Cardiovascular diseases (CVDs) are currently one of the main causes of morbidity and mortality worldwide, affecting millions of people annually. Data prepared by the World Health Organization (WHO) show the prevalence of 31% of deaths in the general population are caused by CVDs, which is, respectively, equivalent to 17.9 million deaths per year . In the United States, heart disease is the leading cause of death followed by cancer of all types . US population, recent data from the American Heart Association (AHA) show that CVDs are responsible for approximately 1 in 3 deaths, consequently equating to about 2,300 deaths per day . From an economic point of view, CVDs have a significant economic impact, contributing to the increase in presenteeism, and consequently reducing labor productivity. $ 351 billion in 2018, with expenditures divided respectively between hospitalization expenses and long-term pharmacological and non-pharmacological treatment . Under this scenario, continuous efforts have been widely carried out for the prevention and diagnosis of these diseases.
In this context, radiology has been an area characterized by significant advances in the management of CVDs. The main application of radiology refers to performing imaging exams, such as computed tomography (CT), magnetic resonance imaging (MRI), and x-ray angiography, which allow a detailed assessment of the cardiac and vascular anatomy, as well as such as the evaluation of the effectiveness of a pharmacological intervention or not . Despite the exponential development with the use of artificial intelligence (AI) models in the health area, new perspectives are emerging for the use of AI in the management of CVD diagnosis .
One of the main applications refers to the use of algorithms capable of recognizing patterns in signals in electrocardiogram (ECG) exams, which are capable of indicating the presence or absence of cardiovascular conditions, such as atrial fibrillation and heart failure . Another use of AI in the management of CVDs is in the analysis of imaging tests, such as echocardiograms and computed tomography, for the detection of cardiovascular diseases, such as coronary artery disease, and the detection of abnormalities in heart valves . A study published in the “Journal of the American College of Cardiology” found that AI algorithms can accurately identify the presence and severity of coronary artery disease from CT angiograms . Not far from a recent application of AI based on prevention, it refers to the potential of algorithms to play a role in the stratification of traditional and non-traditional factors for cardiovascular diseases, having the capacity to customize treatment plans based on these data . This approach can help optimize patient outcomes and reduce the risk of adverse events.
In conclusion, the use of AI in the management and diagnosis of CVDs has the potential to revolutionize the way these conditions are diagnosed and treated. With the ability to analyze vast amounts of data and identify patterns that may not be apparent to the human eye, AI has the potential to improve diagnostic accuracy, optimize patient outcomes and reduce the burden of cardiovascular disease worldwide. However, despite the encouraging results, there are still important gaps to be filled, such as data availability, implementation within medical practice, safety, and privacy of patients and health professionals involved.
. OMS (2019). Cardiovascular diseases. Available: htts://www.who.int/health-topics/cardiovascular-diseases
 American Heart Association (2020). Cardiovascular Disease. Available: https://www.heart.org/en/health-topics/cardiovascular-diseases.
 Agency for Healthcare Research and Quality (2021). Heart Disease and Stroke Statistics – 2021 Update: A Report From American Heart Association Circulation, 143(16), e133-3160.
 Lipton, Z. C., Steinhubl, S. R., & Topol, E. J. (2018). The use of artificial intelligence in cardiovascular medicine. Nature machine intelligence, 1(2), 61-70.
 Ramaswamy, V., Mani, V., Bixby, D., & Stone, N. J. (2019). Artificial intelligence in cardiovascular imaging: a comprehensive review. Journal of the American College of Cardiology, 73(20), 2614-2630.