EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Artificial intelligence and machine learning in cardiovascular medicine: current applications, clinical evidence, and future directions

Vaibhav Sharma, Gurpreet Kaur Chawla, Shreyashi Kukreti, Kriti Ahuja, Surender Singh

Exploration of Medicine · 01.03.2026 · 7

DOI: 10.37349/emed.2026.1001383 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Exploration of Medicine, online erschienen am 01.03.2026. Verfasst von Vaibhav Sharma und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 93 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cardiovascular disease remains the leading cause of global mortality with nearly 19 million deaths annually, while exponential growth in multimodal imaging, continuous monitoring, and electronic health record data has created analytical challenges exceeding traditional methods. This narrative review examines artificial intelligence (AI) and machine learning (ML) applications in cardiovascular medicine through a comprehensive literature analysis from 2019 to 2025, focusing on clinical validation and regulatory approvals. Current applications demonstrate significant clinical utility: automated ECG interpretation achieves > 90% accuracy in arrhythmia detection and predicts life-threatening arrhythmias up to two weeks before clinical onset; deep learning cardiac imaging analysis matches expert performance while reducing analysis time from 45 minutes to under 5 minutes; and ML risk prediction outperforms traditional scores with area under the curve values of 0.865 vs. 0.765. The FDA has approved 122 cardiology AI algorithms representing 14% of all clinical AI in the U.S. market, including ECG interpretation, echocardiographic measurement, and imaging analysis systems. Real-world implementations demonstrate 15–25% reductions in diagnostic errors and 20–30% faster emergency intervention times. However, substantial challenges persist: data quality limitations, algorithmic bias with 10–15% performance variation across populations, workflow integration barriers, and validation requirements. Future directions include multimodal systems, continuously learning algorithms, precision medicine applications, and equitable global implementation. Successful integration requires addressing limitations through diverse training datasets, transparent development, standardized validation, provider education, and maintaining physician autonomy. AI and ML represent powerful augmentation tools that, through evidence-based implementation, can transform cardiovascular care while preserving clinical expertise in decision-making.

Zitieren

APA

Sharma, V., Chawla, G. K., Kukreti, S., Ahuja, K., & Singh, S. (2026). Artificial intelligence and machine learning in cardiovascular medicine: current applications, clinical evidence, and future directions. Exploration of Medicine, 7. https://doi.org/10.37349/emed.2026.1001383

Vancouver

Sharma V, Chawla GK, Kukreti S, Ahuja K, Singh S. Artificial intelligence and machine learning in cardiovascular medicine: current applications, clinical evidence, and future directions. Exploration of Medicine. 2026;7. doi:10.37349/emed.2026.1001383

BibTeX
@article{Sharma2026,
  author = {Sharma, Vaibhav and Chawla, Gurpreet Kaur and Kukreti, Shreyashi and Ahuja, Kriti and Singh, Surender},
  title = {Artificial intelligence and machine learning in cardiovascular medicine: current applications, clinical evidence, and future directions},
  journal = {Exploration of Medicine},
  year = {2026},
  volume = {7},
  doi = {10.37349/emed.2026.1001383}
}
Kostenlos starten →