polymorphisms and clinical parameters. J Cardiol. 2012;59(2):190194.
