Artificial Intelligence‐Driven Angiographic Quantification of Fractional Flow Reserve: Proof‐of‐Concept Validation Study
Journal of the American Heart Association · 01.09.2026 · 15 (17)
DOI: 10.1161/jaha.125.049331 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift Journal of the American Heart Association, erschienen am 01.09.2026. Verfasst von Seung Hun Lee und 18 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiology, Chonnam National University Hospital Chonnam National University Medical School Gwangju Korea. Hauptthemen laut MEDLINE: Fractional Flow Reserve, Myocardial, Coronary Angiography, Artificial Intelligence, Coronary Stenosis. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Angiography‐based fractional flow reserve (FFR) techniques offer wire‐free alternatives but often require manual segmentation and 3‐dimensional reconstruction. Although an artificial intelligence‐driven approach automates these steps, validation remains limited. This study investigated the diagnostic performance of an artificial intelligence‐driven angiography‐based FFR (medipixel FFR [MPFFR]), compared with quantitative flow ratio (QFR) in predicting functionally significant coronary artery stenosis defined by FFR ≤0.80.
Methods
A total of 599 vessels from 452 patients who underwent clinically indicated FFR measurement were prospectively enrolled from 5 university hospitals in Korea. MPFFR used automated processes in frame selection, artificial intelligence contour detection, corresponding points matching, 3‐dimensional reconstruction, and analytical hemodynamic modeling. The primary end point was diagnostic accuracy for detecting FFR ≤0.80. Secondary end points were target vessel failure (composite of cardiac death, target‐vessel myocardial infarction, and target‐vessel revascularization) at 2 years.
Results
Mean analysis time of MPFFR was 12.5±1.7 seconds and manual correction was needed in 32 vessels (5.3%). MPFFR showed similar diagnostic performance with QFR (correlation with FFR; MPFFR versus QFR: R=0.885 versus R=0.860, P for comparison=0.011; area under the curve to predict FFR ≤0.80; 0.949 versus 0.953, P for comparison=0.631). At a median follow‐up of 2 years (interquartile range, 1.6–2.6 years), patients with MPFFR ≤0.80 had higher risk of target vessel failure than those with MPFFR >0.80 (4.5% versus 0.8%; adjusted hazard ratio, 5.94 [95% CI, 1.27–27.91]; P =0.024). C‐index to predict target vessel failure was comparable between MPFFR and QFR (0.770 versus 0.753, P for comparison=0.469).
Conclusions
In this multicenter registry, an artificial intelligence‐driven angiography‐based FFR demonstrated comparable diagnostic accuracy with QFR in identifying functionally significant stenosis, and similar prognostic ability with QFR in terms of target vessel failure at 2 years. Registration Multicenter QFR Registry; Unique Identifier: NCT03791788.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Cardiology, Chonnam National University Hospital Chonnam National University Medical School Gwangju Korea.
- Division of Cardiology, Department of Medicine, Heart Vascular Stroke Institute, Samsung Medical Center Sungkyunkwan University School of Medicine Seoul Korea.
- Department of Internal Medicine and Cardiovascular Center Seoul National University Hospital Seoul Republic of Korea.
- Department of Internal Medicine and Cardiovascular Center, Chosun University Hospital University of Chosun College of Medicine Gwangju Republic of Korea.
- Department of Medicine Inje University Ilsan Paik Hospital Goyang Republic of Korea.
- Department of Medicine Keimyung University Dongsan Medical Center Daegu Republic of Korea.
ORCID-Profile: Seung Hun Lee, Dong Hyun Gim, Hyun Kuk Kim, Hyun Cho, Sung Eun Kim, Sung Woo Cho, Ki Hong Choi, Taek Kyu Park, Jeong Hoon Yang, Young Bin Song, Joon-Hyung Doh, Chang-Wook Nam, Joo-Yong Hahn, Bon-Kwon Koo, Seung-Hyuk Choi, Hyeon-Cheol Gwon, Hyuck-Jun Yoon, Joo Myoung Lee
Zitieren
APA
Lee, S. H., Gim, D. H., Hwang, D., Kim, H. K., Cho, H., Kim, S. E., Cho, S. W., Choi, K. H., Park, T. K., Yang, J. H., Song, Y. B., Doh, J. H., Nam, C. W., Hahn, J. Y., Koo, B. K., Choi, S. H., Gwon, H. C., Yoon, H. J., & Lee, J. M. (2026). Artificial Intelligence‐Driven Angiographic Quantification of Fractional Flow Reserve: Proof‐of‐Concept Validation Study. Journal of the American Heart Association, 15(17). https://doi.org/10.1161/jaha.125.049331
Vancouver
Lee SH, Gim DH, Hwang D, Kim HK, Cho H, Kim SE, et al. Artificial Intelligence‐Driven Angiographic Quantification of Fractional Flow Reserve: Proof‐of‐Concept Validation Study. Journal of the American Heart Association. 2026;15(17). doi:10.1161/jaha.125.049331
BibTeX
@article{Lee2026,
author = {Lee, Seung Hun and Gim, Dong Hyun and Hwang, Doyeon and Kim, Hyun Kuk and Cho, Hyun and Kim, Sung Eun and Cho, Sung Woo and Choi, Ki Hong and Park, Taek Kyu and Yang, Jeong Hoon and Song, Young Bin and Doh, Joon-Hyung and Nam, Chang-Wook and Hahn, Joo-Yong and Koo, Bon-Kwon and Choi, Seung-Hyuk and Gwon, Hyeon-Cheol and Yoon, Hyuck-Jun and Lee, Joo Myoung},
title = {Artificial Intelligence‐Driven Angiographic Quantification of Fractional Flow Reserve: Proof‐of‐Concept Validation Study},
journal = {Journal of the American Heart Association},
year = {2026},
volume = {15},
number = {17},
doi = {10.1161/jaha.125.049331}
}
EUVIMED