4
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Angiography‐Based Machine Learning for Predicting Fractional Flow Reserve in Intermediate Coronary Artery Lesions

      research-article
      , BS 1 , , PhD 2 , , MD, PhD 1 , , , MD 3 , , MD 4 , , BS 2 , , PhD 1 , , BS 1 , , MD 1 , , MD 1 , , MD 1 , , MD 1 , , MD 1 , , MD 1 , , MD 1 , , MD 1 , , MD 1
      Journal of the American Heart Association: Cardiovascular and Cerebrovascular Disease
      John Wiley and Sons Inc.
      artificial intelligence, coronary angiography, fractional flow reserve, machine learning, Diagnostic Testing, Imaging, Angiography, Catheter-Based Coronary and Valvular Interventions, Coronary Artery Disease

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Background

          An angiography‐based supervised machine learning ( ML) algorithm was developed to classify lesions as having fractional flow reserve ≤0.80 versus >0.80.

          Methods and Results

          With a 4:1 ratio, 1501 patients with 1501 intermediate lesions were randomized into training versus test sets. Between the ostium and 10 mm distal to the target lesion, a series of angiographic lumen diameter measurements along the centerline was plotted. The 24 computed angiographic features based on the diameter plot and 4 clinical features (age, sex, body surface area, and involve segment) were used for ML by XGBoost. The model was independently trained and tested by 2000 bootstrap iterations. External validation with 79 patients was conducted. Including all 28 features, the ML model with 5‐fold cross‐validation in the 1204 training samples predicted fractional flow reserve ≤0.80 with overall diagnostic accuracy of 78±4% (averaged area under the curve: 0.84±0.03). The 12 high‐ranking features selected by scatter search were involved segment; body surface area; distal lumen diameter; minimal lumen diameter; length of a lumen diameter <2.0 mm, <1.5 mm, and <1.25 mm; mean lumen diameter within the worst segment; sex; diameter stenosis; distal 5‐mm reference lumen diameter; and length of diameter stenosis >70%. Using those 12 features, the ML predicted fractional flow reserve ≤0.80 in the test set with sensitivity of 84%, specificity of 80%, and overall accuracy of 82% (area under the curve: 0.87). The averaged diagnostic accuracy in bootstrap replicates was 81±1% (averaged area under the curve: 0.87±0.01). External validation showed accuracy of 85% (area under the curve: 0.87).

          Conclusions

          Angiography‐based ML showed good diagnostic performance in identifying ischemia‐producing lesions and reduced the need for pressure wires.

          Related collections

          Most cited references13

          • Record: found
          • Abstract: found
          • Article: not found

          Measurement of fractional flow reserve to assess the functional severity of coronary-artery stenoses.

          The clinical significance of coronary-artery stenoses of moderate severity can be difficult to determine. Myocardial fractional flow reserve (FFR) is a new index of the functional severity of coronary stenoses that is calculated from pressure measurements made during coronary arteriography. We compared this index with the results of noninvasive tests commonly used to detect myocardial ischemia, to determine the usefulness of the index. In 45 consecutive patients with moderate coronary stenosis and chest pain of uncertain origin, we performed bicycle exercise testing, thallium scintigraphy, stress echocardiography with dobutamine, and quantitative coronary arteriography and compared the results with measurements of FFR. In all 21 patients with an FFR of less than 0.75, reversible myocardial ischemia was demonstrated unequivocally on at least one noninvasive test. After coronary angioplasty or bypass surgery was performed, all the positive test results reverted to normal. In contrast, 21 of the 24 patients with an FFR of 0.75 or higher tested negative for reversible myocardial ischemia on all the noninvasive tests. No revascularization procedures were performed in these patients, and none were required during 14 months of follow-up. The sensitivity of FFR in the identification of reversible ischemia was 88 percent, the specificity 100 percent, the positive predictive value 100 percent, the negative predictive value 88 percent, and the accuracy 93 percent. In patients with coronary stenosis of moderate severity, FFR appears to be a useful index of the functional severity of the stenoses and the need for coronary revascularization.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Artificial Intelligence in Precision Cardiovascular Medicine.

