{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T04:17:39Z","timestamp":1776399459917,"version":"3.51.2"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,1,24]],"date-time":"2020-01-24T00:00:00Z","timestamp":1579824000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,1,24]],"date-time":"2020-01-24T00:00:00Z","timestamp":1579824000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"American College of Cardiology\/ Merck Research Fellowship"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"Abstract<\/jats:title>\n \n Echocardiography uses ultrasound technology to capture high temporal and spatial resolution images of the heart and surrounding structures, and is the most common imaging modality in cardiovascular medicine. Using convolutional neural networks on a large new dataset, we show that deep learning applied to echocardiography can identify local cardiac structures, estimate cardiac function, and predict systemic phenotypes that modify cardiovascular risk but not readily identifiable to human interpretation. Our deep learning model, EchoNet, accurately identified the presence of pacemaker leads (AUC\u2009=\u20090.89), enlarged left atrium (AUC\u2009=\u20090.86), left ventricular hypertrophy (AUC\u2009=\u20090.75), left ventricular end systolic and diastolic volumes (\n \n \n $${R}^{2}$$<\/jats:tex-math>\n \n \n \n R<\/mml:mi>\n <\/mml:mrow>\n \n 2<\/mml:mn>\n <\/mml:mrow>\n <\/mml:msup>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n \u2009=\u20090.74 and\n \n \n $${R}^{2}$$<\/jats:tex-math>\n \n \n \n R<\/mml:mi>\n <\/mml:mrow>\n \n 2<\/mml:mn>\n <\/mml:mrow>\n <\/mml:msup>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n \u2009=\u20090.70), and ejection fraction (\n \n \n $${R}^{2}$$<\/jats:tex-math>\n \n \n \n R<\/mml:mi>\n <\/mml:mrow>\n \n 2<\/mml:mn>\n <\/mml:mrow>\n <\/mml:msup>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n \u2009=\u20090.50), as well as predicted systemic phenotypes of age (\n \n \n $${R}^{2}$$<\/jats:tex-math>\n \n \n \n R<\/mml:mi>\n <\/mml:mrow>\n \n 2<\/mml:mn>\n <\/mml:mrow>\n <\/mml:msup>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n \u2009=\u20090.46), sex (AUC\u2009=\u20090.88), weight (\n \n \n $${R}^{2}$$<\/jats:tex-math>\n \n \n \n R<\/mml:mi>\n <\/mml:mrow>\n \n 2<\/mml:mn>\n <\/mml:mrow>\n <\/mml:msup>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n \u2009=\u20090.56), and height (\n \n \n $${R}^{2}$$<\/jats:tex-math>\n \n \n \n R<\/mml:mi>\n <\/mml:mrow>\n \n 2<\/mml:mn>\n <\/mml:mrow>\n <\/mml:msup>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n \u2009=\u20090.33). Interpretation analysis validates that EchoNet shows appropriate attention to key cardiac structures when performing human-explainable tasks and highlights hypothesis-generating regions of interest when predicting systemic phenotypes difficult for human interpretation. Machine learning on echocardiography images can streamline repetitive tasks in the clinical workflow, provide preliminary interpretation in areas with insufficient qualified cardiologists, and predict phenotypes challenging for human evaluation.\n <\/jats:p>","DOI":"10.1038\/s41746-019-0216-8","type":"journal-article","created":{"date-parts":[[2020,1,24]],"date-time":"2020-01-24T06:03:17Z","timestamp":1579845797000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":414,"title":["Deep learning interpretation of echocardiograms"],"prefix":"10.1038","volume":"3","author":[{"given":"Amirata","family":"Ghorbani","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3813-7518","authenticated-orcid":false,"given":"David","family":"Ouyang","sequence":"additional","affiliation":[]},{"given":"Abubakar","family":"Abid","sequence":"additional","affiliation":[]},{"given":"Bryan","family":"He","sequence":"additional","affiliation":[]},{"given":"Jonathan H.","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Robert A.","family":"Harrington","sequence":"additional","affiliation":[]},{"given":"David H.","family":"Liang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9418-9577","authenticated-orcid":false,"given":"Euan A.","family":"Ashley","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8880-4764","authenticated-orcid":false,"given":"James Y.","family":"Zou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,1,24]]},"reference":[{"key":"216_CR1","doi-asserted-by":"publisher","first-page":"933","DOI":"10.1161\/CIR.0b013e31820a55f5","volume":"123","author":"P Heidenreich","year":"2011","unstructured":"Heidenreich, P. et al. Forecasting the future of cardiovascular disease in the united states: a policy statement from the american heart association. Circulation 123, 933\u2013944 (2011).","journal-title":"Circulation"},{"key":"216_CR2","doi-asserted-by":"publisher","first-page":"2294","DOI":"10.1161\/CIRCULATIONAHA.109.922286","volume":"121","author":"M Cohen","year":"2010","unstructured":"Cohen, M. et al. Racial and ethnic differences in the