Prognostic value of angiographic and inflammatory parameters in non ST-segment elevation acute coronary syndrome based on real-world data

Background. The relevance of real-world data is promising for prognosis, as it represents the entire spectrum of patients with their individual characteristics, including comorbidities, which are often not included in clinical studies. The application of machine learning methods has the potential to enhance the prognostic value; the availability of a substantial amount of data allows to perform cross-validation and confirm results. Objective. To identify clinically relevant laboratory and angiographic markers that are associated with an unfavourable out-come in patients with non-ST-segment elevation acute coronary syndrome (NSTE-ACS). Design and methods. A total of 2348 medical records of patients diagnosed with acute coronary syndrome were analyzed. Factors evaluated included the disease course, risk factors and comorbidity, as well as laboratory and instrumental investigations. A logistic regression model was developed using a cross-validation approach. Results. The analysis revealed a number of risk factors for unfavourable course of NSTE-ACS, including angiographic factors (such as left main coronary artery stenosis or chronic coronary artery occlusion) and laboratory factors (haemoglobin level, MPV, monocyte count and SII index). A prognostic model was developed to assess the risk of in-hospital mortality, demonstrating optimal accuracy, sensitivity and specificity. Conclusion. The data obtained support the prognostic value of indicators derived from routine clinical examination in prediction of in-hospital mortality in patients with NSTE-ACS.

1. Demandt JPA, Zelis JM, Koks A, et al. Prehospital risk assessment in patients suspected of non-ST-segment elevation acute coronary syndrome: a systematic review and meta-analysis. BMJ Open. 2022;12(4):e057305. DOI:10.1136/bmjopen-2021-057305.

2. Riehle L, Maier B, Behrens S, et al. Changes in treatment for NSTEMI in women and the elderly over the past 16 years in a large real-world population. Int J Cardiol. 2020;316:7–12. DOI:10.1016/j.ijcard.2020.04.021.

3. Tsivanyuk MM, Geltser BI, Shakhgeldyan KI, et al. 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. In Russian DOI:10.15829/1560-4071-2022-5079.

4. Chaulin AM, Grigorieva YuV, Pavlova TV, Duplyakov DV. Diagnostic significance of complete blood count in cardiovascular patients; Samara State Medical University. Russian Journal of Cardiology. 2020;25(12):3923. In Russian DOI:10.15829/1560-4071-2020-3923.

5. Dentali F, Nigro O, Squizzato A, et al. Impact of neutrophils to lymphocytes ratio on major clinical outcomes in patients with acute coronary syndromes: A systematic review and meta-analysis of the literature. Int J Cardiol. 2018;266:31–37. DOI:10.1016/j.ijcard.2018.02.116.

6. Oylumlu M, Oylumlu M, Arslan B, et al. Platelet-to-lymphocyte ratio is a predictor of long-term mortality in patients with acute coronary syndrome. Advances in Interventional Cardiology/Postępy w Kardiologii Interwencyjnej. 2020;16(2):170–176. DOI: 10.5114/AIC.2020.95859.

7. Xia Y, Xia C, Wu L, et al. Systemic Immune Inflammation Index (SII), System Inflammation Response Index (SIRI) and Risk of All-Cause Mortality and Cardiovascular Mortality: A 20-Year Follow-Up Cohort Study of 42,875 US Adults. Journal of Clinical Medicine. 2023;12(3):1128. DOI:10.3390/jcm1203112.

8. Hassan N, Slight R, Morgan G, et al. Road map for clinicians to develop and evaluate AI predictive models to inform clinical decision-making. BMJ Health Care Inform. 2023;30(1):e100784. DOI:10.1136/bmjhci-2023-100784.

9. Hunter DJ, Holmes C. Where Medical Statistics Meets Artificial Intelligence. N Engl J Med. 2023;389(13):1211–1219. DOI:10.1056/NEJMra2212850.

10. D’Ascenzo F, De Filippo O, Gallone G, et al. Machine learning-based prediction of adverse events following an acute coronary syndrome (PRAISE): a modelling study of pooled datasets. Lancet. 2021;397(10270):199–207. DOI:10.1016/S0140-6736(20)32519-8.

11. Kwon JM, Jeon KH, Kim HM, et al. Deep-learning-based risk stratification for mortality of patients with acute myocardial infarction. PLoS One. 2019;14(10):e0224502. Published 2019 Oct 31. DOI:10.1371/journal.pone.0224502.

12. Zhao Y, Hao C, Bo X, et al. The prognostic value of admission lymphocyte-to-monocyte ratio in critically ill patients with acute myocardial infarction. BMC Cardiovasc Disord. 2022;22:308. https://doi.org/10.1186/s12872-022-02745-z

13. Neverova YuN, Tarasov RS, Nagirnyak OA. Main predictors of in-hospital adverse outcomes in non-ST elevation acute coronary syndrome patients with multivessel disease. Cardiovascular Therapy and Prevention. 2018;17(4):19–25. In Russian DOI:10.15829/1728-8800-2018-4-19-25.

14. Pavlov NA,AndreychenkoAE, VladzymyrskyyAV, et al. Reference medical datasets (MosMedData) for independent external evaluation of algorithms based on artificial intelligence in diagnostics. Digital Diagnostics. 2021;2(1):49−65. In Russian DOI:10.17816/DD60635.