Artificial Intelligence Advances in Cardiology—Part 1: Key Points

Elias P, Jain SS, Poterucha T, et al.
Artificial Intelligence for Cardiovascular Care—Part 1: Advances: JACC Review Topic of the Week. J Am Coll Cardiol 2024;83:2472-2486.

The following are key points to remember from a JACC review topic of the week on advances in artificial intelligence (AI) for cardiovascular care—part 1:

  1. The recent AI advancements in cardiovascular care offer potential enhancements in diagnosis, treatment, and clinical outcomes.
  2. Innovations to date focus on automating measurements, enhancing image quality, and detecting diseases using novel methods. Applications span wearables, electrocardiograms (ECGs), echocardiography, angiography, genetics, and more.
  3. AI models detect diseases from ECGs at accuracy not previously achieved by technology or human experts, including reduced ejection fraction, valvular heart disease, and other cardiomyopathies.
  4. All cardiac imaging modalities now have applications using AI, improving acquisition, measurement, and diagnostic capacity.
  5. Recent studies have also shown that machine learning can exploit nonlinear and complex relationships in genomic data, leading to improved risk prediction across diverse ancestries.
  6. However, AI's unique characteristics necessitate rigorous validation by addressing training methods, real-world efficacy, equity concerns, and long-term reliability.
  7. Despite an exponentially growing number of studies in cardiovascular AI, trials showing improvement in outcomes remain lacking. A number are currently underway.
  8. Embracing this rapidly evolving technology while setting a high evaluation benchmark will be crucial for cardiology to leverage AI to enhance patient care and the provider experience.
  9. AI technologies have shown early promise in screening for disease, integrating disparate imaging data sources into composite assessments, providing workflow efficiencies through preprocessing of images, and assisting clinicians with more accurate diagnoses. These applications begin to show how AI can serve not only as “artificial intelligence,” but also as “augmented intelligence” for our clinicians.
  10. Future directions involve a focus on higher quality and quantity of labeling, more diverse training data, rigorous evaluation of model generalizability, and education to promote adoption.

Note: Part 2 of Artificial Intelligence for Cardiovascular Care is linked here.

Clinical Topics: Cardiovascular Care Team, Prevention

Keywords: Artificial Intelligence, Machine Learning

< Back to Listings