Καρδιά: Machine Learning Applied to Patient Flow for Chest Pain
Machine learning. Patient flow. Chest pain. Heart diseases.
Cardiovascular diseases (CVD) are the leading cause of death in the world. According to the American Heart Association, coronary artery disease is the cause of death of approximately 1 in 7 people in the United States. In Brazil, CVD is also the leading cause of death from chronic non-communicable diseases. In 2007, 27.4% of hospitalizations of patients over 60 years were due to CVD. Before the patient with chest pain, predicting who will have an adverse cardiovascular event or not, especially in those with intermediate and low risk, is not always an easy task and the support of technology has been increasing. Machine learning (ML) is a computer field that uses computational algorithms to identify patterns in large data sets with many variables, and can be used to predict varying results based on data. The benefit of using ML with clinical, laboratory, and coronary artery CT data in the chest pain unit to predict cardiovascular events has not yet been assessed on a large scale. Therefore, the objective of this study will be to use the angio-CT data of the coronary arteries, in addition to the clinical and laboratory data of the patients that will be evaluated according to the respective protocols of care in the thoracic pain units, to analyze the viability and precision of ML to predict cardiovascular events.