treatment of acute myocardial infarction: findings from the get with the guidelines-coronary artery disease program. Circulation 121, 2294\u20132301 (2010).","journal-title":"Circulation"},{"key":"216_CR3","doi-asserted-by":"publisher","first-page":"873","DOI":"10.1161\/CIR.0000000000000228","volume":"132","author":"E Havranek","year":"2015","unstructured":"Havranek, E. et al. Social determinants of risk and outcomes of cardiovascular disease a scientific statement from the american heart association. Circulation 132, 873\u2013898 (2015).","journal-title":"Circulation"},{"key":"216_CR4","first-page":"502","volume":"67","author":"A Madani","year":"2016","unstructured":"Madani, A., Ong, J. R., Tiberwal, A. & Mofrad, M. R. US hospital use of echocardiography: Insights from the nationwide inpatient sample. J. Am. Coll. Cardiol. 67, 502\u2013511 (2016).","journal-title":"J. Am. Coll. Cardiol."},{"key":"216_CR5","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1161\/CIRCULATIONAHA.118.034338","volume":"138","author":"J Zhang","year":"2018","unstructured":"Zhang, J. et al. Fully automated echocardiogram interpretation in clinical practice: feasibility and diagnostic accuracy. Circulation 138, 1623\u20131635 (2018).","journal-title":"Circulation"},{"key":"216_CR6","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-018-0065-x","volume":"1","author":"A Madani","year":"2018","unstructured":"Madani, A., Ong, J. R., Tiberwal, A. & Mofrad, M. R. Deep echocardiography: data-efficient supervised and semisupervised deep learning towards automated diagnosis of cardiac disease. npj Digital Med. 1, 59 (2018).","journal-title":"npj Digital Med."},{"key":"216_CR7","doi-asserted-by":"publisher","first-page":"2507","DOI":"10.1056\/NEJMp1702071","volume":"376","author":"JH Chen","year":"2017","unstructured":"Chen, J. H. & Asch, S. M. Machine learning and prediction in medicine-beyond the peak of inflated expectations. N. Engl. J. Med. 376, 2507 (2017).","journal-title":"N. Engl. J. Med."},{"key":"216_CR8","doi-asserted-by":"crossref","unstructured":"Dong, C., Loy, C.C., He, K. & Tang, X. Learning a deep convolutional network for image super-resolution. in European conference on computer vision, 184\u2013199 (Springer, 2014).","DOI":"10.1007\/978-3-319-10593-2_13"},{"key":"216_CR9","doi-asserted-by":"crossref","unstructured":"Russakovsky, O. et al. Imagenet large scale visual recognition challenge. Int. j. comp. vis. 115, 211\u2013252 (2015).","DOI":"10.1007\/s11263-015-0816-y"},{"key":"216_CR10","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V. & Alemi, A.A., Inception-v4, inception-resnet and the impact of residual connections on learning. In Thirty-First AAAI Conference on Artificial Intelligence (AAAI.org, 2017).","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"216_CR11","doi-asserted-by":"crossref","unstructured":"Karpathy, A. et al. Large-scale video classification with convolutional neural networks. In Proc. of the IEEE conference on Computer Vision and Pattern Recognition, 1725\u20131732 (IEEE, 2014).","DOI":"10.1109\/CVPR.2014.223"},{"key":"216_CR12","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1038\/s41551-018-0195-0","volume":"2","author":"R Poplin","year":"2018","unstructured":"Poplin, R. et al. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nat. Biomed. Eng. 2, 158 (2018).","journal-title":"Nat. Biomed. Eng."},{"key":"216_CR13","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","volume":"542","author":"A Esteva","year":"2017","unstructured":"Esteva, A. et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115 (2017).","journal-title":"Nature"},{"key":"216_CR14","doi-asserted-by":"publisher","first-page":"1559","DOI":"10.1038\/s41591-018-0177-5","volume":"24","author":"N Coudray","year":"2018","unstructured":"Coudray, N. et al. Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning. Nat. Med. 24, 1559 (2018).","journal-title":"Nat. Med."},{"key":"216_CR15","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1038\/s41592-018-0111-2","volume":"15","author":"C Ounkomol","year":"2018","unstructured":"Ounkomol, C., Seshamani, S., Maleckar, M. M., Collman, F. & Johnson, G. R. Label-free prediction of three-dimensional fluorescence images from transmitted-light microscopy. Nat. Methods 15, 917 (2018).","journal-title":"Nat. Methods"},{"key":"216_CR16","doi-asserted-by":"crossref","unstructured":"Nagpal, K. et al. Development and validation of a deep learning algorithm for improving Gleason scoring of prostate cancer. npj Digit. Med. 2, 48 (2019).","DOI":"10.1038\/s41746-019-0196-8"},{"key":"216_CR17","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1016\/j.echo.2010.12.008","volume":"24","author":"P Douglas","year":"2011","unstructured":"Douglas, P. et al. Accf\/ase\/aha\/asnc\/hfsa\/hrs\/scai\/sccm\/scct\/scmr 2011 appropriate use criteria for echocardiography. J. Am. Soc. Echocardiogr. 24, 229\u2013267 (2011).","journal-title":"J. Am. Soc. