The Use of Artificial Intelligence in Predicting Cardiovascular Events in High-Risk Patients
Main Article Content
http://orcid.org/0000-0002-1871-4605
Adelcio Machado dos Santos
http://orcid.org/0000-0003-3916-972X
Maria Eugênia Paula Pires
http://orcid.org/0000-0003-4459-3509
Maria Iranilda Silva Magalhães
http://orcid.org/0000-0001-6121-8984
Abstract
The article aims to explore the potential of artificial intelligence in predicting cardiovascular events in high-risk patients, by reviewing studies recent studies and the discussion of the advantages and limitations of artificial intelligence techniques in this area. The systematic review included 12 studies that addressed the application of artificial intelligence algorithms to predict cardiovascular events in high-risk patients, such as those with a prior history of cardiovascular disease, hypertension, or diabetes. The studies used a variety of data sources, including medical imaging, clinical data, and genomic information. The results showed that artificial intelligence algorithms were significantly more accurate than traditional cardiovascular risk prediction models, especially in identifying patients at high risk of cardiovascular events. However, the studies also highlighted some limitations in the application of artificial intelligence, such as the need for large training datasets and the lack of transparency in the interpretation of results. The studies also evaluated the performance of different artificial intelligence algorithms, including artificial neural networks, decision trees and reinforcement learning algorithms. Although the results were variable, in general, neural network algorithms showed the best accuracy in predicting cardiovascular events. Patients' characteristics were also evaluated in the studies, and it was observed that clinical variables such as age, sex, blood pressure and cholesterol were the main predictors of cardiovascular events. The inclusion of genomic data also showed potential to improve prediction accuracy. Finally, the review discussed the advantages and limitations of artificial intelligence in predicting cardiovascular events in high-risk patients. Although artificial intelligence has significant potential to improve prediction accuracy, its implementation in clinical practice must take into account the limitations of algorithms and the need for transparency in the interpretation of results. In summary, the review highlights the potential of artificial intelligence in predicting cardiovascular events in high-risk patients, but also underscores the importance of a careful approach in its implementation in clinical practice.
Article Details
The Medical Research Archives grants authors the right to publish and reproduce the unrevised contribution in whole or in part at any time and in any form for any scholarly non-commercial purpose with the condition that all publications of the contribution include a full citation to the journal as published by the Medical Research Archives.
References
2. Gurevich P, Shargorodsky M. Artificial intelligence and machine learning in cardiovascular medicine. Isr Med Assoc J. 2020;22(2):105-108. PMID: 32043375.
3. Poulson M, Marks JR, Wang S, et al. Applying machine learning to facilitate risk-stratified screening for carotid artery stenosis. J Vasc Surg. 2020;72(5):1582-1590.e5. doi:10.1016/j.jvs.2019.10.058
4. Shouval R, Hadanny A, Shlomo N, et al. Utilizing machine learning algorithms to predict the occurrence of cardiovascular disease events in patients with diabetes mellitus. J Diabetes Res. 2020;2020:6781935. doi:10.1155/2020/6781935
5. Wang X, Zou B, Zhou Q, et al. Development and validation of a prognostic model based on artificial intelligence for major adverse cardiovascular events among patients with coronary artery disease. JAMA Netw Open. 2019;2(7):e197042. doi:10.1001/jamanetworkopen.2019.7042
6. Hannun AY, Rajpurkar P, Haghpanahi M, et al. Cardiologist-level arrhythmia detection with convolutional neural networks. arXiv. 2017. arXiv:1707.01836
7. Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019;25(1):44-56. doi:10.1038/s41591-018-0300-7
8. Singh R, Kalra MK, Nitiwarangkul C, Patti JA, Homayounieh F, Padole A. Artificial intelligence in cardiovascular imaging: state of the art and implications for the imaging cardiologist. JACC Cardiovasc Imaging. 2020;13(6):1367-1387. doi:10.1016/j.jcmg.2020.01.007
9. Ge Z, Wu Y, Gao Y, et al. Deep learning for diagnosis of chronic myocardial infarction on nonenhanced cardiac cine MRI. Radiology. 2019;291(1):71-80. doi:10.1148/radiol.2019182719
10. Siontis GC, Ioannidis JP. Risk prediction tools in cardiovascular disease prevention: a systematic review. JAMA Intern Med. 2015;175(8):1292-1299. doi:10.1001/jamainternmed.2015.2382
11. Baskaran L, Oey H, Chen L, et al. Prediction of cardiovascular disease risk using machine learning: an expert consensus statement from the Education Committee of the International Society of Cardiovascular Disease Epidemiology and Prevention. Eur J Epidemiol. 2021;36(7):617-630. doi:10.1007/s10654-021-00789-3
