Open AccessIncorporating clinical parameters to improve the accuracy of angiography-derived computed fractional flow reserve
Author(s) -
Rebecca Gosling,
Eleanor Gunn,
Hua Liang Wei,
Yu Gu,
Vignesh Rammohan,
Timothy P. Hughes,
D. Rodney Hose,
Patricia Lawford,
Julian Gunn,
Paul Morris
Publication year - 2022
Publication title -
european heart journal. digital health
Language(s) - English
Resource type - Journals
ISSN - 2634-3916
DOI - 10.1093/ehjdh/ztac045
Subject(s) - fractional flow reserve , medicine , angiography , tortuosity , hyperaemia , radiology , cardiology , coronary angiography , nuclear medicine , blood flow , myocardial infarction , geotechnical engineering , porosity , engineering
Angiography-derived fractional flow reserve (angio-FFR) permits physiological lesion assessment without the need for an invasive pressure wire or induction of hyperaemia. However, accuracy is limited by assumptions made when defining the distal boundary, namely coronary microvascular resistance (CMVR). We sought to determine whether machine learning (ML) techniques could provide a patient-specific estimate of CMVR and therefore improve the accuracy of angio-FFR.