Back to Search
Start Over
Impact of machine learning-based coronary computed tomography angiography fractional flow reserve on treatment decisions and clinical outcomes in patients with suspected coronary artery disease.
- Source :
-
European radiology [Eur Radiol] 2020 Nov; Vol. 30 (11), pp. 5841-5851. Date of Electronic Publication: 2020 May 28. - Publication Year :
- 2020
-
Abstract
- Objectives: This study investigated the impact of machine learning (ML)-based fractional flow reserve derived from computed tomography (FFR <subscript>CT</subscript> ) compared to invasive coronary angiography (ICA) for therapeutic decision-making and patient outcome in patients with suspected coronary artery disease (CAD).<br />Methods: One thousand one hundred twenty-one consecutive patients with stable chest pain who underwent coronary computed tomography angiography (CCTA) followed ICA within 90 days between January 2007 and December 2016 were included in this retrospective study. Medical records were reviewed for the endpoint of major adverse cardiac events (MACEs). FFR <subscript>CT</subscript> values were calculated using an artificial intelligence (AI) ML platform. Disagreements between hemodynamic significant stenosis via FFR <subscript>CT</subscript> and severe stenosis on qualitative CCTA and ICA were also evaluated.<br />Results: After FFR <subscript>CT</subscript> results were revealed, a change in the proposed treatment regimen chosen based on ICA results was seen in 167 patients (14.9%). Over a median follow-up time of 26 months (4-48 months), FFR <subscript>CT</subscript> ≤ 0.80 was associated with MACE (HR, 6.84 (95% CI, 3.57 to 13.11); p < 0.001), with superior prognostic value compared to severe stenosis on ICA (HR, 1.84 (95% CI, 1.24 to 2.73), p = 0.002) and CCTA (HR, 1.47 (95% CI, 1.01 to 2.14, p = 0.045). Reserving ICA and revascularization for vessels with positive FFR <subscript>CT</subscript> could have reduced the rate of ICA by 54.5% and lead to 4.4% fewer percutaneous interventions.<br />Conclusions: This study indicated ML-based FFR <subscript>CT</subscript> had superior prognostic value when compared to severe anatomic stenosis on CCTA and adding FFR <subscript>CT</subscript> may direct therapeutic decision-making with the potential to improve efficiency of ICA.<br />Key Points: • ML-based FFR <subscript>CT</subscript> shows superior outcome prediction value when compared to severe anatomic stenosis on CCTA. • FFR <subscript>CT</subscript> noninvasively informs therapeutic decision-making with potential to change diagnostic workflows and enhance efficiencies in patients with suspected CAD. • Reserving ICA and revascularization for vessels with positive FFR <subscript>CT</subscript> may reduce the normalcy rate of ICA and improve its efficiency.
- Subjects :
- Artificial Intelligence
Coronary Artery Disease physiopathology
Coronary Artery Disease therapy
Female
Humans
Male
Middle Aged
Predictive Value of Tests
Retrospective Studies
Severity of Illness Index
Computed Tomography Angiography methods
Coronary Angiography methods
Coronary Artery Disease diagnosis
Decision Making
Disease Management
Fractional Flow Reserve, Myocardial physiology
Machine Learning
Subjects
Details
- Language :
- English
- ISSN :
- 1432-1084
- Volume :
- 30
- Issue :
- 11
- Database :
- MEDLINE
- Journal :
- European radiology
- Publication Type :
- Academic Journal
- Accession number :
- 32462444
- Full Text :
- https://doi.org/10.1007/s00330-020-06964-w