New possibilities for predicting the resumption of clinical manifestations of coronary artery disease after endovascular intervention

• Gelena A. Berezovskaya
• Tatiana V. Lazovskaya
• Dmitry A. Tarkhov
• Eduard G. Malev
• Nikolai N. Petrishchev
• Mikhail A. Karpenko

Abstract

Background. Difficulties in predicting the course of coronary artery disease (CAD) after endovascular revascularization are associated with its clinical variety and the physiologic reactions to stent implantation, primarily from the side of hemostasis.

Aim – to study the possibilities of using an artificial neural network for mathematical modeling of the effect of hemostasis disorders on the angina pectoris resumption after endovascular revascularization.

Methods. Venous blood of 66 CAD patients, aged 53 to 75 years, were obtained before primary percutaneous coronary intervention. Hemostasis was assessed using the thrombin generation test. The relationship between changes in the hemostatic system before revascularization and the clinical events during the first year after the intervention was analyzed using a neural network model.

Results. Using mathematical modeling, we obtained a formula for calculating the individual risk coefficient for the recurrence of angina pectoris after revascularization. It was found that the minimum and maximum risks of recurrence for CAD ranged from 0.10 to 3.35 (in 43 patients) and from –0.02 to –4.58 (in 23 patients), respectively.

Conclusion. The likelihood of angina pectoris recurrence within the first year after endovascular revascularization is related to the intensity and rate of thrombin formation before the intervention; it can be calculated using a mathematical model of an artificial neural network.

Keywords:coronary artery disease; endovascular revascularization; thrombin generation test; mathematical model; neural networks

References

1. Garg A., Rout A., Raheja H., et al. Long-term follow-up of percutaneous coronary intervention versus coronary artery bypass grafting in left main coronary artery disease: A systematic review and meta-analysis. Catheter Cardiovasc Interv. 2021; 98 (3): 427–33. DOI: https://www.doi.org/10.1002/ccd.29338

2. Izzo P., Macchi A., De Gennaro L., et al. Recurrent angina after coronary angioplasty: mechanisms, diagnosticand therapeutic options. Eur Heart J Acute Cardiovasc Care. 2012; 1 (2): 158–69.

3. Kamphuisen P.W. Thrombogenicity in patients with percutaneous coronary artery intervention and dual antiplatelet treatment. Eur Heart J. 2008; 29 (14): 1699–700.

4. Schulz B., Pruessmeyer J., Maretzky T., et al. ADAM10 regulates endothelial permeability and T-Cell transmigration by proteolysis of vascular endothelial cadherin. Circ Res. 2008; 102: 1192–201.

5. Siller-Matula J.M., Bayer G., Bergmeister H., et al. An experimental model to study isolated effects of thrombin in vivo. Thromb Res 2010; 126: 454–61.

6. Ku D.D., Zaleski J.K. Receptor mechanism of thrombin-induced endothelium-dependent and endothelium-independent coronary vascular effects in dogs. J. Cardiovasc Pharmacol. 1993; 22: 609–16.

7. Binder B.R. Thrombin is bad, accepted; but is smoking good to prevent restenosis? J Thromb Haemost. 2006; 4 (10): 2188–90.

8. Hemker H.C., Giesen P., Dier R.Al., et al. Саlibrаtеd аutоmаtеd thrоmbin gеnеrаtiоn mеаsurеmеnt in clоtting рlаsmа. Pathophysiol Haemost Thromb. 2003; 33: 4–15.

9. Dargaud Y., Trzeciak M.C., Bordet J.C., et al. Use of calibrated automated thrombinography +/- thrombomodulin to recognize the prothrombotic phenotype. Thromb Haemost. 2006; 96 (5): 562–7.

10. Berezovskaya G.A. Hemostasis disorders and the course of coronary heart disease after endovascular revascularization: Diss. SPb, 2019: 212 p. (in Russian)

11. Berezovskaya G.A., Lazovskaya T.V., Klokova E.S., et al. Method for predicting resumption of coronary heart disease clinical picture by means of neural networks in patients after endovascular intervention. Izobreteniya, poleznye modeli [Inventions, utility models]. 2018; 35. (in Russian)

12. Blagoveshchenskaya E.A., Ryabukhina V.V., Dashkina A.I., et al. Neural network methods for construction of sociodynamic models hierarchy. Lecture Notes in Computer Science. 2016; 9719: 513–20.

13. Filkin V., Kaverzneva T., Lazovskaya T., et al. Neural network modeling of conditions of destruction of wood plank based on measurements. Journal of Physics: Conference Series. 2016; Vol. 772: 012041. DOI: https://www.doi.org/10.1088/1742-6596/772/1/012041

14. Kaverzneva T., Lazovskaya T., Tarkhov D., et al. Neural network modeling of air pollution in tunnels according to indirect measurements. Journal of Physics: Conference Series 772. 2016: 012035. DOI: https://www.doi.org/10.1088/1742-6596/772/1/012035

15. Lazovskaya T.V., Tarkhov D.A., Berezovskaya G.A., et al. Possibilities of neural networks for personalization approaches for prevention of complications after endovascular interventions. In: Cong F., Leung A., Wei Q., eds. Advances in Neural Networks – ISNN 2017: 14^th International Symposium, ISNN 2017, Sapporo, Hakodate, and Muroran, Hokkaido, Japan, June 21–26, 2017, Proceedings, Part I. Cham: Springer International Publishing. 2017: 379–85. DOI: https://www.doi.org/10.1007/978-3-319-59072-1-45

16. Attanasio M., Marcucci R., Gori A.M., et al. Residual thrombin potential predicts cardiovascular death in acute coronary syndrome patients undergoing percutaneous coronary intervention. Thromb. Res. 2016; 147: 52–7. DOI: https://www.doi.org/10.1016/j.thromres.2016.09.020

17. Loeffеn R., Gоdschаlk T.C., vаn Оеrle R., еt al. Тhе hyреrсоаgulable рrоfile of раtients with stеnt thrоmbоsis. Hеаrt. 2015; 101 (14): 1126–32.

18. Souza C., Pizzolato E., Mendes R., et al. Artificial neural networks prognostic evaluation of post-surgery complications in patients underwent to coronary artery bypass graft surgery. International Conference on Machine Learning and Applications, ICMLA 2009, Miami Beach, Florida, USA. 2009: 799–803. DOI: https://www.doi.org/10.1109/ICMLA.2009.116

19. Bonde A., Varadarajan K.M., Bonde N., et al. Assessing the utility of deep neural networks in predicting postoperative surgical complications: a retrospective study. Lancet Digit Health. 2021; 3 (8): e471–e485. DOI: https://www.doi.org/10.1016/S2589-7500(21)00084-4

All articles in our journal are distributed under the Creative Commons Attribution 4.0 International License (CC BY 4.0 license)