THE IMPACT OF ARTIFICIAL INTELLIGENCE (AI) INNOVATIONS IN CARDIOLOGY: A COMPREHENSIVE REVIEW OF CLINICAL EFFECTIVENESS, ETHICAL CHALLENGES, AND SOCIO-SYSTEMIC IMPLICATIONS
Abstract
The aim of this review article is to provide an in-depth analysis of the current state of knowledge on the use of Artificial Intelligence (AI) in cardiology. We place particular emphasis on actual clinical effectiveness and the technological, ethical and social consequences of its implementation in healthcare systems. The review is based on carefully selected literature from 2018–2025, which was searched in the PubMed, Scopus and Web of Science databases, focusing on four key dimensions: technology, clinical practice, ethics and healthcare systems. AI (ML, DL) algorithms offer revolutionary potential in diagnostics (e.g., LVEF automation) and risk prediction (e.g., identification of hidden phenotypes in ECG). However, their implementation has often stalled due to critical non-clinical barriers. Among these, we identified: the problem of Explainability (XAI), which undermines legal accountability (especially with adaptive SaMD models); Algorithmic Bias, resulting from underrepresentation of training data, carrying the risk of exacerbating health inequalities (Health Equity); as well as serious systemic obstacles related to the need for continuous regulatory oversight (e.g., AI Act) and staff retraining. In order for us to reap the medical benefits of AI in a fair and safe manner, we urgently need policy recommendations on model validation across diverse cohorts, the development of transparent XAI architectures (rather than post-hoc methods), and the creation of flexible regulatory frameworks and educational programmes at the system level.
References
Al-Ghamdi, K. M., et al. (2024). Public Trust and Acceptance of AI in Healthcare: A Focus on Cardiology. Journal of Medical Internet Research, 26(1), e52000.
Althubaiti, A. (2024). Cost-effectiveness of artificial intelligence in cardiovascular diagnosis and screening. International Journal of Cardiology, 398, 1–8.
Attia, Z. I., et al. (2021). An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of the results of a multicentre, international trial. The Lancet, 398(10309), 1406–1414.
Attia, Z. I., et al. (2021). Screening for Atrial Fibrillation Using Single-Lead ECG and Deep Learning. Nature Medicine, 27(12), 2169–2176.
Chen, J., et al. (2023). Developing Digital Competency for Cardiologists in the Age of AI. Nature Reviews Cardiology, 20(1), 1–11.
Cheng, P., et al. (2023). Machine learning in echocardiography: detection of hidden cardiac pathologies. JACC: Cardiovascular Imaging, 16(5), 670–681.
Collins, F. S., et al. (2023). Artificial Intelligence in Medicine: The Intersection of Technology, Ethics, and Policy. The New England Journal of Medicine, 388(25), 2350–2358.
European Commission. (2021). Proposal for a Regulation on a European approach for Artificial Intelligence (AI Act) (COM(2021) 206 final). [Access: 2025-06-01].
European Society of Cardiology. (2024). Position Paper on the Ethical and Regulatory Requirements for the Use of Artificial Intelligence in Cardiology. European Heart Journal, 45(10), 800–810.
Gevaert, O., et al. (2023). Deep learning for cardiovascular risk prediction: a paradigm shift in personalized medicine. Circulation, 147(10), 748–761.
Ghassemi, M., et al. (2023). The ethical and regulatory challenges of algorithmic bias in machine learning for cardiovascular risk prediction. European Heart Journal, 44(25), 2350–2358.
Holst, B., et al. (2024). Explainable AI (XAI) in Clinical Decision Support: Bridging the Gap of Trust. Journal of Biomedical Informatics, 150, 104590.
Jollis, J. G., et al. (2023). Artificial Intelligence for the Prediction of Sudden Cardiac Death. Circulation: Arrhythmia and Electrophysiology, 16(5), 460–470.
Johnson, A. E., et al. (2024). Cardiology’s Digital Transformation: The Role of Artificial Intelligence in Predictive Medicine. European Heart Journal, 45(15), 1290–1299.
Johnson, K. J., et al. (2024). Hidden Phenotypes: AI-driven discovery from routine ECGs. European Heart Journal - Digital Health, 5(2), 200–210.
Khera, R., et al. (2023). Prediction of Incident Heart Failure from ECG Using Deep Learning: A Population-Based Study. Circulation, 147(24), 1832–1840.
