Dataset Information

Optical coherence tomography-based machine learning for predicting fractional flow reserve in intermediate coronary stenosis: a feasibility study.

ABSTRACT: Machine learning approaches using intravascular optical coherence tomography (OCT) to predict fractional flow reserve (FFR) have not been investigated. Both OCT and FFR data were obtained for left anterior descending artery lesions in 125 patients. Training and testing groups were partitioned in the ratio of 5:1. The OCT-based machine learning-FFR was derived for the testing group and compared with wire-based FFR in terms of ischemia diagnosis (FFR???0.8). The OCT-based machine learning-FFR showed good correlation (r?=?0.853, P?

SUBMITTER: Cha JJ

PROVIDER: S-EPMC7686372 | biostudies-literature | 2020 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Optical coherence tomography-based machine learning for predicting fractional flow reserve in intermediate coronary stenosis: a feasibility study.

Cha Jung-Joon JJ Son Tran Dinh TD Ha Jinyong J Kim Jung-Sun JS Hong Sung-Jin SJ Ahn Chul-Min CM Kim Byeong-Keuk BK Ko Young-Guk YG Choi Donghoon D Hong Myeong-Ki MK Jang Yangsoo Y

Scientific reports 20201124 1

Machine learning approaches using intravascular optical coherence tomography (OCT) to predict fractional flow reserve (FFR) have not been investigated. Both OCT and FFR data were obtained for left anterior descending artery lesions in 125 patients. Training and testing groups were partitioned in the ratio of 5:1. The OCT-based machine learning-FFR was derived for the testing group and compared with wire-based FFR in terms of ischemia diagnosis (FFR ≤ 0.8). The OCT-based machine learning-FFR show ...[more]

PMID: 33235309

Similar Datasets

Project description:The management of patients with angiographically intermediate coronary lesions is a major clinical issue. Fractional flow reserve provides validated functional insights while optical coherence tomography provides high resolution anatomic imaging. Both techniques may be applied to guide management in case of angiographically intermediate coronary lesions. Moreover, these techniques may be used to optimize the result of percutaneous coronary intervention. We aim to compare the clinical and economic impact of fractional flow reserve versus optical coherence tomography guidance in patients with angiographically intermediate coronary lesions.Patients with at least one angiographically intermediate coronary lesion will be randomized (ratio 1:1) to fractional flow reserve or optical coherence tomography guidance. In the fractional flow reserve arm, percutaneous coronary intervention will be performed if fractional flow reserve value is ?0.80, and will be conducted with the aim of achieving a post-percutaneous coronary intervention fractional flow reserve target value of ?0.90. In the optical coherence tomography arm, percutaneous coronary intervention will be performed if percentage of area stenosis (AS%) is ?75% or 50 to 75% with minimal lumen area <2.5 mm2, or if a major plaque ulceration is detected. In case of percutaneous coronary intervention, optical coherence tomography will guide the procedure in order to minimize under-expansion, malapposition, and edge dissections.Cost load and clinical outcome will be prospectively assessed at one and thirteen months. The assessed clinical outcome measures will be: major cardiovascular events and occurrence of significant angina defined as a Seattle Angina Questionnaire score <90 in the angina frequency scale.The FORZA trial will provide useful guidance for the management of patients with coronary artery disease by prospectively assessing the use of two techniques representing the gold standard for functional and anatomical definition of coronary plaques.Clinicaltrials.gov NCT01824030.

