Today: Jul 1, 2025
RU / EN
Last update: Jun 30, 2025
Machine Learning Efficiency in Predicting Obstructive Coronary Artery Disease in Patients with Non-ST Elevation Acute Coronary Syndrome in the First Hours of Admission

Machine Learning Efficiency in Predicting Obstructive Coronary Artery Disease in Patients with Non-ST Elevation Acute Coronary Syndrome in the First Hours of Admission

Tsivanyuk M.M., Shakhgeldyan K.I., Markov M.A., Shirobokov V.G., Geltser B.I.
Key words: coronary arteries; obstructive disease; acute coronary syndrome; unstable angina; prognostic models; risk stratification; stochastic gradient boosting.
2025, volume 17, issue 3, page 50.

Full text

html pdf
29
23

The aimof the study was to assess the accuracy of prognostic models for obstructive coronary artery disease (OCAD) in the first hours of admission in patients with non-ST segment elevation acute coronary syndrome (NSTE-ACS).

Materials and Methods. The study involved 610 patients with low- and intermediate-risk NSTE-ACS (Me — 62 years). Based on invasive coronary angiography findings the patients were divided into 2 groups: the first — 363 (59.5%) patients with OCAD (coronary artery luminal occlusion ≥50%), the second — 247 (40.5%) patients without coronary obstruction (<50%). Clinical and functional status was assessed using 62 parameters available at the early hospitalization including: clinical and demographic, anthropometric, laboratory, electrocardiographic and echocardiographic data.

OCAD predictive models were developed using machine learning methods: multifactorial logistic regression, random forest, and stochastic gradient boosting (SGB). The models contained the sets of predictors identified during the initial medical examination in the hospital (the first scenario), after 1-hour observation (the second scenario), and 3 h later (the third scenario). The quality of the models was assessed using six metrics. The impact degree of individual predictors on the study endpoint was determined by the Shapley method of additive explanation (SHAP). OCAD probability stratification was performed by distinguishing the categories of low, medium, high and very high risk.

Results. Based on machine learning methods, OCAD predictive models were developed, among which the best quality metrics were demonstrated by SGB models with the sets of predictors corresponding to three prognostic scenarios (the area under ROC curve: 0.846, 0.887, and 0.949, respectively). Using the SHAP method, we identified the factors with a dominant impact on OCAD, which included the anthropometric indicators (waist circumference, hip circumference, and their ratio) — in the first and second prognostic scenarios; and global longitudinal systolic strain of the left ventricle — in the third scenario. Based on SGB model data there were distinguished the categories of low, medium, high and very high risk of OCAD, their digital ranges depended on the prognostic scenarios.

Conclusion. The prognostic OCAD models developed based on SGB enable to highly accurately assess the degree of coronary damage in NSTE-ACS patients in the first hours of hospitalization. The highest accuracy of OCAD prediction was demonstrated by the models of the third scenario, the structure of which, in addition to anamnestic, anthropometric and ECG data, included clinical and biochemical blood parameters and echocardiographic indicators. Thus, OCAD risk stratification using the mentioned models can be a useful tool in selecting the optimal myocardial revascularization strategy.

  1. Barbarash O.L., Duplyakov D.V., Zateischikov D.A., Panchenko E.P., Shakhnovich R.M., Yavelov I.S., Yakovlev A.N., Abugov S.A., Alekyan B.G., Arkhipov M.V., Vasilieva E.Yu., Galyavich A.S., Ganyukov V.I., Gilyarevskyi S.R., Golubev E.P., Golukhova E.Z., Gratsiansky N.A., Karpov Yu.A., Kosmacheva E.D., Lopatin Yu.M., Markov V.A., Nikulina N.N., Pevzner D.V., Pogosova N.V., Protopopov A.V., Skrypnik D.V., Tereshchenko S.N., Ustyugov S.A., Khripun A.V., Shalaev S.V., Shpektor V.A., Yakushin S.S. 2020 Clinical practice guidelines for acute coronary syndrome without ST segment elevation. Russian Journal of Cardiology 2021; 26(4): 4449, https://doi.org/10.15829/1560-4071-2021-4449.
  2. Byrne R.A., Rossello X., Coughlan J.J., Barbato E., Berry C., Chieffo A., Claeys M.J., Dan G.A., Dweck M.R., Galbraith M., Gilard M., Hinterbuchner L., Jankowska E.A., Jüni P., Kimura T., Kunadian V., Leosdottir M., Lorusso R., Pedretti R.F.E., Rigopoulos A.G., Rubini Gimenez M., Thiele H., Vranckx P., Wassmann S., Wenger N.K., Ibanez B.; ESC Scientific Document Group. 2023 ESC Guidelines for the management of acute coronary syndromes. Eur Heart J 2023; 44(38): 3720–3826, https://doi.org/10.1093/eurheartj/ehad191.
  3. Tsivanyuk M.M., Geltser B.I., Shakhgeldyan K.I., Emtseva E.D., Zavalin G.S., Shekunova O.I. Electrocardiographic, echocardiographic and lipid parameters in predicting obstructive coronary artery disease in patients with non-ST elevation acute coronary syndrome. Russian Journal of Cardiology 2022; 27(6): 5036, https://doi.org/10.15829/1560-4071-2022-5036.
  4. Kuznetsova K.V., Bikbaeva G.R., Sukhinina E.M., Taumova G.Kh., Benyan A.S., Duplyakov D.V., Tukhbatova A.A., Adonina E.V., Kislukhin T.V., Nagornova V.V. Computed tomography angiography or invasive coronary angiography in patients with lowto intermediate risk acute coronary syndrome — a single-center study. Russian Journal of Cardiology 2024; 29(1S): 5702, https://doi.org/10.15829/1560-4071-2024-5702.
  5. Nesova A.K., Ryabov V.V. Paradoxes of non-ST-segment elevation acute coronary in real-life clinical practice settings. Russian Journal of Cardiology 2024; 29(3): 5623, https://doi.org/10.15829/1560-4071-2024-5623.
  6. Kabiri A., Gharin P., Forouzannia S.A., Ahmadzadeh K., Miri R., Yousefifard M. HEART versus GRACE score in predicting the outcomes of patients with acute coronary syndrome; a systematic review and meta-analysis. Arch Acad Emerg Med 2023; 11(1): e50, https://doi.org/10.22037/aaem.v11i1.2001.
  7. Zykov M.V., D’yachenko N.V., Trubnikova O.A., Erlih A.D., Kashtalap V.V., Barbarash O.L. Comorbidity and gender of patients at risk of hospital mortality after emergency percutaneous coronary intervention. Kardiologiia 2020; 60(9): 38–45, https://doi.org/10.18087/cardio.2020.9.n1166.
  8. Tsivanyuk M.M., Geltser B.I., Shakhgeldyan K.I., Vishnevskiy A.A., Shekunova O.I. Parameters of complete blood count, lipid profile and their ratios in predicting obstructive coronary artery disease in patients with non-ST elevation acute coronary syndrome. Russian Journal of Cardiology 2022; 27(8): 5079, https://doi.org/10.15829/1560-4071-2022-5079.
  9. Geltser B.I., Tsivanyuk M.M., Shakhgeldyan K.I., Emtseva E.D., Vishnevskiy A.A. Cardiometabolic risk factors in predicting obstructive coronary artery disease in patients with non-ST-segment elevation acute coronary syndrome. Russian Journal of Cardiology 2021; 26(11): 4494, https://doi.org/10.15829/1560-4071-2021-4494.
  10. Namazi G., Heidar Beygi S., Vahidi M.H., Asa P., Bahmani F., Mafi A., Raygan F. Relationship between red cell distribution width and oxidative stress indexes in patients with coronary artery disease. Rep Biochem Mol Biol 2023; 12(2): 241–250, https://doi.org/10.61186/rbmb.12.2.241.
  11. Chaulin A.M., Grigorieva Yu.V., Pavlova T.V., Duplyakov D.V. Diagnostic significance of complete blood count in cardiovascular patients. Russian Journal of Cardiology 2020; 25(12): 3923, https://doi.org/10.15829/1560-4071-2020-3923.
  12. Nagula P., Karumuri S., Otikunta A.N., Yerrabandi S.R.V. Correlation of red blood cell distribution width with the severity of coronary artery disease — a single center study. Indian Heart J 2017; 69(6): 757–761, https://doi.org/10.1016/j.ihj.2017.04.007.
  13. Zhao Z., Zhang X., Sun T., Huang X., Ma M., Yang S., Zhou Y. Prognostic value of systemic immune-inflammation index in CAD patients: systematic review and meta-analyses. Eur J Clin Invest 2024; 54(2): e14100, https://doi.org/10.1111/eci.14100.
  14. Choi D.H., Kang S.H., Song H. Mean platelet volume: a potential biomarker of the risk and prognosis of heart disease. Korean J Intern Med 2016; 31(6): 1009–1017, https://doi.org/10.3904/kjim.2016.078.
  15. Bekler A., Ozkan M.T., Tenekecioglu E., Gazi E., Yener A.U., Temiz A., Altun B., Barutcu A., Erbag G., Binnetoglu E. Increased platelet distribution width is associated with severity of coronary artery disease in patients with acute coronary syndrome. Angiology 2015; 66(7): 638–643, https://doi.org/10.1177/0003319714545779.
  16. Vogiatzis I., Samaras A., Grigoriadis S., Sdogkos E., Koutsampasopoulos K., Bostanitis I. The mean platelet volume in the prognosis of coronary artery disease severity and risk stratification of acute coronary syndromes. Med Arch 2019; 73(2): 76–80, https://doi.org/10.5455/medarh.2019.73.76-80.
  17. Liou K., Negishi K., Ho S., Russell E.A., Cranney G., Ooi S.Y. Detection of obstructive coronary artery disease using peak systolic global longitudinal strain derived by two-dimensional speckle-tracking: a systematic review and meta-analysis. J Am Soc Echocardiogr 2016; 29(8): 724–735.e4, https://doi.org/10.1016/j.echo.2016.03.002.
  18. Sharma S., Lassen M.C.H., Nielsen A.B., Skaarup K.G., Biering-Sørensen T. The clinical application of longitudinal layer specific strain as a diagnostic and prognostic instrument in ischemic heart diseases: a systematic review and meta-analysis. Front Cardiovasc Med 2023; 10: 980626, https://doi.org/10.3389/fcvm.2023.980626.
Tsivanyuk M.M., Shakhgeldyan K.I., Markov M.A., Shirobokov V.G., Geltser B.I. Machine Learning Efficiency in Predicting Obstructive Coronary Artery Disease in Patients with Non-ST Elevation Acute Coronary Syndrome in the First Hours of Admission. Sovremennye tehnologii v medicine 2025; 17(3): 50, https://doi.org/10.17691/stm2025.17.3.05


Journal in Databases

pubmed_logo.jpg

web_of_science.jpg

scopus.jpg

crossref.jpg

ebsco.jpg

embase.jpg

ulrich.jpg

cyberleninka.jpg

e-library.jpg

lan.jpg

ajd.jpg

SCImago Journal & Country Rank