Myocardial infarction (MI) remains one of the leading causes of mortality and disability worldwide, which necessitates accurate and timely assessment of the risk of adverse outcomes. Modern clinical practice uses a number of prognostic scales, including TIMI, GRACE, PURSUIT, and HEART, each of which has proven effectiveness but also certain limitations related to narrow focus, complexity of calculation, or lack of dynamic reassessment of the patient's condition.

This paper presents an extended analysis of existing risk assessment scales for myocardial infarction, compares them, and proposes a scoring scale—the Myocardial Infarction Grading Scale (MIGS)—that integrates clinical, symptomatic, laboratory, and instrumental indicators. A mathematical model based on a weighted sum of risk factors with logistic transformation has been developed for MIGS, allowing quantitative assessment of the likelihood of complications and fatal outcomes. Examples of scoring calculations for various clinical scenarios are presented, as well as a graphical visualization of the dependence of the probability of complications on the total MIGS score.

It is shown that the scale has advantages over traditional tools due to its comprehensive approach, dynamic monitoring capabilities, and integration into digital clinical systems. The results obtained indicate the feasibility of using MIGS in inpatient and emergency cardiology practice to improve the accuracy of risk stratification and personalization of treatment tactics.

myocardial infarction; risk stratification; prognostic scales; TIMI; GRACE; PURSUIT; HEART; scoring scale; mathematical model; probability of complications; clinical prediction; digital cardiology.

Yusuf S. et al. Effect of potentially modifiable risk factors associated with myocardial infarction in 52 countries (the INTERHEART study): Case-control study // The Lancet. – 2021. – Vol. 364, No. 9438. – P. 937–952.

Antman E. M. et al. The TIMI risk score for unstable angina/non–ST elevation MI: A method for prognostication and therapeutic decision making // JAMA. – 2000 (updated 2025). – Vol. 284, No. 7. – P. 835–842.

Fox K. A. et al. Prediction of risk of death and myocardial infarction in the six months after presentation with acute coronary syndrome: Prospective multinational observational study (GRACE) // BMJ. – 2006 (reprinted 2020). – Vol. 333, No. 7578. – P. 1091.

Backus B. E. et al. A prospective validation of the HEART score for chest pain patients at the emergency department // International Journal of Cardiology. – 2013. – Vol. 168, No. 3. – P. 2153–2158.

Wang X. et al. Novel grading system for ischemia-reperfusion injury // Scientific Reports. – 2022. – Vol. 12. – No. 24019-6.

Islam M. M. et al. Cardiovascular risk prediction and influencing predictors using machine learning // PLOS ONE. – 2025. – Vol. 20, No. 3. – P. e0333913.

Al-Zaiti S. S. et al. Machine learning for ECG diagnosis and risk stratification // Nature Medicine. – 2023. – Vol. 29. – P. 1531–1541.

Rao S. S. Thrombolysis In Myocardial Infarction Risk Score [Electronic resource] // StatPearls. – NCBI, 2023. – Access mode: https://www.ncbi.nlm.nih.gov/books/NBK556069/ (date of access: 21.01.2026).

Morrow D. A. et al. TIMI risk score for ST-elevation myocardial infarction: A convenient, bedside, clinical score for risk assessment at presentation // Circulation. – 2000 (updated 2023). – Vol. 102, No. 17. – P. 2031–2037.

Eagle K. A. et al. A validated prediction model for all forms of acute coronary syndrome: Estimating the risk of 6-month post-discharge death in an international registry // JAMA. – 2004 (reprinted 2021). – Vol. 291, No. 22. – P. 2727–2733.

HEART Score for Predicting Adverse Outcomes // American Family Physician. – 2018. – Vol. 98, No. 2. – P. 72–77.

Comparison of GRACE, HEART and TIMI Scores in Predicting MACE [Electronic resource] // Global Medical Congress. – 2025. – Access mode: https://globemcc.com/articles/comparison-of-grace-heart-and-timi-scores (date of access: 21.01.2026).

Wenzl F. A. et al. Extension of the GRACE score for non-ST-elevation acute coronary syndromes // JACC: Cardiovascular Interventions. – 2025. – Vol. 18, No. 5. – P. 1–12.

Johnson K. W. et al. Artificial intelligence in cardiology // Journal of the American College of Cardiology. – 2020. – Vol. 71, No. 23. – P. 2668–2679.

GRACE score for acute coronary syndrome (ACS) [Electronic resource] // Evidencio. – 2023. – Access mode: https://www.evidencio.com/models/show/1028 (date of access: 21.01.2026).

AI approaches for predicting progression to acute coronary syndrome // Nature Cardiovascular Research. – 2025. – DOI: 10.1038/s44325-025-00094-2.

Russian Journal on ACS Risks // Cardiology. – 2025. – Vol. 83. – P. 285–291.

NT-proBNP Cut-off Values for Risk Stratification in Acute MI [Electronic resource] // JAPSC Journal. – 2022. – Access mode: https://www.japscjournal.com/articles/nt-probnp-cut-values-risk-stratification-acute-mi (date of access: 21.01.2026).

Schellings D. A. A. M. et al. Predictive value of NT-proBNP for 30-day mortality in NSTE-ACS [Electronic resource] // DovePress. – 2016. – Access mode: https://www.dovepress.com/predictive-value-of-nt-probnp-for-30-day-mortality-in-patients-with-n-peer-reviewed-fulltext-article (date of access: 21.01.2026).

Granger C. B. et al. Biomarkers in ACS prognosis // Circulation. – 2017. – Vol. 135, No. 10. – P. 1015–1027.

Al-Zaiti S. S. Machine learning model for OMI // Nature Medicine. – 2023. – DOI: 10.1038/s41591-023-02396-3.

Wenzl F. A. GRACE 3.0 sex-specific model // JACC: Cardiovascular Interventions. – 2025. – DOI: 10.1016/S2589-7500(25)00089-5.

Islam M. M. XGBoost for CVD prediction // PLOS ONE. – 2025. – DOI: 10.1371/journal.pone.0333913.

Yuldashev B. E. Information technologies as a strategic factor in the modernization of pediatrician training // Bulletin of the Association of Pulmonologists of Central Asia. – 2025. – Vol. 8, No. 3. – P. 285–291.