Key result
AI-driven angiography-based FFR outperformed %DS for detecting hemodynamically significant coronary stenosis.
Why the study?
Angiography-derived FFR methods offer noninvasive alternatives to wire-based FFR for functional assessment of coronary stenosis, but the diagnostic performance of AI-driven angiography-based FFR requires validation against invasive FFR and QCA.
Does AI-driven angiography-based FFR improve diagnostic performance for detecting hemodynamically significant coronary stenosis compared to QCA-derived percentage diameter stenosis in patients undergoing clinically indicated angiography?
Cohort (n=189)
Yes
Does AI-driven angiography-based FFR improve diagnostic performance for detecting hemodynamically significant coronary stenosis compared to QCA-derived percentage diameter stenosis in patients undergoing clinically indicated angiography?
Answers are grounded in this paper and cite their sources.
AI-driven angiography-based FFR provides rapid (median 20.9 s), accurate, wire-free physiological assessment of coronary stenosis that outperforms anatomical %DS and could reduce the need for invasive FFR by 57.1% using a hybrid strategy.
Background and Objectives: Angiography-derived fractional flow reserve (FFR) methods offer noninvasive alternatives to wire-based FFR for functional assessment of coronary stenosis, but their diagnostic performance requires validation. This study evaluated the diagnostic performance of artificial intelligence (AI)-driven angiography-based FFR for detecting hemodynamically significant coronary stenosis, as compared with percentage diameter stenosis (%DS) from quantitative coronary angiography (QCA), using invasive FFR as the reference standard. Methods: In this prospective, multicenter study, 189 patients (211 lesions) undergoing clinically indicated angiography were enrolled. AI-driven angiography-based FFR and %DS were derived from angiographic images and compared with invasive FFR (cutoff ≤ 0.80). Diagnostic performance was assessed using AUROC, sensitivity, specificity, and predictive values, along with correlation analysis and analysis time. Results: AI-driven angiography-based FFR showed significantly greater diagnostic performance than %DS (per-patient AUROC: 0.87 vs. 0.63, p < 0.001; per-lesion AUROC: 0.89 vs. 0.65, p < 0.001). AI-driven angiography-based FFR demonstrated higher specificity (92.7%) and positive predictive value (86.7%) than %DS (64.2% and 51.9%, respectively). AI-driven angiography-based FFR correlated strongly with invasive FFR (r = 0.746), whereas %DS showed a weak inverse correlation (r = −0.250). Median analysis time for AI-driven angiography-based FFR was 20.9 s. A gray-zone hybrid strategy (thresholds 0.73–0.83) yielded 89.8% accuracy and could reduce invasive FFR use by 57.1%. Conclusions: AI-driven angiography-based FFR demonstrated high diagnostic accuracy, strong correlation with invasive FFR, and rapid analysis time. These findings support AI-driven angiography-based FFR as a pressure-wire-free tool for physiological assessment during coronary angiography.
No takes yet. Share an insight, caveat, or question.
Ahn et al. (2026) conducted a cohort in Hemodynamically significant coronary stenosis (n=189). AI-driven angiography-based FFR (MPFFR) vs. Percentage diameter stenosis (%DS) from quantitative coronary angiography (QCA), with invasive FFR (≤0.80) as reference standard was evaluated on Diagnostic performance (AUROC) for detecting hemodynamically significant coronary stenosis (invasive FFR ≤ 0.80) (Per-patient AUROC 0.87 vs 0.63; Per-lesion AUROC 0.89 vs 0.65, p=< 0.001). AI-driven angiography-based FFR outperformed %DS for detecting hemodynamically significant coronary stenosis.
Synapse has enriched 10 related papers. Consider them for comparative context: