Artificial Intelligence Applications in Cardiology—Part 2: Key Points

Jain SS, Elias P, Poterucha T, et al.
Artificial Intelligence in Cardiovascular Care—Part 2: Applications: JACC Review Topic of the Week. J Am Coll Cardiol 2024;83:2487-2496.

The following are key points to remember from a JACC review topic of the week on applications in artificial intelligence (AI) for cardiovascular care—part 2:

  1. Applications of AI to cardiovascular care have accelerated as a result of advances in multimodal inputs and generative technology.
  2. Over 600 Food and Drug Administration (FDA)-approved clinical AI algorithms now exist, with 10% focusing on cardiovascular applications, highlighting the growing opportunities for AI to augment cardiovascular care.
  3. Generative AI, which is a subcategory of AI in which algorithms can generate new content, has become an area of immense interest in medical care and has the potential to revolutionize multiple facets of cardiovascular care, from streamlining administrative tasks, to helping make cardiovascular care more efficient and allowing doctors to work at the top of their license, to diagnostics and treatment planning, to drug discovery and education.
  4. A critical bottleneck for the clinical application of generative AI models has been the lack of availability and access to large, high-quality training datasets for machine learning.
  5. Realizing the potential of AI requires enhanced infrastructure, rigorous evaluation, regulatory oversight, and viable business models.
  6. Embracing this rapidly evolving technology while setting an appropriately high evaluation benchmark with careful and patient-centered implementation will be crucial for cardiology to leverage AI to enhance patient care and the provider experience.
  7. While not all AI applications in health care will need randomized controlled trials to prove safety and value, this kind of rigorous evaluation is warranted for applications that affect patient outcomes, and should be focused on evaluating patient safety, implementation success metrics, clinical efficacy, and clinical effectiveness.
  8. Practicing clinicians should have a basic understanding of AI, its applications, and limitations to assure appropriate use.
  9. Realizing the potential for AI in cardiovascular medicine will require a concerted effort by the cardiology community to develop, test, and implement these technologies into our practice, continually evaluating where AI can and cannot provide significant value.
  10. As AI research progresses and the technology matures, it is vital for the cardiology community to engage actively with these developments and ensure AI tools and associated AI-assisted clinical workflows are validated, ethical, and effective for patient care.

Note: Part 1 of Artificial Intelligence for Cardiovascular Care is linked here.

Clinical Topics: Cardiovascular Care Team, Prevention

Keywords: Artificial Intelligence

< Back to Listings