{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T20:31:49Z","timestamp":1793046709497,"version":"4.5.0"},"reference-count":24,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2023,1,3]],"date-time":"2023-01-03T00:00:00Z","timestamp":1672704000000},"content-version":"unspecified","delay-in-days":2,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Open Heart"],"accepted":{"date-parts":[[2022,12,14]]},"published-print":{"date-parts":[[2023,1]]},"abstract":"<jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>Angiographic parameters can facilitate the risk stratification of coronary lesions but remain insufficient in the prediction of future myocardial infarction (MI).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>AIMS<\/jats:title>\n                  <jats:p>We compared the ability of humans, angiographic parameters and deep learning (DL) to predict the lesion that would be responsible for a future MI in a population of patients with non-significant CAD at baseline.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>We retrospectively included patients who underwent invasive coronary angiography (ICA) for MI, in whom a previous angiogram had been performed within 5 years. The ability of human visual assessment, diameter stenosis, area stenosis, quantitative flow ratio (QFR) and DL to predict the future culprit lesion (FCL) was compared.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>In total, 746 cropped ICA images of FCL and non-culprit lesions (NCL) were analysed. Predictive models for each modality were developed in a training set before validation in a test set. DL exhibited the best predictive performance with an area under the curve of 0.81, compared with diameter stenosis (0.62, p=0.04), area stenosis (0.58, p=0.05) and QFR (0.67, p=0.13). DL exhibited a significant net reclassification improvement (NRI) compared with area stenosis (0.75, p=0.03) and QFR (0.95, p=0.01), and a positive nonsignificant NRI when compared with diameter stenosis. Among all models, DL demonstrated the highest accuracy (0.78) followed by QFR (0.70) and area stenosis (0.68). Predictions based on human visual assessment and diameter stenosis had the lowest accuracy (0.58).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>In this feasibility study, DL outperformed human visual assessment and established angiographic parameters in the prediction of FCLs. Larger studies are now required to confirm this finding.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1136\/openhrt-2022-002237","type":"journal-article","created":{"date-parts":[[2023,1,3]],"date-time":"2023-01-03T11:54:17Z","timestamp":1672746857000},"page":"e002237","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":22,"title":["Deep learning-based prediction of future myocardial infarction using invasive coronary angiography: a feasibility study"],"prefix":"10.1136","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0025-8162","authenticated-orcid":false,"given":"Thabo","family":"Mahendiran","sequence":"first","affiliation":[{"name":"Cardiology Department, Lausanne University Center Hospital, Lausanne, Switzerland"},{"name":"Chair of Mathematical Data Science and LTS4 laboratory, EPFL, Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dorina","family":"Thanou","sequence":"additional","affiliation":[{"name":"Chair of Mathematical Data Science and LTS4 laboratory, EPFL, Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ortal","family":"Senouf","sequence":"additional","affiliation":[{"name":"Chair of Mathematical Data Science and LTS4 laboratory, EPFL, Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Meier","sequence":"additional","affiliation":[{"name":"Cardiology Department, Lausanne University Center Hospital, Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolas","family":"Dayer","sequence":"additional","affiliation":[{"name":"Cardiology Department, Lausanne University Center Hospital, Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fahrang","family":"Aminfar","sequence":"additional","affiliation":[{"name":"Cardiology Department, Lausanne University Center Hospital, Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Denise","family":"Auberson","sequence":"additional","affiliation":[{"name":"Cardiology Department, Lausanne University Center Hospital, Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Omar","family":"Raita","sequence":"additional","affiliation":[{"name":"Chair of Mathematical Data Science and LTS4 laboratory, EPFL, Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pascal","family":"Frossard","sequence":"additional","affiliation":[{"name":"LTS4 laboratory, School of Engineering, EPFL, Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mattia","family":"Pagnoni","sequence":"additional","affiliation":[{"name":"Cardiology Department, Lausanne University Center Hospital, Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"St\u00e9phane","family":"Cook","sequence":"additional","affiliation":[{"name":"Cardiology Department, University and hospital Fribourg, Fribourg, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernard","family":"De Bruyne","sequence":"additional","affiliation":[{"name":"Cardiovascular Center OLV Aalst, Aalst, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olivier","family":"Muller","sequence":"additional","affiliation":[{"name":"Cardiology Department, Lausanne University Center Hospital, Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emmanuel","family":"Abb\u00e9","sequence":"additional","affiliation":[{"name":"Chair of Mathematical Data Science, Institute of Mathematics and School of Computer and Communication Sciences, EPFL, Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephane","family":"Fournier","sequence":"additional","affiliation":[{"name":"Cardiology Department, Lausanne University Center Hospital, Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2023,1,3]]},"reference":[{"key":"2025081612084174000_10.1.e002237.1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1408758"},{"key":"2025081612084174000_10.1.e002237.2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1803538"},{"key":"2025081612084174000_10.1.e002237.3","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.117.028782"},{"key":"2025081612084174000_10.1.e002237.4","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.119.041980"},{"key":"2025081612084174000_10.1.e002237.5","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-020-17804-2","article-title":"Machine