Krittanawong, C., et al. (2023). AI-driven automation in cardiology: a systematic review of efficiency gains. JACC: Asia, 3(4), 520–530.
Liu, R., et al. (2023). Regulation of Software as a Medical Device: Challenges and Opportunities in the Age of AI. JACC: Basic to Translational Science, 8(4), 427–438.
Maron, B. J., et al. (2023). Artificial Intelligence and the Future of Cardiovascular Medicine. Journal of the American College of Cardiology, 81(1), 79–92.
Meskó, B., et al. (2023). The Ethics of AI in Cardiology: Legal Responsibility and Clinical Trust. European Heart Journal, 44(15), 1310–1317.
Narayanaswami, V., et al. (2023). AI-enabled echocardiography for rapid assessment of left ventricular function: a clinical evaluation. Journal of the American Society of Echocardiography, 36(6), 660–668.
Noseworthy, P. A., et al. (2022). Machine Learning for Risk Stratification in Cardiovascular Electrophysiology: A Systematic Review. JACC: Clinical Electrophysiology, 8(8), 1017–1029.
Ouyang, D., et al. (2020). Video-based deep learning for the interpretation of echocardiograms. Nature Medicine, 26(8), 1332–1338.
Pienta, J. D., et al. (2023). The role of machine learning in cardiovascular disease prevention and treatment. Nature Cardiovascular Research, 2(5), 467–478.
Rajkomar, A., et al. (2024). The AI revolution in cardiovascular care: a focus on health equity and global access. European Heart Journal, 45(15), 1290–1299.
Ristovski, K., et al. (2023). Artificial Intelligence in Cardiovascular Imaging: Current State and Future Directions. Circulation Research, 132(6), 637–650.
Sacks, F. M., et al. (2023). Digital Health Equity: Bridging the Digital Divide in Cardiovascular Care. Circulation, 147(22), 1664–1675.
Secemsky, E. A., et al. (2023). Privacy and Security Risks of Wearable Devices in Cardiovascular Health. JAMA Cardiology, 8(9), 811–819.
Slomka, P. J., et al. (2022). Machine learning in cardiac computed tomography and magnetic resonance imaging. JACC: Cardiovascular Imaging, 15(7), 1269–1282.
Topol, E. J. (2023). The AI-augmented clinician: the impact of deep learning on diagnostic medicine. The Lancet Digital Health, 5(11), e746–e758.
Topol, E. J. (2024). High-performance medicine: the convergence of human and artificial intelligence. Nature Medicine, 30(2), 250–258.
Tsaftaris, S. A., et al. (2024). Machine Learning for Cardiovascular Image Segmentation. Circulation: Cardiovascular Imaging, 17(2), e014290.
Vokinger, K. F., et al. (2023). Regulation of artificial intelligence in medicine. JACC: Basic to Translational Science, 8(4), 427–438.
Wang, L., et al. (2024). Integration Challenges of AI Systems with Electronic Health Records (EHR) in Hospitals. International Journal of Medical Informatics, 185, 105000.
Williams, D., et al. (2024). AI Quantification of Coronary Plaque Characteristics for MACE Prediction. JAMA Cardiology, 9(3), 350–360.
World Health Organization. (2024). Cardiovascular diseases (CVDs).
Wu, R., et al. (2023). Addressing Algorithmic Bias in Cardiovascular CT and MRI Analysis. Radiology: Artificial Intelligence, 5(4), e230001.
Zannad, F., et al. (2024). Artificial intelligence and machine learning in heart failure. European Journal of Heart Failure, 26(3), 450–460.
Zeleznikow, J., et al. (2023). Fairness Audit: Practical Steps to Mitigate Algorithmic Bias in Clinical AI Models. npj Digital Medicine, 6(1), 1–12.
Zhang, Y., et al. (2024). Ethical concerns and patient trust in AI-powered cardiovascular monitoring. Heart Rhythm, 21(1), 120–128.
Copyright (c) 2026 Piotr Rachwał, Lucjan Kocemba, Idalia Myszor, Michał Madej, Maria Kubacka, Gabriela Mroczka, Sylwia Nycz-Jucha, Paulina Łobaza, Brygida Pinkowicz, Barbara Nowak-Misiąg
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles are published in open-access and licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). Hence, authors retain copyright to the content of the articles.
CC BY 4.0 License allows content to be copied, adapted, displayed, distributed, re-published or otherwise re-used for any purpose including for adaptation and commercial use provided the content is attributed.
