ADVANCES IN ARTIFICIAL INTELLIGENCE IN THE DIAGNOSIS OF CARDIOVASCULAR DISEASES: AN INTEGRATIVE REVIEW
Keywords:
Imaging Diagnosis, Cardiovascular Diseases, Ethics in Artificial Intelligence, Artificial IntelligenceAbstract
Cardiovascular diseases (CVD) are the leading cause of global mortality, making early and accurate diagnosis essential. In this context, Artificial Intelligence (AI) emerges as a transformative technology in cardiology. The objective of this study was to conduct an integrative literature review on the advances, applications, and challenges of AI in the diagnosis of CVD. The method consisted of an integrative review with articles published between 2017 and 2023, selected from the databases Scientific Electronic Library Online (SciELO), PubMed, Coordination for the Improvement of Higher Education Personnel (CAPES), Institute of Electrical and Electronics Engineers Xplore (IEEE Xplore), and Scopus. The results demonstrate the high capability of AI in interpreting electrocardiograms (ECGs) and medical images, predicting adverse events, and providing personalized risk stratification. However, significant challenges were identified, such as the need for high-quality data, algorithmic biases, ethical dilemmas, and the absence of robust regulation. It is concluded that, although the potential of AI is immense, its safe and effective integration into clinical practice depends on an ethical, regulated approach focused on strengthening human clinical decision-making, rather than replacing it.
References
Adadi, A.; Berrada, M. Peeking Inside The Black-Box: A Survey On Explainable Artificial Intelligence (Xai). Ieee Access, V. 6, P. 52138-52160, 2018.
Attia, Z. I. Et Al. An Artificial Intelligence-Enabled Ecg Algorithm For The Identification Of Patients With Atrial Fibrillation During Sinus Rhythm: A Retrospective Analysis Of Outcome Prediction. The Lancet, V. 394, N. 10201, P. 861-867, 2019.
Cirillo, D. Et Al. Sex And Gender Differences And Biases In Artificial Intelligence For Biomedicine And Healthcare. Npj Digital Medicine, V. 3, N. 1, P. 81, 2020.
Hannun, A. Y. Et Al. Cardiologist-Level Arrhythmia Detection And Classification In Ambulatory Electrocardiograms Using A Deep Neural Network. Nature Medicine, V. 25, N. 1, P. 65-69, 2019.
Organização Mundial Da Saúde (Oms). Cardiovascular Diseases. Fact Sheet, 11 June 2021. Disponível Em: Https://Www.Who.Int/News-Room/Fact-Sheets/Detail/Cardiovascular-Diseases-(Cvds.
Souza, M. T.; Silva, M. D.; Carvalho, R. Revisão Integrativa: O Que É E Como Fazer. Einstein (São Paulo), V. 8, N. 1, P. 102-106, 2010.
Topol, E. J. High-Performance Medicine: The Convergence Of Human And Artificial Intelligence. Nature Medicine, V. 25, N. 1, P. 44-56, 2019.
Weng, S. F. Et Al. Can Machine-Learning Improve Cardiovascular Risk Prediction Using Routine Clinical Data? Plos One, V. 12, N. 4, P. E0174944, 2017.
Zhang, J. Et Al. Fully Automated Echocardiogram Interpretation In Clinical Practice. Circulation, V. 138, N. 16, P. 1623-1635, 2018.