The Transformation of Cardiovascular Medicine Under the Influence of Artificial Intelligence: History, Achievements, and Prospects

Abstract

Background — This comprehensive literature review aims to examine key milestones in the development of artificial intelligence (AI) in cardiology, highlight current advances, and identify significant challenges associated with AI integration that are underrepresented in the literature. Using a rigorous methodological approach, this review provides a detailed understanding of the transformative potential and practical limitations of AI technologies in cardiovascular medicine. Methods — A thorough search of e-Library, PubMed, and Scopus databases was conducted using a carefully selected set of keywords, including ‘artificial intelligence’, ‘expert systems’, ‘personalized medicine’, ‘polygenic risk assessment’, ‘neural networks’, ‘large language models’, ‘deep learning’, ‘cardiovascular disease’, and ‘prevention’. The search encompassed publications from 1995 to June 2025, resulting in a total of 268 articles that were systematically reviewed and analyzed. A subset of 65 articles was subsequently selected for in-depth review to ensure a comprehensive and representative sample of the current state of research in this field. Results — This article provides a comprehensive analysis of the AI application in cardiology, tracing the historical evolution of technological advances, current achievements, existing challenges, and prospects for integration. The development of AI in cardiology is described in detail from the development of the first expert systems to the emergence of sophisticated neural network models that have demonstrated exceptional accuracy in the diagnosis and prognosis of cardiovascular diseases (CVD). Particular attention is paid to the use of AI for cardiovascular risk prediction, including the integration of polygenic risk scores (PRS) with patient clinical data. The main drivers of AI adoption are revealed, including a chronic shortage of medical specialists, economic demands, and rapid technological innovation. Additionally, the article identifies significant barriers, such as patient and healthcare professional resistance, legal and ethical considerations, data quality issues, and cybersecurity challenges. Conclusion — It is emphasized that modern AI systems are shifting from human-dependent learning paradigms to autonomous self-learning models, which facilitates their accelerated development and integration into clinical practice. In conclusion, it should be noted that the successful and safe implementation of AI in cardiology depends on the readiness of the medical community, patients, and healthcare systems to engage in collaborative transformation, as well as on the improvement of the regulatory framework and quality control mechanisms for AI technologies.

Ähnliche Arbeiten