APPLICATIONS OF ARTIFICIAL INTELLIGENCE IN CARDIAC IMAGING EXAMS (ECHOCARDIOGRAPHY AND CORONARY CT ANGIOGRAPHY): ACCURACY, CLINICAL FEASIBILITY, AND ALGORITHMIC BIASES – AN INTEGRATIVE REVIEW
DOI:
https://doi.org/10.47820/recima21.v7i1.7150Keywords:
Artificial Intelligence, Echocardiography, Coronary AngiographyAbstract
Cardiovascular diseases (CVD) remain the leading cause of global morbidity and mortality, requiring accurate and scalable diagnostic strategies. Artificial intelligence (AI), through deep learning algorithms, emerges as a disruptive technology for medical image analysis. This integrative review aimed to evaluate the impact of AI on the interpretation of echocardiography and coronary computed tomography angiography (CTA), analyzing diagnostic accuracy, clinical feasibility, and biases. Sixteen articles published between 2021 and 2025 were selected from the PubMed, Scopus, and Web of Science databases. The results show that convolutional neural network (CNN) models consistently achieve areas under the curve (AUC) greater than 0.90, with sensitivity and specificity comparable to or superior to those of specialists in the detection of significant coronary stenoses and cardiac chamber segmentation. A significant reduction in interobserver variability (between 20% and 40%) and workflow optimization were observed, in addition to support for image acquisition by inexperienced operators. However, critical barriers remain: the lack of protocol standardization, dataset bias, and the limited interpretability (black-box) of the models. It is concluded that, although AI has the potential to democratize high-precision diagnosis, its safe integration into clinical practice depends on multicenter external validations, greater algorithmic transparency, and the establishment of robust ethical and regulatory guidelines.
Downloads
References
DU, M. et al. Inteligência Artificial em Angiografia por TC para a Detecção de Estenose Arterial Coronariana e Placa Calcificada: Uma Revisão Sistemática e Meta-análise. Radiologia Acadêmica, v. 32, n. 7, p. 3776-3787, jul. 2025. Disponível em: https://doi.org/10.1016/j.acra.2025.03.054. DOI: https://doi.org/10.1016/j.acra.2025.03.054
IRANNEGJAD, K. et al. Inteligência artificial na angiografia por TC coronária: transformando o diagnóstico e a estratificação de risco de aterosclerose. International Journal of Cardiovascular Imaging, v. 41, n. 9, p. 1643-1656, set. 2025. Disponível em: https://doi.org/10.1007/s10554-025-03440-8. DOI: https://doi.org/10.1007/s10554-025-03440-8
KARAKUŞ, G.; DEĞIRMENCIOĞLU, A.; NANDA, N. C. Inteligência artificial em ecocardiografia: Revisão e limitações, incluindo preocupações epistemológicas. Ecocardiografia, v. 39, n. 8, p. 1044-1053, ago. 2022. Disponível em: https://doi.org/10.1111/echo.15417. DOI: https://doi.org/10.1111/echo.15417
KRITTANAWONG, C. et al. Aprendizagem Profunda para Ecocardiografia: Introdução para Médicos e Visão Futura: Revisão de Estado da Arte. Life, v. 13, n. 4, p. 1029, 17 abr. 2023. Disponível em: https://doi.org/10.3390/life13041029. DOI: https://doi.org/10.3390/life13041029
LIU, B. et al. A deep learning framework assisted echocardiography (AIEchoDx) differentiating common cardiac diseases. Scientific Reports, 2022/2023.