Project description:Background Fractional flow reserve (FFR) and optical coherence tomography (OCT) may help both in assessment and in percutaneous coronary intervention optimization of angiographically intermediate coronary lesions. We designed a prospective trial comparing the clinical and economic outcomes associated with FFR or OCT in angiographically intermediate coronary lesions. Methods and Results Three hundred fifty patients with angiographically intermediate coronary lesions (n=446) were randomized to FFR or OCT guidance. In the FFR arm, percutaneous coronary intervention was performed if FFR was ≤0.80 aiming for a postprocedure FFR >0.90. In the OCT arm, percutaneous coronary intervention was performed if percentage of area stenosis was ≥75% or 50% to 75% with minimal lumen area <2.5 mm2 or plaque ulceration. Costs, angina frequency, and major adverse cardiac events were assessed at 1 month and at 13 months. We present early data at 1 month consistent with a prespecified analysis of secondary end points. Patients randomized to FFR, as compared with OCT, were significantly more commonly managed with medical therapy alone (67.7% versus 41.1%; P<0.001), required less contrast media (245±137 versus 280±129 mL; P=0.004), and exhibited a lower occurrence of contrast-induced acute kidney injury (1.7% versus 8.6%; P=0.034). At 1 month, in comparison to FFR, OCT was associated with increased total costs (2831±1288 versus 4292±3844 euros/patient; P<0.001) whereas occurrence of major adverse cardiac events or significant angina was similar. Conclusions In patients with angiographically intermediate coronary lesions, a functional guidance by FFR, as compared with OCT, increased the rate of patients treated with medical therapy alone. This translated into a significant reduction in administered contrast, contrast-induced acute kidney injury, and total costs at 1 month with FFR. Clinical Trial Registration URL: http://www.clinicaltrialsgov. Unique identifier: NCT01824030.

Project description:BackgroundCoronary artery disease is common in patients with severe aortic stenosis. Computed tomography-derived fractional flow reserve (CT-FFR) is a clinically used modality for assessing coronary artery disease, however, its use has not been validated in patients with severe aortic stenosis. This study assesses the safety, feasibility, and validity of CT-FFR in patients with severe aortic stenosis.MethodsProspectively recruited patients underwent standard-protocol invasive FFR and coronary CT angiography (CTA). CTA images were analyzed by central core laboratory (HeartFlow, Inc) for independent evaluation of CT-FFR. CT-FFR data were compared with FFR (ischemia defined as FFR ≤0.80).ResultsForty-two patients (68 vessels) underwent FFR and CTA; 39 patients (92.3%) and 60 vessels (88.2%) had interpretable CTA enabling CT-FFR computation. Mean age was 76.2±6.7 years (71.8% male). No patients incurred complications relating to premedication, CTA, or FFR protocol. Mean FFR and CT-FFR were 0.83±0.10 and 0.77±0.14, respectively. CT calcium score was 1373.3±1392.9 Agatston units. On per vessel analysis, there was positive correlation between FFR and CT-FFR (Pearson correlation coefficient, R=0.64, P<0.0001). Sensitivity, specificity, positive predictive value, and negative predictive values were 73.9%, 78.4%, 68.0%, and 82.9%, respectively, with 76.7% diagnostic accuracy. The area under the receiver-operating characteristic curve for CT-FFR was 0.83 (0.72-0.93, P<0.0001), which was higher than that of CTA and quantitative coronary angiography (P=0.01 and P<0.001, respectively). Bland-Altman plot showed mean bias between FFR and CT-FFR as 0.059±0.110. On per patient analysis, the sensitivity, specificity, positive predictive, and negative predictive values were 76.5%, 77.3%, 72.2%, and 81.0% with 76.9% diagnostic accuracy. The per patient area under the receiver-operating characteristic curve analysis was 0.81 (0.67-0.95, P<0.0001).ConclusionsCT-FFR is safe and feasible in patients with severe aortic stenosis. Our data suggests that the diagnostic accuracy of CT-FFR in this cohort potentially enables its use in clinical practice and provides the foundation for future research into the use of CT-FFR for coronary evaluation pre-aortic valve replacement.

Dataset Information

Optical coherence tomography-based machine learning for predicting fractional flow reserve in intermediate coronary stenosis: a feasibility study.

Publications

Optical coherence tomography-based machine learning for predicting fractional flow reserve in intermediate coronary stenosis: a feasibility study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets