Machine learning assessment of myocardial ischemia using angiography: Development and retrospective validation.

Hyeonyong Hae Soo-Jin Kang Won Jang KimSo-Yeon ChoiJune Goo LeeYoungoh BaeHyungjoo ChoDong-Hyun YangJoon-Won KangTae-Hwan LimCheol Hyun LeeDo-Yoon KangPil Hyung LeeJung-Min AhnDuk-Woo ParkSeung Whan LeeYoung-Hak KimCheol Whan LeeSeong-Wook ParkSeung-Jung Park

Published in: PLoS medicine (2018)

We found that angiography-based ML is useful to predict subtended myocardial territories and ischemia-producing lesions by mitigating the visual-functional mismatch between angiographic and FFR. Assessment of clinical utility requires further validation in a large, prospective cohort study.

Keyphrases

optical coherence tomography
machine learning
computed tomography
left ventricular
cross sectional
artificial intelligence
heart failure
big data
deep learning