Pilot clinical evaluation of artificial intelligence-driven guiding catheter simulation for optimizing percutaneous...

Area of Science:

• Cardiovascular Interventions
• Medical Imaging
• Artificial Intelligence in Medicine

Background:

• Suboptimal guiding catheter selection in percutaneous coronary intervention (PCI) can lead to longer procedures, increased radiation, and contrast agent exposure.
• Coaxial alignment and backup support are critical for efficient and safe PCI procedures.

Purpose of the Study:

• To evaluate the efficacy of a computed tomography (CT)-driven, artificial intelligence (AI)-guided preprocedural simulation for guiding catheter selection in PCI.
• To determine if this AI-assisted approach improves procedural efficiency and safety compared to conventional methods.

Main Methods:

• A single-centre prospective registry study compared 55 elective PCI procedures using CT-based AI-assisted guiding-catheter selection with 55 historical control procedures.
• Primary endpoint was total procedure time; secondary endpoints included time to coronary engagement, radiation dose, contrast volume, and guiding-catheter-related events.

Main Results:

• CT-based AI assistance resulted in significantly shorter procedure times (68.5 vs. 91.8 min) and reduced time to coronary engagement.
• AI-guided selection led to lower radiation doses, decreased contrast volume, and fewer guiding-catheter exchanges (3.6% vs. 16.4%).
• Procedural success was 100% in both groups, with no in-hospital major adverse cardiac or cerebrovascular events.

Conclusions:

• CT-driven, AI-guided simulation for guiding-catheter selection enhances procedural efficiency and safety in elective PCI.
• This standardized approach reduces empirical catheter exchanges and may optimize resource utilization.
• Further validation in multicentre randomized trials is warranted to confirm these findings.