Cited 0 times in Scipus Cited Count

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

DC Field Value Language
dc.contributor.authorCho, H-
dc.contributor.authorLee, JG-
dc.contributor.authorKang, SJ-
dc.contributor.authorKim, WJ-
dc.contributor.authorChoi, SY-
dc.contributor.authorKo, J-
dc.contributor.authorMin, HS-
dc.contributor.authorChoi, GH-
dc.contributor.authorKang, DY-
dc.contributor.authorLee, PH-
dc.contributor.authorAhn, JM-
dc.contributor.authorPark, DW-
dc.contributor.authorLee, SW-
dc.contributor.authorKim, YH-
dc.contributor.authorLee, CW-
dc.contributor.authorPark, SW-
dc.contributor.authorPark, SJ-
dc.date.accessioned2020-10-21T07:21:08Z-
dc.date.available2020-10-21T07:21:08Z-
dc.date.issued2019-
dc.identifier.urihttp://repository.ajou.ac.kr/handle/201003/18864-
dc.description.abstractBACKGROUND: An angiography-based supervised machine learning ( ML ) algorithm was developed to classify lesions as having fractional flow reserve 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 70%. Using those 12 features, the ML predicted fractional flow reserve CONCLUSIONS: Angiography-based ML showed good diagnostic performance in identifying ischemia-producing lesions and reduced the need for pressure wires.
-
dc.language.isoen-
dc.subject.MESHAlgorithms-
dc.subject.MESHCoronary Angiography-
dc.subject.MESHCoronary Stenosis-
dc.subject.MESHCoronary Vessels-
dc.subject.MESHFemale-
dc.subject.MESHFractional Flow Reserve, Myocardial-
dc.subject.MESHHumans-
dc.subject.MESHImaging, Three-Dimensional-
dc.subject.MESHMachine Learning-
dc.subject.MESHMale-
dc.subject.MESHMiddle Aged-
dc.subject.MESHROC Curve-
dc.subject.MESHRetrospective Studies-
dc.subject.MESHSeverity of Illness Index-
dc.titleAngiography-Based Machine Learning for Predicting Fractional Flow Reserve in Intermediate Coronary Artery Lesions-
dc.typeArticle-
dc.identifier.pmid30764731-
dc.identifier.urlhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC6405668/-
dc.subject.keywordartificial intelligence-
dc.subject.keywordcoronary angiography-
dc.subject.keywordfractional flow reserve-
dc.subject.keywordmachine learning-
dc.contributor.affiliatedAuthor최, 소연-
dc.type.localJournal Papers-
dc.identifier.doi10.1161/JAHA.118.011685-
dc.citation.titleJournal of the American Heart Association-
dc.citation.volume8-
dc.citation.number4-
dc.citation.date2019-
dc.citation.startPagee011685-
dc.citation.endPagee011685-
dc.identifier.bibliographicCitationJournal of the American Heart Association, 8(4). : e011685-e011685, 2019-
dc.identifier.eissn2047-9980-
dc.relation.journalidJ020479980-
Appears in Collections:
Journal Papers > School of Medicine / Graduate School of Medicine > Cardiology
Files in This Item:
30764731.pdfDownload

qrcode

해당 아이템을 이메일로 공유하기 원하시면 인증을 거치시기 바랍니다.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse