JACC Asia. 2026 May 2:S2772-3747(26)00268-1. doi: 10.1016/j.jacasi.2026.04.011. Online ahead of print.
ABSTRACT
BACKGROUND: Ultrasonic flow ratio (UFR) is an artificial intelligence-powered method that derives fractional flow reserve (FFR) from intravascular ultrasound (IVUS) imaging. While retrospective core-laboratory studies have demonstrated its diagnostic accuracy, prospective onsite validation remains unexplored.
OBJECTIVES: This study evaluated the diagnostic accuracy of onsite UFR for identifying hemodynamically significant coronary stenosis, using wire-based FFR as the reference standard.
METHODS: Consecutive patients with ≥1 de novo lesion exhibiting 50-80% diameter stenosis and a reference diameter ≥2.5 mm were prospectively enrolled. After FFR measurement, IVUS pullbacks were acquired and analyzed onsite using dedicated software, with analysts blinded to FFR results. Minimal lumen area (MLA) was simultaneously available during UFR computation. The prespecified primary endpoint was onsite diagnostic accuracy of UFR for identifying FFR ≤0.80.
RESULTS: Between February 2023 and November 2024, 112 patients (138 pullbacks) were enrolled; after exclusion of 6 patients (7 pullbacks), 106 patients with 131 vessels remained for analysis. Median FFR was 0.84 [IQR 0.78-0.90], with 43/131 (32.8%) of lesions showing FFR ≤0.80. UFR achieved diagnostic accuracy of 94% (95%CI: 88-97%), significantly exceeding the prespecified target of 78% (P<0.001). Compared with IVUS-derived MLA, UFR demonstrated superior sensitivity (88% [95% CI: 75-96%] versus 47% [95% CI: 31-62%], P<0.001) and specificity (97% [95% CI: 90-99%] versus 84% [95% CI: 75-91%], P=0.003). The corresponding positive and negative predictive values were 93% (95% CI: 81-97%) and 94% (95% CI: 88-97%), respectively.
CONCLUSIONS: The study achieved its prespecified primary goal by demonstrating high onsite diagnostic accuracy of UFR in identifying hemodynamically significant coronary stenosis. (The FEATURE [Functional ComprEhensive AssessmenT by IVUS Reconstruction in Patients with Suspected IschEmic Heart Disease] study; NCT05694065).
PMID:42145031 | DOI:10.1016/j.jacasi.2026.04.011