FLASH: AI-Based Quantitative Angiography Shows Promise For Assisting PCI
Results from the FLASH trial demonstrate the noninferiority of artificial intelligence-based fully automated quantitative coronary angiography (AI-QCA)-assisted PCI compared with optical coherence tomography (OCT)-guided PCI in achieving optimal minimal stent area, with comparable procedural complications, OCT-defined endpoints, and six-month clinical outcomes, according to researchers presenting the findings at TCT 2024.
The trial, which was also simultaneously published in JACC: Cardiovascular Interventions, randomized 400 patients with significant coronary artery disease undergoing PCT at 13 centers in South Korea to either AI-QCA-assisted or OCT-guided PCI. The primary endpoint, which was the post-PCI minimal stent area (MSA) assessed by OCT, was 6.3 ± 2.2 mm2 in the AI-QCA group and 6.2 ± 2.2mm2 in the OCT group (difference, -0.16; 95% CI, -0.59 to 0.28; P for noninferiority <0.001). Other OCT-defined endpoints, such as stent under-expansion, dissection and untreated reference segment disease, were not significantly different between groups. However, researchers did observe a higher incidence of stent malapposition in the AI-QCA group (13.6% vs. 5.6 %, respectively).
"Intracoronary imaging-guided PCI has demonstrated improved clinical outcomes compared to angiography-guided PCI, particularly in complex coronary artery disease. However, its global utilization remains limited due to various clinical, logistic, and economic constraints," write Yongcheol Kim, MD, FACC, et al. "The FLASH trial introduces AI-QCA as a promising approach for guiding coronary intervention, particularly valuable in resource-limited settings or in less complex coronary artery disease where the clinical benefits of intravascular imaging are not fully established."
Moving forward the researchers suggest that larger clinical trials focusing on long-term clinical outcomes will be necessary to "fully establish the role of AI-QCA-assisted PCI in daily interventional cardiology practice."
In a related editorial comment highlighting several key points from the study warranting further discussion, Mohamad Alkhouli, MD, MBA, FACC, and Shih-Sheng Chang, MD, PhD, write that "the FLASH trial represents an important step toward addressing unmet needs in interventional cardiology through advanced technology. Although much work remains, we are steadily progressing toward a future when comprehensive AI solutions will play a central role in diagnosing and treating CAD in the catheterization laboratory."
Clinical Topics: Invasive Cardiovascular Angiography and Intervention, Noninvasive Imaging, Interventions and Imaging, Angiography, Nuclear Imaging
Keywords: Transcatheter Cardiovascular Therapeutics, TCT24, Artificial Intelligence, Coronary Stenosis, Coronary Angiography, Percutaneous Coronary Intervention