ADVANCES IN ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING IN THE DIAGNOSIS OF HEART DISEASES: AN INTEGRATIVE REVIEW

• DOI: 10.22533/at.ed.1593602316088

• Palavras-chave: artificial intelligence, machine learning, heart valve diseases, differential diagnosis.

• Keywords: artificial intelligence, machine learning, heart valve diseases, differential diagnosis.

• Abstract:

  Cardiovascular diseases are one of the main causes of morbidity and mortality worldwide. Accurate and early diagnosis of these conditions is essential to improve clinical outcomes and quality of life for patients. In recent years, artificial intelligence (AI) and machine learning have emerged as innovative approaches in the field of cardiology, offering promise to improve the diagnosis of heart disease.
  Through a search in databases such as PubMed, Scopus and Web of Science, relevant studies published in the last 8 years were identified. Inclusion criteria included original articles that investigated the use of AI and machine learning in the context of diagnosing heart disease, with an emphasis on clinical applications, validation and accuracy of the developed models. Analysis of selected studies revealed several promising applications of AI and machine learning in diagnosing heart disease. Among them, we highlight the use of deep learning algorithms in cardiovascular images for the detection of arrhythmias, the prediction of cardiovascular risk factors based on retinal fundus photographs and risk stratification in patients with heart failure. In addition, the application of convolutional neural networks has been shown to be effective in detecting arrhythmias at the level of cardiologists, achieving results comparable to human specialists. Studies have also explored the use of AI in identifying coronary artery disease through image analysis, offering a more efficient and accurate approach in diagnosing these conditions. The results of this integrative review highlight the growing interest of the scientific community in the application of AI and machine learning in cardiology, showing significant advances in this area in recent years. However, some limitations, such as the need for external validation of the developed models and the scarcity of studies in different populations, still need to be addressed for a successful clinical implementation of these technologies. In conclusion, the use of artificial intelligence and machine learning in the diagnosis of heart disease shows promise and may represent an important advance in clinical practice. Continued research and development in this area is essential to achieve more accurate and personalized diagnostic approaches, thereby improving care and outcomes for patients with cardiovascular disease.