Cited 527 times in
Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: a 5-year multicentre prospective registry analysis
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 장혁재 | - |
dc.date.accessioned | 2018-07-20T08:08:23Z | - |
dc.date.available | 2018-07-20T08:08:23Z | - |
dc.date.issued | 2017 | - |
dc.identifier.issn | 0195-668X | - |
dc.identifier.uri | https://ir.ymlib.yonsei.ac.kr/handle/22282913/160870 | - |
dc.description.abstract | Aims: Traditional prognostic risk assessment in patients undergoing non-invasive imaging is based upon a limited selection of clinical and imaging findings. Machine learning (ML) can consider a greater number and complexity of variables. Therefore, we investigated the feasibility and accuracy of ML to predict 5-year all-cause mortality (ACM) in patients undergoing coronary computed tomographic angiography (CCTA), and compared the performance to existing clinical or CCTA metrics. Methods and results: The analysis included 10 030 patients with suspected coronary artery disease and 5-year follow-up from the COronary CT Angiography EvaluatioN For Clinical Outcomes: An InteRnational Multicenter registry. All patients underwent CCTA as their standard of care. Twenty-five clinical and 44 CCTA parameters were evaluated, including segment stenosis score (SSS), segment involvement score (SIS), modified Duke index (DI), number of segments with non-calcified, mixed or calcified plaques, age, sex, gender, standard cardiovascular risk factors, and Framingham risk score (FRS). Machine learning involved automated feature selection by information gain ranking, model building with a boosted ensemble algorithm, and 10-fold stratified cross-validation. Seven hundred and forty-five patients died during 5-year follow-up. Machine learning exhibited a higher area-under-curve compared with the FRS or CCTA severity scores alone (SSS, SIS, DI) for predicting all-cause mortality (ML: 0.79 vs. FRS: 0.61, SSS: 0.64, SIS: 0.64, DI: 0.62; P< 0.001). Conclusions: Machine learning combining clinical and CCTA data was found to predict 5-year ACM significantly better than existing clinical or CCTA metrics alone. | - |
dc.description.statementOfResponsibility | open | - |
dc.language | English | - |
dc.publisher | Oxford University Press | - |
dc.relation.isPartOf | EUROPEAN HEART JOURNAL | - |
dc.rights | CC BY-NC-ND 2.0 KR | - |
dc.rights | https://creativecommons.org/licenses/by-nc-nd/2.0/kr/ | - |
dc.subject.MESH | Cause of Death | - |
dc.subject.MESH | Computed Tomography Angiography | - |
dc.subject.MESH | Coronary Artery Disease/diagnostic imaging | - |
dc.subject.MESH | Coronary Artery Disease/mortality* | - |
dc.subject.MESH | Feasibility Studies | - |
dc.subject.MESH | Female | - |
dc.subject.MESH | Humans | - |
dc.subject.MESH | Machine Learning | - |
dc.subject.MESH | Male | - |
dc.subject.MESH | Middle Aged | - |
dc.subject.MESH | Prospective Studies | - |
dc.subject.MESH | Registries | - |
dc.subject.MESH | Risk Factors | - |
dc.title | Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: a 5-year multicentre prospective registry analysis | - |
dc.type | Article | - |
dc.contributor.college | College of Medicine | - |
dc.contributor.department | Dept. of Internal Medicine | - |
dc.contributor.googleauthor | Manish Motwani | - |
dc.contributor.googleauthor | Damini Dey | - |
dc.contributor.googleauthor | Daniel S. Berman | - |
dc.contributor.googleauthor | Guido Germano | - |
dc.contributor.googleauthor | Stephan Achenbach | - |
dc.contributor.googleauthor | Mouaz H. Al-Mallah | - |
dc.contributor.googleauthor | Daniele Andreini | - |
dc.contributor.googleauthor | Matthew J. Budoff | - |
dc.contributor.googleauthor | Filippo Cademartiri | - |
dc.contributor.googleauthor | Tracy Q. Callister | - |
dc.contributor.googleauthor | Hyuk-Jae Chang | - |
dc.contributor.googleauthor | Kavitha Chinnaiyan | - |
dc.contributor.googleauthor | Benjamin J.W. Chow | - |
dc.contributor.googleauthor | Ricardo C. Cury | - |
dc.contributor.googleauthor | Augustin Delago | - |
dc.contributor.googleauthor | Millie Gomez | - |
dc.contributor.googleauthor | Heidi Gransar | - |
dc.contributor.googleauthor | Martin Hadamitzky | - |
dc.contributor.googleauthor | Joerg Hausleiter | - |
dc.contributor.googleauthor | Niree Hindoyan | - |
dc.contributor.googleauthor | Gudrun Feuchtner | - |
dc.contributor.googleauthor | Philipp A. Kaufmann | - |
dc.contributor.googleauthor | Yong-Jin Kim | - |
dc.contributor.googleauthor | Jonathon Leipsic | - |
dc.contributor.googleauthor | Fay Y. Lin | - |
dc.contributor.googleauthor | Erica Maffei | - |
dc.contributor.googleauthor | Hugo Marques | - |
dc.contributor.googleauthor | Gianluca Pontone | - |
dc.contributor.googleauthor | Gilbert Raff | - |
dc.contributor.googleauthor | Ronen Rubinshtein | - |
dc.contributor.googleauthor | Leslee J. Shaw | - |
dc.contributor.googleauthor | Julia Stehli | - |
dc.contributor.googleauthor | Todd C. Villines | - |
dc.contributor.googleauthor | Allison Dunning | - |
dc.contributor.googleauthor | James K. Min | - |
dc.contributor.googleauthor | Piotr J. Slomka | - |
dc.identifier.doi | 10.1093/eurheartj/ehw188 | - |
dc.contributor.localId | A03490 | - |
dc.relation.journalcode | J00805 | - |
dc.identifier.eissn | 1522-9645 | - |
dc.identifier.pmid | 27252451 | - |
dc.subject.keyword | Coronary CT angiography | - |
dc.subject.keyword | Coronary artery disease | - |
dc.subject.keyword | Machine learning | - |
dc.subject.keyword | Prognosis | - |
dc.contributor.alternativeName | Chang, Hyuck Jae | - |
dc.contributor.affiliatedAuthor | Chang, Hyuck Jae | - |
dc.citation.volume | 38 | - |
dc.citation.number | 7 | - |
dc.citation.startPage | 500 | - |
dc.citation.endPage | 507 | - |
dc.identifier.bibliographicCitation | EUROPEAN HEART JOURNAL, Vol.38(7) : 500-507, 2017 | - |
dc.identifier.rimsid | 60754 | - |
dc.type.rims | ART | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.