Back to all papers

Artificial intelligence in the cath lab: Bridging predictive models and real-time procedural decision support.

August 6, 2026pubmed logopapers

Authors

Padda I,Sharma S,Sethi Y,Sebastian SA,Atwal H,Bharaj I,Choudhary K,Sineri C

Affiliations (8)

  • Department of Cardiology, One Brooklyn Health, Brooklyn, NY, USA.
  • Department of Cardiovascular Medicine, PearResearch, Dehradun 248001, India.
  • Department of Medicine, Subharti Medical College, Swami Vivekanand, Subharti University, Meerut, India.
  • Department of Internal Medicine, Augusta Health, Fisherville, West Virginia, USA.
  • Department of Internal Medicine, Saint James School of Medicine, Park Ridge, IL, USA.
  • Department of Internal Medicine, Abrazo Health Network, Glendale, AZ, USA.
  • Department of Interventional Cardiology, Icahn School of Medicine, Mount Sinai, New York, NY, USA.
  • Department of Cardiology, Richmond University Medical Center/Mount Sinai, Staten Island, NY, USA.

Abstract

The integration of Artificial Intelligence (AI) in medicine has been revolutionary, particularly in cardiology, where AI offers transformative tools for data integration, image analysis, and predictive modeling. In procedural settings such as percutaneous coronary intervention (PCI) planning, where timely decision-making is crucial, AI represents a promising avenue for real-time risk prediction. However, current clinical scores and risk models often fall short in dynamic environments like the catheterization (cath) lab due to their static nature and limited adaptability to intra-procedural complexities. Emerging AI models aim to leverage high-frequency physiological data, procedural metadata, and multimodal imaging to recognize evolving patterns and anticipate complications. Nevertheless, most existing applications remain retrospective, lack real-time integration, and are constrained by limited external validation. Looking ahead, the implementation of real-time AI systems in the cath lab holds significant potential to enhance procedural safety and outcomes by delivering anticipatory alerts and actionable insights that support clinical decision-making during PCI. However, it is important to note that most currently available AI models remain retrospective or observational in nature, and prospective evidence demonstrating improved clinical outcomes through real-time AI-guided interventions remains limited. See also the graphical abstract(Fig. 1).

Topics

Journal ArticleReview

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAISlice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.