A simplified coronary model for diagnosis of ischemia-causing coronary stenosis

Yili Feng; Bao Li; Ruisen Fu; Yaodong Hao; Tongna Wang; Huanmei Guo; Junling Ma; Gerold Baier; Haisheng Yang; Quansheng Feng; Liyuan Zhang; Youjun Liu

doi:10.1016/j.cmpb.2023.107862

A simplified coronary model for diagnosis of ischemia-causing coronary stenosis

Comput Methods Programs Biomed. 2023 Dec:242:107862. doi: 10.1016/j.cmpb.2023.107862. Epub 2023 Oct 12.

Authors

Yili Feng¹, Bao Li¹, Ruisen Fu¹, Yaodong Hao¹, Tongna Wang¹, Huanmei Guo¹, Junling Ma¹, Gerold Baier², Haisheng Yang¹, Quansheng Feng³, Liyuan Zhang⁴, Youjun Liu⁵

Affiliations

¹ Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, No. 100 Pingleyuan, Chaoyang District, Beijing 100124, China.
² Cell and Developmental Biology, University College London, London WC1E 6BT, UK.
³ Department of Cardiology, the First People's Hospital of Guangshui, Guangshui, Hubei 432700, China.
⁴ Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, No. 100 Pingleyuan, Chaoyang District, Beijing 100124, China. Electronic address: LiyuanZhang@bjut.edu.cn.
⁵ Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, No. 100 Pingleyuan, Chaoyang District, Beijing 100124, China. Electronic address: lyjlma@bjut.edu.cn.

PMID: 37857024
DOI: 10.1016/j.cmpb.2023.107862

Abstract

Background and objective: The functional assessment of the severity of coronary stenosis from coronary computed tomography angiography (CCTA)-derived fractional flow reserve (FFR) has recently attracted interest. However, existing algorithms run at high computational cost. Therefore, this study proposes a fast calculation method of FFR for the diagnosis of ischemia-causing coronary stenosis.

Methods: We combined CCTA and machine learning to develop a simplified single-vessel coronary model for rapid calculation of FFR. First, a zero-dimensional model of single-vessel coronary was established based on CCTA, and microcirculation resistance was determined through the relationship between coronary pressure and flow. In addition, a coronary stenosis model based on machine learning was introduced to determine stenosis resistance. Computational FFR (cFFR) was then obtained by combining the zero-dimensional model and the stenosis model with inlet boundary conditions for resting (cFFR_r) and hyperemic (cFFR_h) aortic pressure, respectively. We retrospectively analyzed 75 patients who underwent clinically invasive FFR (iFFR), and verified the model accuracy by comparison of cFFR with iFFR.

Results: The average computing time of cFFR was less than 2 s. The correlations between cFFR_r and cFFR_h with iFFR were r = 0.89 (p < 0.001) and r = 0.90 (p < 0.001), respectively. Diagnostic accuracy, sensitivity, specificity, positive predictive value, negative predictive value, positive likelihood ratio, negative likelihood ratio for cFFR_r and cFFR_h were 90.7%, 95.0%, 89.1%, 76.0%, 98.0%, 8.7, 0.1 and 92.0%, 95.0%, 90.9%, 79.2%, 98.0%, 10.5, 0.1, respectively.

Conclusions: The proposed model enables rapid prediction of cFFR and exhibits high diagnostic performance in selected patient cohorts. The model thus provides an accurate and time-efficient computational tool to detect ischemia-causing stenosis and assist with clinical decision-making.

Keywords: Coronary computed tomography angiography; Coronary stenosis model; Coronary zero-dimensional model; Fractional flow reserve; Machine learning.

MeSH terms

Constriction, Pathologic
Coronary Angiography / methods
Coronary Artery Disease*
Coronary Stenosis* / diagnostic imaging
Fractional Flow Reserve, Myocardial*
Humans
Ischemia
Predictive Value of Tests
Retrospective Studies