Validation of a novel approach to identify potential radiologic predictors of myocardial infarction in patients under 50: a pilot study

Cardiovascular diseases (CVDs) continue to be the leading cause of mortality in Russia. Over the past three decades, effective preventive measures have led to a one-third reduction in morbidity rates. However, there remains a significant risk of mortality among patients under 50 years of age who experience acute myocardial infarction (AMI). This highlights the need to identify additional predictors, including radiological features, to enhance prognostic models for CVD. There is an approach suggesting that incorporating low-correlation pairs of features may yield more informative model predictions.

Aim. To evaluate the hypothesis that patients under 50 years of age with AMI exhibit distinct low-correlation pairs of characteristics, as identifi ed by chest computed tomography (CT), compared to patients over 50 years of age with AMI.

Material and methods. This was a retrospective study involving patients who experienced their first AMI and had undergone chest CT 6–12 months prior to the cardiovascular event. Correlation matrices were created for patients under 50 years of age and those over 50. Subsequently, pairs of features with low correlation that were common to all patients were removed from the set of feature pairs for the younger group.

Results. The study included 59 patients, with 12 under the age of 50 and 47 over 50. The groups diff ered in the prevalence of multivessel lesions, the presence of osteoporosis and hydrothorax as assessed by chest CT, and the average aortic size. By constructing correlation matrices and eliminating common feature pairs with weak correlations, we identified 12 unique feature pairs that could enhance existing risk models.

Conclusion. Utilizing radiological markers to improve CVD prognosis shows promise, but further prospective cohort studies with larger sample sizes are necessary to validate these findings.

1. Kakorina E.P., Nikitina S.Y. Features of the structure of mortality in Russian Federation. Problems of Social Hygiene, Public Health and History of Medicine. 2019;27(5):822–826. DOI: https://doi.org/10.32687/0869-866X-2019-27-5-822-826

2. GBD 2016 DALYs and HALE Collaborators. Global, regional, and national disability-adjusted life-years (DALYs) for 333 diseases and injuries and healthy life expectancy (HALE) for 195 countries and territories, 1990–2016: a systematic analysis for the Global Burden of Disease Study 2016. Lancet. 2017;390(10100):1260–1344. DOI: 10.1016/S0140-6736(17)32130-X

3. Gupta A., Wang Y., Spertus J.A., Geda M., Lorenze N., NkondePrice C. et al. Trends in acute myocardial infarction in young patients and diff erences by sex and race, 2001 to 2010. J. Am. Coll. Cardiol. 2014;64(4):337–345. DOI: 10.1016/j.jacc.2014.04.054

4. Faresjö Å., Karlsson J-E., Segerberg H., Lebena A., Faresjö T. Cardiovascular and psychosocial risks among patients below age 50 with acute myocardial infarction. BMC Cardiovasc. Disord. 2023;23(1):121. DOI: 10.1186/s12872-023-03134-w

5. Faresjö T., Strömberg S., Jones M., Stomby A., Karlsson J-E., Östgren C.J., Faresjö Å., Theodorsson E. Elevated levels of cortisol in hair precede acute myocardial infarction. Sci. Rep. 2020;10(1):22456. DOI: https://doi.org/10.1038/s41598-020-80559-9

6. Stomby A., Strömberg S., Theodorsson E., Faresjö Å., Jones M., Faresjö T. Standard modifi able cardiovascular risk factors mediate the association between elevated hair cortisol concentrations and coronary artery disease. Front Cardiovasc. Med. 2022;8:765000. DOI: https://doi.org/10.3389/fcvm.2021.765000

7. Abuzaid A., Saad M., Addoumieh A., Ha L.D., Elbadawi A., Mahmoud A.N. et al. Coronary artery calcium score and risk of cardiovascular events without established coronary artery disease: a systemic review and meta-analysis. Coron. Artery Dis. 2021;32(4):317–328. DOI: 10.1097/MCA.0000000000000974

8. Al-Makhamreh H.K., Toubasi A.A., Al-Harasis L.M., Albustanji F.H., Al-Sayegh T.N., Al-Harasis S.M. Pericardial fat and cardiovascular diseases: A systematic review and meta-analysis. .J Evid. Based Med. 2023;16(2):178–185. DOI: doi: 10.1111/jebm.12542

