Development and testing of new methodical approaches for predicting cardiovascular events in healthy people using machine learning technology based on the «INTEREPID» international research

Close metadata

OBJECTIVE

To develop and test new methodical approaches for predicting cardiovascular events in healthy people using artificial intelligence.

MATERIAL AND METHODS

The study was performed on the basis of «INTEREPID» international research data. The sample consisted of 2.392 thous. participants who have been observed for 4 years, among them 1022 (42.7%) were men, 1369 (57.2%) — women. The analysis included 191 predictors. We used 5 classification algorithms to create prediction models on the Python programming environment: RandomForestClassifier, GradientBoostingClassifier, ExtraTreesClassifier, XGBClassifier, LGBMClassifier. ROC-analysis was used to evaluate the effectiveness of prediction models.

RESULTS

The most effective algorithm was GradientBoostingClassifier with AUC-0.76. The worst result had ExtraTreesClassifier with AUC-0.68. The most significant risk factors were age, C-reactive protein level in the blood and animal fat consumption.

CONCLUSION

As a result of the research we were able to obtain a prediction algorithm with relatively good quality of discrimination. Further studies on larger amount of data are necessary to improve this development.

Keywords:

cardiovascular risk

artificial intelligence

machine learning

cardiovascular diseases prognosis

diseases of circulatory system

Authors:

Mishkin I.A.

National Medical Research Center for Therapy and Preventive Medicine;
Kireevsk Central District Hospital

ORCID: 0000-0003-4850-0648

Kontsevaya A.V.

National Medical Research Center for Therapy and Preventive Medicine

SPIN RSCI: 6787-2500
Scopus AuthorID: 55672262900
ORCID: 0000-0003-2062-1536

Gusev A.V.

Russian Research Institute of Health;
K-SkAI

SPIN RSCI: 168742
Scopus AuthorID: 57222273391
ResearcherID: AAD-2073-2019
ORCID: 0000-0002-7380-8460

Saharov A.A.

Renaissance Insurance Group

Drapkina O.M.

National Medical Research Center for Therapy and Preventive Medicine;
A.I. Yevdokimov Moscow State University of Medicine and Dentistry

SPIN RSCI: 4456-1297
Scopus AuthorID: 57208852308
ResearcherID: G-8443-2016
ORCID: 0000-0002-4453-8430

Received:

13.07.2023

Accepted:

21.09.2023

List of references:

WHO. About Cardiovascular Diseases. Accessed January 07, 2024. https://www.who.int/home/cms-decommissioning
Roth GA, Forouzanfar MH, Moran AE, et al. Demographic and epidemiologic drivers of global cardiovascular mortality. The New England Journal of Medicine. 2015;372(14):1333-1341. https://doi.org/10.1056/NEJMoa1406656
Zabolevaemost’ naseleniya po osnovnym klassam boleznej v 2000—2021 gg. Dannye Minzdrava Rossii, raschet Rosstata. Accessed January 07, 2024. (In Russ.). https://rosstat.gov.ru/storage/mediabank/zdr2-1.xls
Umershie po osnovnym klassam prichin smerti. Rosstat. Accessed January 07, 2024. (In Russ.). https://rosstat.gov.ru/free_doc/new_site/population/demo/dem4_bd.htm
Gusev AV, Kuznetsova TYu, Korsakov IN. Artificial intelligence in risk assessment of cardiovascular diseases. Zhurnal telemediciny i jelektronnogo zdravoohranenija. 2018;3(8):85-90. (In Russ.).
Ukaz Prezidenta Rossijskoj Federacii ot 07.05.2018 g. №204 «O nacional’nyh celyah i strategicheskih zadachah razvitiya Rossijskoj Federacii na period do 2024 goda». Accessed January 07, 2024. (In Russ.). https://www.kremlin.ru/acts/bank/43027
Organizaciya provedeniya profilakticheskogo medicinskogo osmotra i dispanserizacii opredelennyh grupp vzroslogo naseleniya. Metodicheskie rekomendacii po prakticheskoj realizacii prikaza Minzdrava Rossii ot 13 marta 2019 g. №124n «Ob utverzhdenii poryadka provedeniya profilakticheskogo medicinskogo osmotra i dispanserizacii opredelennyh grupp vzroslogo naseleniya». M. 2019. Accessed January 07, 2024. (In Russ.). https://www.garant.ru/products/ipo/prime/doc/72936994/?ysclid=lrki1cvfcr815460192
Belyalov FI. Prognozirovanie i shkaly v medicine. 3-e izd., pererab. i dop. M.: MEDpress-inform; 2020. (In Russ.).
Conroy RM, Pyörälä K, Fitzgerald AP, et al. Estimation of ten-year risk of fatal cardiovascular disease in Europe: the SCORE project. European Heart Journal. 2003;24(11):987-1003. https://doi.org/10.1016/s0195-668x(03)00114-3
SCORE2 working group and ESC Cardiovascular risk collaboration. SCORE2 risk prediction algorithms: new models to estimate 10-year risk of cardiovascular disease in Europe. European Heart Journal. 2021;42(25): 2439-2454. https://doi.org/10.1093/eurheartj/ehab309
Gusev AV, Gavrilov DV, Korsakov IN, et al. Prospects of using machine learning methods to predict cardiovascular diseases. Vrach i informacionnye tehnologii. 2019;(3):41-47. (In Russ.).
Zhang Y, Guo SL, Han LN, Li TL. Application and Exploration of Big Data Mining in Clinical Medicine. Chinese Medical Journal. 2016;129(6): 731-738. https://doi.org/10.4103/0366-6999.178019
Brink H. Real-world Machine Learning. Shelter Island, NY: Manning Publications Co.; 2017.
Mishkin IA, Koncevaya AV, Gusev AV, Drapkina OM. Prediction of cardiovascular events using proportional risk models and machine learning models: a systematic review. Sovremennye problemy zdravoohranenija i medicinskoj statistiki. 2023;(2):804-829. (In Russ.).
Myrzamatova AO, Kontsevaya AV, Polupanov AG, et al. The results of a 7-year prospective follow-up in the intrepid study: factors affecting the overall and cardiovascular mortality of rural residents of Russia and the Kyrgyz Republic. Rossijskij kardiologicheskij zhurnal. 2022;27(5):38-48. (In Russ.). https://doi.org/10.15829/1560-4071-2022-4999
Kontsevaya AV, Myrzamatova AO, Khalmatov AN, et al. Results of the 4year prospective observation in the prospective trial Interepid: factors influencing morbidity and mortality in the population of rural regions of Russia and Kyrgyz Republic. Kardiovaskuljarnaja terapija i profilaktika. 2018;17(2):49-56. (In Russ.). https://doi.org/10.15829/1728-8800-2018-2-49-56
Plekhova NG, Nevzorova VA, Chernenko IN, et al. Prognozirovanie iskhodov i riskov serdechno-sosudistyh zabolevanij s primeneniem mashinnogo obucheniya. Sovremennye dostizheniya himiko-biologicheskih nauk v profilakticheskoj i klinicheskoj medicine: Sbornik nauchnyh trudov Vserossijskoj nauchno-prakticheskoj konferencii s mezhdunarodnym uchastiem, Sankt-Peterburg, 03 dekabrya 2020 goda. Pod red. Silina A.V., Gajkovoj L.B. SPb.: Severo-Zapadnyj gosudarstvennyj medicinskij universitet im. I.I. Mechnikova; 2020;305-309. (In Russ.).
Soboleva AD, Sabinin OYu. Metod kompozicii algoritmov mashinnogo obucheniya na osnove Oracle data mining dlya prognozirovaniya serdechno-sosudistyh zabolevanij. Mashinnoe obuchenie v issledovaniyah mediko-biologicheskih i social’no-ekonomicheskih dannyh: Sbornik nauchnyh trudov. Pod red. Najdenovoj K.A., Shvecova K.V., Yakovleva A.V., Parhomenko V.A. SPb.: Federal’noe gosudarstvennoe avtonomnoe obrazovatel’noe uchrezhdenie vysshego obrazovaniya «Sankt-Peterburgskij politekhnicheskij universitet Petra Velikogo»; 2020;123-162. (In Russ.). https://doi.org/10.18720/SPBPU/2/id20-63
Mishkin IA, Sakharov AA. Studying the use of machine learning algorithms in assessing the risk of developing cardiovascular diseases. Innovacii. Nauka. Obrazovanie. 2020;17:187-202. (In Russ.).
Kim JOR, Jeong YS, Kim JH, et al. Machine Learning-Based Cardiovascular Disease Prediction Model: A Cohort Study on the Korean National Health Insurance Service Health Screening Database. Diagnostics. 2021; 11(6):943. https://doi.org/10.3390/diagnostics11060943
Ward A, Sarraju A, Chung S, et al. Machine learning and atherosclerotic cardiovascular disease risk prediction in a multi-ethnic population. NPJ Digital Medicine. 2020;3:125. https://doi.org/10.1038/s41746-020-00331-1
Jamthikar A, Gupta D, Khanna NN, et al. A low-cost machine learning-based cardiovascular/stroke risk assessment system: integration of conventional factors with image phenotypes. Cardiovascular Diagnosis and Therapy. 2019;9(5):420-430. https://doi.org/10.21037/cdt.2019.09.03
Quesada JA, Lopez-Pineda A, Gil-Guillén VF, et al. Machine learning to predict cardiovascular risk. International Journal of Clinical Practice. 2019; 73(10):e13389. https://doi.org/10.1111/ijcp.13389
Poplin R, Varadarajan AV, Blumer K, et al. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nature Biomedical Engineering. 2018;2(3):158-164. https://doi.org/10.1038/s41551-018-0195-0
Nakanishi R, Slomka PJ, Rios R, et al. Machine Learning Adds to Clinical and CAC Assessments in Predicting 10-Year CHD and CVD Deaths. JACC. Cardiovascular Imaging. 2021;14(3):615-625. https://doi.org/10.1016/j.jcmg.2020.08.024
Eisenberg E, McElhinney PA, Commandeur F, et al. Deep Learning-Based Quantification of Epicardial Adipose Tissue Volume and Attenuation Predicts Major Adverse Cardiovascular Events in Asymptomatic Subjects. Circulation. Cardiovascular Imaging. 2020;13(2):e009829. https://doi.org/10.1161/CIRCIMAGING.119.009829
Commandeur F, Slomka PJ, Goeller M, et al. Machine learning to predict the long-term risk of myocardial infarction and cardiac death based on clinical risk, coronary calcium, and epicardial adipose tissue: a prospective study. Cardiovascular Research. 2020;116(14):2216-2225. https://doi.org/10.1093/cvr/cvz321

Close metadata