APPLICATIONS OF ARTIFICIAL INTELLIGENCE IN CARDIOVASCULAR MEDICINE

Abstract

Artificial intelligence (AI) is described as a collection of algorithms and intelligence that attempt to replicate human intelligence. Deep learning is one of the machine learning approaches. The use of AI in healthcare systems, including hospitals and clinics, provides numerous potential benefits and future opportunities. AI applications in cardiovascular medicine include machine learning approaches for diagnostic processes such as imaging modalities and biomarkers, as well as predictive analytics for tailored medicines and improved results. AI-based systems have discovered new uses in cardiovascular medicine, including risk prediction for cardiovascular illnesses, cardiovascular imaging, predicting outcomes following revascularization treatments, and identifying new therapeutic targets. AI, such as machine learning, has partially resolved and supplied prospective solutions to unfulfilled requirements in interventions. Due to significant successes in the organization of medical care for patients with ST-segment elevation ACS (ST ACS), the introduction of percutaneous coronary interventions (PCI) into widespread practice, over the past few years, it has been possible to reduce in-hospital mortality from this pathology [3]. Artificial Intelligence (AI) lies at the core of many activity sectors that have embraced new information technologies [1]. While the roots of AI trace back to several decades ago, there is a clear consensus on the paramount importance featured nowadays by intelligent machines endowed with learning, reasoning and adaptation capabilities. It is by virtue of these capabilities that AI methods are achieving unprecedented levels of performance when learning to solve increasingly complex computational tasks, making them pivotal for the future development of the human society [2]. The sophistication of AI-powered systems has lately increased to such an extent that almost no human intervention is required for their design and deploymentHowever, the mortality rate of patients with ACS, especially with cardiogenic shock, is still high [4, 5]. Moreover, most of the deaths occur in the early stages of the onset of ACS, i.e., in the first 24 hours of the patient's hospitalization [3]. For this reason, when ST-elevation ACS or non-ST-elevation ACS (ST-elevation) develops, the physician needs a "tool" to predict the risk of death, in order to make quick decisions and optimize patient management. To date, such a "tool" for assessing the risk of an adverse outcome in patients is scales based on multivariate analysis, the strength and significance of which are confirmed by ROC analysis [4]. Currently, there are many scales and methods for assessing the risk of death (GRACE, TIMI, PURSUIT, EuroSCORE II, RECORD), however, they mainly take into account well-known "classical" risk factors [8, 9]. However, when analyzing the research data, it should be noted that the search for universal predictors for assessing the risk of in-hospital mortality continues, combining a number of criteria: ease of use, taking into account the impact of comorbidity, as well as the results of laboratory and instrumental research methods [5]. That is why the establishment of a set of prognostic factors can help optimize risk stratification and accurately assess the probability of death at the hospital stage.