learning-based prediction of acute coronary syndrome using only the pre-hospital 12-lead electrocardiogram","volume":"11","author":"Al-Zaiti","year":"2020","journal-title":"Nat Commun"},{"key":"2025081612084174000_10.1.e002237.6","doi-asserted-by":"crossref","first-page":"765","DOI":"10.4244\/EIJ-D-20-01155","article-title":"A deep learning algorithm for detecting acute myocardial infarction","volume":"17","author":"Liu","year":"2021","journal-title":"EuroIntervention"},{"key":"2025081612084174000_10.1.e002237.7","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-019-53254-7","article-title":"Deep learning segmentation of major vessels in X-ray coronary angiography","volume":"9","author":"Yang","year":"2019","journal-title":"Sci Rep"},{"key":"2025081612084174000_10.1.e002237.8","doi-asserted-by":"crossref","unstructured":"Cho H , Lee June\u2010Goo , Kang Soo\u2010Jin , Lee J , Kang S , et al . Angiography\u2010Based machine learning for predicting fractional flow reserve in intermediate coronary artery lesions. J Am Heart Assoc 2019;8 https:\/\/www.ahajournals.org\/doi\/ doi:10.1161\/JAHA.118.011685","DOI":"10.1161\/JAHA.118.011685"},{"key":"2025081612084174000_10.1.e002237.9","doi-asserted-by":"crossref","first-page":"1510","DOI":"10.3390\/math8091510","article-title":"Transfer learning for stenosis detection in X-ray coronary angiography","volume":"8","author":"Ovalle-Magallanes","year":"2020","journal-title":"Mathematics"},{"key":"2025081612084174000_10.1.e002237.10","unstructured":"Du T , Xie L , Zhang H . Automatic and multimodal analysis for coronary angiography: training and validation of a deep learning architecture. EuroIntervention https:\/\/eurointervention.pcronline.com\/article\/automatic-and-multimodal-analysis-for-coronary-angiography-training-and-validation-of-a-deep-learning-architecture"},{"key":"2025081612084174000_10.1.e002237.11","doi-asserted-by":"crossref","unstructured":"Min HS , Yoo J , Kang SJ . Detection of optical coherence tomography-defined thin-cap fibroatheroma in the coronary artery using deep learning. EuroIntervention 2021 https:\/\/eurointervention.pcronline.com\/article\/detection-of-optical-coherence-tomographydefined-thin-cap-fibroatheroma-in-the-coronary-artery-using-deep-learning","DOI":"10.4244\/EIJ-D-19-00487"},{"key":"2025081612084174000_10.1.e002237.12","first-page":"E388-E394","article-title":"Future culprit detection based on angiography-derived FFR","volume":"98","author":"Pagnoni","year":"2021","journal-title":"Catheter Cardiovasc Interv"},{"key":"2025081612084174000_10.1.e002237.13","doi-asserted-by":"crossref","unstructured":"He K , Zhang X , Ren S . Deep residual learning for image recognition, 2016: 770.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2025081612084174000_10.1.e002237.14","doi-asserted-by":"crossref","unstructured":"Deng J , Dong W , Socher R . ImageNet: a large-scale hierarchical image database.IEEE conference on computer vision and pattern recognition, 2009: 248\u201355.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2025081612084174000_10.1.e002237.15","unstructured":"Manning C , Raghavan P , Sch\u00fctze H . Introduction to information retrieval, 2021. https:\/\/nlp.stanford.edu\/IR-book\/information-retrieval-book.html"},{"key":"2025081612084174000_10.1.e002237.16","doi-asserted-by":"publisher","DOI":"10.1161\/01.CIR.53.4.627"},{"key":"2025081612084174000_10.1.e002237.17","doi-asserted-by":"publisher","DOI":"10.1016\/0735-1097(94)90388-3"},{"key":"2025081612084174000_10.1.e002237.18","doi-asserted-by":"publisher","DOI":"10.1136\/heart.89.9.961"},{"key":"2025081612084174000_10.1.e002237.19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2016.08.055"},{"key":"2025081612084174000_10.1.e002237.20","doi-asserted-by":"crossref","DOI":"10.1161\/JAHA.120.017729","article-title":"Global fractional flow reserve value predicts 5-year outcomes in patients with coronary atherosclerosis but without ischemia","volume":"9","author":"Fournier","year":"2020","journal-title":"J Am Heart Assoc"},{"key":"2025081612084174000_10.1.e002237.21","doi-asserted-by":"crossref","first-page":"985","DOI":"10.1016\/S0140-6736(21)00249-X","article-title":"Identification of vulnerable plaques and patients by intracoronary near-infrared spectroscopy and ultrasound (prospect II): a prospective natural history study","volume":"397","author":"Erlinge","year":"2021","journal-title":"The Lancet"},{"key":"2025081612084174000_10.1.e002237.22","doi-asserted-by":"crossref","unstructured":"Lee W , Lee J , Woo S-I , et al . Machine learning enhances the performance of short and long-term mortality prediction model in non-ST-segment elevation myocardial infarction. Sci Rep 2021;11.doi:10.1038\/s41598-021-92362-1","DOI":"10.1038\/s41598-021-92362-1"},{"key":"2025081612084174000_10.1.e002237.23","unstructured":"Goodfellow I , Bengio Y , Courville A . Deep Learning. In: Bach F , ed. Adaptive computation and machine learning series. Cambridge, MA, USA: MIT Press, 2016: 800 p."},{"key":"2025081612084174000_10.1.e002237.24","doi-asserted-by":"crossref","first-page":"213522","DOI":"10.1109\/ACCESS.2020.3040235","article-title":"A Convolutional neural network reaches optimal sensitivity for detecting some, but not all, patterns","volume":"8","author":"Reith","year":"2020","journal-title":"IEEE Access"}],"container-title":["Open Heart"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/openhrt-2022-002237","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T19:08:52Z","timestamp":1755371332000},"score":1,"resource":{"primary":{"URL":"https:\/\/openheart.bmj.com\/lookup\/doi\/10.1136\/openhrt-2022-002237"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":24,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,1,3]]},"published-print":{"date-parts":[[2023,1]]}},"alternative-id":["10.1136\/openhrt-2022-002237"],"URL":"https:\/\/doi.org\/10.1136\/openhrt-2022-002237","relation":{},"ISSN":["2053-3624"],"issn-type":[{"value":"2053-3624","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]}}}