9. Vasilev YA, Vladzymyrskyy AV, Arzamasov K.M. et al. Computer vision in radiology: stage one of the Moscow experiment – Second edition. Moscow: Publishing Solutions. 2023:388. (In Russ.)]. ISBN 978-5-0059-3043-9

10. Sharova D.E., Garbuk S.V., Vasilyev Y.A. Artificial intelligence systems in clinical medicine: the world’s fi rst series of national standards. Standards and Quality. 2023;(1):46–51. (In Russ.)]. DOI:10.35400/0038-9692-2023-1-304-22

11. Wang T.J. Assessing the role of circulating, genetic, and imaging biomarkers in cardiovascular risk prediction. Circulation. 2011;123(5):551–565. DOI: 10.1161/CIRCULATIONAHA.109.912568

12. Russian Society of Cardiology. [Clinical practice guidelines for Acute ST-segment elevation myocardial infarction. Russian Journal of Cardiology. 2020;25(11):4103. (In Russ.)]. DOI: 10.15829/29/1560-4071-2020-4103

13. Exploring the use of innovative computer vision technologies for analyzing medical images and their future applications in healthcare: offi cial website. (In Russian)]. URL: https://mosmed.ai/ai/

14. Ismaiel A., Popa S.L., Dumitrascu D.L.. Acute coronary syndromes and nonalcoholic fatty liver disease: “Un Aff aire de Coeur”. Can. J. Gastroenterol. Hepatol. 2020;2020(1):8825615. DOI: 10.1155/2020/8825615

15. Brydges C.R. Eff ect size guidelines, sample size calculations, and statistical power in gerontology. Innov. Aging. 2019;3(4):igz036. DOI: 10.1093/geroni/igz036

16. Vasiliev Yu.A., Reshetnikov R.V., Shumskaya Yu.F. et al. (2025). MosMedData: A dataset of clinical data, cardiac ultrasound parameters of patients with acute coronary syndrome at the time of vascular accident and chest computed tomography data 3–12 months prior to AMI development. Certifi cate of State Registration of the Database No. 2025620216, Russian Federation. State Budgetary Institution of Health Care of Moscow, Scientifi c and Practical Clinical Center of Diagnostics and Telemedicine Technologies. (In Russ.)].

17. Ndumele C.E., Matsushita K., Lazo M., Bello N., Blumenthal R.S., Gerstenblith G., Nambi V., Ballantyne C.M., Solomon S.D., Selvin E., Folsom A.R., Coresh J. Obesity and subtypes of incident cardiovascular disease. .J Am. Heart Assoc. 2016;5(8):e003921. DOI: 10.1161/JAHA.116.003921

18. Kang M.Y., Hong Y.C. Inter-correlation between working hours, sleep duration, obesity, and 10-year risk for CHD. Am. J. Ind. Med. 2016;59(4):338–339. DOI: 10.1002/ajim.22525

19. Bisaccia G., Ricci F., Khanji M.Y., Sorella A., Melchiorre E., Iannetti G. et al. Cardiovascular morbidity and mortality related to non-alcoholic fatty liver disease: a systematic review and metaanalysis. Curr. Probl. Cardiol. 2023;48(6):101643. DOI: 10.1016/j.cpcardiol.2023.101643

20. Fan J-G., Saibara T., Chitturi S., Kim B.I., Sung J.J.Y., Chutaputti A., the Asia–Pacifi c Working Party for NAFLD. What are the risk factors and settings for non‐alcoholic fatty liver disease in Asia–Pacifi c? //Journal of gastroenterology and hepatology. J. Gastroenterol. Hepatol. 2007;22(6):794–800. DOI: 10.1111/j.1440-1746.2007.04952.x

21. Vernon G., Baranova A., Younossi Z.M. Systematic review: the epidemiology and natural history of non‐alcoholic fatty liver disease and non‐alcoholic steatohepatitis in adults. Aliment Pharmacol Ther. 2011;34(3):274–285. DOI: 10.1111/j.1365-2036.2011.04724.x

22. Filatova D.A., Mershina E.A., Sinitsyn V.E. COVID-19-related cardiac lesion: The questions of pathogenesis and diagnostics. Digital Diagnostics. 2023;4(2):156−169. (In Russian)]. DOI: 10.17816/DD284706