LIU, Y. et al. Application of artificial intelligence in echocardiography from 2009 to 2024: a bibliometric analysis. Frontiers in Medicine, v. 12, p. 1587364, 29 jul. 2025. Disponível em: https://doi.org/10.3389/fmed.2025.1587364. DOI: https://doi.org/10.3389/fmed.2025.1587364
MATURI, B. et al. Revolutionizing Cardiology: The Role of Artificial Intelligence in Echocardiography. Journal of Clinical Medicine, v. 14, n. 2, p. 625, 19 jan. 2025. Disponível em: https://doi.org/10.3390/jcm14020625. DOI: https://doi.org/10.3390/jcm14020625
MOR-AVI, V. et al. Medição assistida por aprendizado profundo de parâmetros ecocardiográficos do coração esquerdo: melhoria na variabilidade interobservador e na eficiência do fluxo de trabalho. The International Journal of Cardiovascular Imaging, v. 39, n. 12, p. 2507-2516, dez. 2023. Disponível em: https://doi.org/10.1007/s10554-023-02960-5. DOI: https://doi.org/10.1007/s10554-023-02960-5
MYHRE, P. L. et al. Ecocardiografia aprimorada por inteligência artificial no manejo de doenças cardiovasculares. Nature Reviews Cardiology, 5 ago. 2025. Disponível em: https://doi.org/10.1038/s41569-025-01197-0. DOI: https://doi.org/10.1038/s41569-025-01197-0
NARANG, A. et al. Utility of a Deep-Learning Algorithm to Guide Novices to Acquire Echocardiograms for Limited Diagnostic Use. JAMA Cardiology, v. 6, n. 6, p. 624–632, jun. 2021. Disponível em: https://doi.org/10.1001/jamacardio.2021.0185. DOI: https://doi.org/10.1001/jamacardio.2021.0185
SCHULZE, K. et al. Coronary CT angiography evaluation with artificial intelligence for individualized medical treatment of atherosclerosis: a Consensus Statement from the QCI Study Group. Nature Reviews Cardiology, 1 ago. 2025. Disponível em: https://doi.org/10.1038/s41569-025-01191-6. DOI: https://doi.org/10.1038/s41569-025-01191-6
SHRIVASTAVA, P. et al. Uma revisão sistemática sobre angiografia por TC coronariana habilitada para aprendizado profundo para quantificação de placa e estenose e previsão de risco cardíaco. European Journal of Radiology Open, v. 14, p. 100652, 2 maio 2025. Disponível em: https://doi.org/10.1016/j.ejro.2025.100652. DOI: https://doi.org/10.1016/j.ejro.2025.100652
STAMATE, E. et al. Revolutionizing Cardiology through Artificial Intelligence-Big Data from Proactive Prevention to Precise Diagnostics and Cutting-Edge Treatment-A Comprehensive Review of the Past 5 Years. Diagnostics, v. 14, n. 11, p. 1103, 26 maio 2024. Disponível em: https://doi.org/10.3390/diagnostics14111103. DOI: https://doi.org/10.3390/diagnostics14111103
TROMP, J. et al. A formal validation of a deep learning-based automated interpretation of echocardiography parameters. Nature Communications, 2022. DOI: https://doi.org/10.1038/s41467-022-34245-1
TU, Li et al. Accuracy of deep learning in the differential diagnosis of coronary artery stenosis: a systematic review and meta-analysis. BMC Medical Imaging, v. 24, n. 243, 2024. Disponível em: https://doi.org/10.1186/s12880-024-01403-4. DOI: https://doi.org/10.1186/s12880-024-01403-4
VAN HERTEN, R. L. M. et al. O papel da inteligência artificial na angiografia por TC coronária. Netherlands Heart Journal, v. 32, n. 11, p. 417-425, nov. 2024. Disponível em: https://doi.org/10.1007/s12471-024-01901-8. DOI: https://doi.org/10.1007/s12471-024-01901-8
Downloads
Published
License
Copyright (c) 2026 RECIMA21 - Revista Científica Multidisciplinar - ISSN 2675-6218
This work is licensed under a Creative Commons Attribution 4.0 International License.
Os direitos autorais dos artigos/resenhas/TCCs publicados pertecem à revista RECIMA21, e seguem o padrão Creative Commons (CC BY 4.0), permitindo a cópia ou reprodução, desde que cite a fonte e respeite os direitos dos autores e contenham menção aos mesmos nos créditos. Toda e qualquer obra publicada na revista, seu conteúdo é de responsabilidade dos autores, cabendo a RECIMA21 apenas ser o veículo de divulgação, seguindo os padrões nacionais e internacionais de publicação.