            Artificial intelligence (AI) is a field of computer science that aims to mimic human thought processes, learning capacity, and knowledge storage. AI techniques have been applied in cardiovascular medicine to explore novel genotypes and phenotypes in existing diseases, improve the quality of patient care, enable cost-effectiveness, and reduce readmission and mortality rates. Over the past decade, several machine-learning techniques have been used for cardiovascular disease diagnosis and prediction. Each problem requires some degree of understanding of the problem, in terms of cardiovascular medicine and statistics, to apply the optimal machine-learning algorithm. In the near future, AI will result in a paradigm shift toward precision cardiovascular medicine. The potential of AI in cardiovascular medicine is tremendous; however, ignorance of the challenges may overshadow its potential clinical impact. This paper gives a glimpse of AI's application in cardiovascular clinical care and discusses its potential role in facilitating precision cardiovascular medicine.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Diagnostic Accuracy of Fast Computational Approaches to Derive Fractional Flow Reserve From Diagnostic Coronary Angiography: The International Multicenter FAVOR Pilot Study.

              The aim of this prospective multicenter study was to identify the optimal approach for simple and fast fractional flow reserve (FFR) computation from radiographic coronary angiography, called quantitative flow ratio (QFR).
                Bookmark

                Author and article information

                Contributors
                sjkang@amc.seoul.kr
                Journal
                J Am Heart Assoc
                J Am Heart Assoc
                10.1002/(ISSN)2047-9980
                JAH3
                ahaoa
                Journal of the American Heart Association: Cardiovascular and Cerebrovascular Disease
                John Wiley and Sons Inc. (Hoboken )
                2047-9980
                15 February 2019
                19 February 2019
                : 8
                : 4 ( doiID: 10.1002/jah3.2019.8.issue-4 )
                : e011685
                Affiliations
                [ 1 ] Department of Cardiology University of Ulsan College of Medicine Asan Medical Center Seoul Korea
                [ 2 ] Biomedical Engineering Research Center Asan Institute for Life Sciences Seoul Korea
                [ 3 ] Department of Cardiology CHA Bundang Medical Center CHA University Seongnam Korea
                [ 4 ] Department of Cardiology Ajou University Suwon Korea
                Author notes
                [*] [* ] Correspondence to: Soo‐Jin Kang, MD, PhD, Department of Cardiology, Asan Medical Center, University of Ulsan College of Medicine, 88, Olympic‐ro 43‐gil, Songpa‐gu, Seoul 05505, Korea. E‐mail: sjkang@ 123456amc.seoul.kr
                [†]

                Dr Cho and Dr June‐Goo Lee equally contributed to this work as co‐first authors.

                Article
                JAH33847
                10.1161/JAHA.118.011685
                6405668
                30764731
                2e7209d5-8503-49b6-b8ff-d95b01fe2c9d
                © 2019 The Authors. Published on behalf of the American Heart Association, Inc., by Wiley.

                This is an open access article under the terms of the http://creativecommons.org/licenses/by-nc-nd/4.0/ License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non‐commercial and no modifications or adaptations are made.

                History
                : 12 December 2018
                : 04 January 2019
                Page count
                Figures: 3, Tables: 4, Pages: 18, Words: 6577
                Funding
                Funded by: Ministry for Health & Welfare Affairs, Republic of Korea
                Award ID: HI15C1790
                Award ID: HI17C1080
                Funded by: Ministry of Science and ICT
                Award ID: NRF‐2017R1A2B4005886
                Funded by: Asan Institute for Life Sciences, Asan Medical Center, Seoul, Korea
                Award ID: 2017‐0745
                Categories
                Original Research
                Original Research
                Coronary Heart Disease
                Custom metadata
                2.0
                jah33847
                19 February 2019
                Converter:WILEY_ML3GV2_TO_NLMPMC version:5.5.9 mode:remove_FC converted:19.02.2019

                Cardiovascular Medicine
                artificial intelligence,coronary angiography,fractional flow reserve,machine learning,diagnostic testing,imaging,angiography,catheter-based coronary and valvular interventions,coronary artery disease

                Comments

                Comment on this article