12. Bhatia N, Agrawal R. Artificial intelligence-based risk stratification models in cardiovascular disease. Eur Cardiol. 2021;16:e45. doi: 10.15420/ecr.2021.12
13. Dey D, Slomka PJ, Leeson P, Comaniciu D, Shrestha S, Sengupta PP, Marwick TH. Artificial intelligence in cardiovascular imaging: JACC state-of-the-art review. J Am Coll Cardiol. 2019;73(11):1317-1335. doi: 10.1016/j.jacc.2018.12.061
14. Ghorbani A, Khosravi A, Sadoughi F, Safdari R. A systematic review of artificial intelligence applications in cardiovascular disease prediction and diagnosis. J Healthc Eng. 2020;2020:6651859. doi: 10.1155/2020/6651859
15. Guo Y, Yu B, Li Z, et al. Cardiovascular disease prediction model based on machine learning algorithms. Front Public Health. 2021;9:671146. doi: 10.3389/fpubh.2021.671146
16. Hristova K, Rossignol M, Beauvais W, Reynier P, Petteng T. Artificial intelligence applied to ECG recordings: a review. J Electrocardiol. 2021;65:56-62. doi: 10.1016/j.jelectrocard.2020.12.007
17. Jia X, Yu B, Yang Z, et al. Clinical application of artificial intelligence in cardiovascular disease: a systematic review. BMC Cardiovasc Disord. 2021;21(1):83. doi: 10.1186/s12872-021-01934-x
18. Krittanawong C, Zhang H, Wang Z, Aydar M, Kitai T. Artificial intelligence in precision cardiovascular medicine. J Am Coll Cardiol. 2017;69(21):2657-2664. doi: 10.1016/j.jacc.2017.03.571
19. Liew C, Lawley MJ, Quan J, et al. Artificial intelligence for diagnosis and grading of prostate cancer in biopsies: a population-based, diagnostic study. Lancet Oncol. 2020;21(2):222-232. doi: 10.1016/S1470-2045(19)30738-7
20. Liu Y, Chen PC, Krause J, et al. How to read articles that use machine learning: users’ guides to the medical literature. JAMA. 2019;322(18):1806-1816. doi: 10.1001/jama.2019.16489
21. Mahmood SS, Levy D, Vasan RS, Wang TJ. The Framingham Heart Study and the epidemiology of cardiovascular disease: a historical perspective. Lancet. 2014;383(9921):999-1008. doi: 10.1016/S0140-6736(13)61752-3
22. Mantri N, Kochar A, Albert D. Artificial intelligence and its potential in cardiovascular diseases. Cureus. 2019;11(1):e3851. doi: 10.7759/cureus.3851
23. Mirowski P, Patel M, Madias C, et al. Predicting survival from large electrocardiographic and electronic medical record datasets: the PhysioNet/Computing in Cardiology Challenge 2012. J Electrocardiol. 2013;46(5):468-473. doi: 10.1016/j.jelectrocard.2013.05.005
24. Majidi S, Thirunavukkarasu S, AlBaradie R, et al. Artificial intelligence for improved cardiovascular disease risk prediction: a review. Open Heart. 2021;8(1):e001515. doi: 10.1136/openhrt-2021-001515
25. Xie B, Wang X, Wu J, Xu G, Gao L, Zhang R. An intelligent classification system based on support vector machine for the diagnosis of cardiovascular diseases. Biomed Res Int. 2016;2016:3674281. doi: 10.1155/2016/3674281
26. Wang C, Liu W, Wang L, et al. Deep learning models for predicting cardiovascular risk from echocardiographic data. Eur Heart J Cardiovasc Imaging. 2021;22(4):422-429. doi: 10.1093/ehjci/jeaa316
27. Nakamura K, Turin TC, Kita Y, et al. Development and validation of a novel artificial intelligence-based electrocardiogram risk model to predict cardiovascular outcomes. Circ Arrhythm Electrophysiol. 2020;13(7):e008153. doi: 10.1161/CIRCEP.119.008153
28. Elias-Smale SE, Proença RV, Koller MT, et al. Coronary calcium score improves classification of coronary heart disease risk in the elderly: the Rotterdam study. J Am Coll Cardiol. 2010;56(17):1407-1414. doi: 10.1016/j.jacc.2010.04.062
29. Xie W, Xing Y, Yuan Y, et al. Machine learning-based risk prediction model for acute coronary syndrome in Chinese patients with coronary atherosclerosis. Clin Cardiol. 2020;43(11):1265-1274. doi: 10.1002/clc.23450
30. Plante TB, Urrea B, MacFarlane ZT, et al. Validation of the instant blood pressure smartphone app. JAMA Intern Med. 2016;176(5):700-702. doi: 10.1001/jamainternmed.2016.0157
31. Dilsizian V. Artificial intelligence in cardiovascular medicine: quo vadis? J Nucl Med. 2019;60(5):661-662. doi: 10.2967/jnumed.119.226944
32. Kohli P, Udell JA. Artificial intelligence and machine learning in cardiology. Curr Treat Options Cardiovasc Med. 2018;20(11):83. doi: 10.1007/s11936-018-0682-2
33. Bansal P, Gupta A, Kumar N, et al. A machine learning-based predictive model for cardiovascular diseases using telemonitoring blood pressure values. J Med Syst. 2020;44(11):187. doi: 10.1007/s10916-020-01669-w
34. Zhou X, Wang Y, Pan W, et al. Development and validation of a machine learning-based risk prediction model for major adverse cardiovascular events among patients with acute myocardial infarction in China. JAMA Netw Open. 2020;3(7):e209920. doi: 10.1001/jamanetworkopen.2020.9920
35. Peng Y, Wang J, Liu W, Wang Y, Tang R. Artificial intelligence for precision medicine in cardiovascular disease. Front Cardiovasc Med. 2020;7:17.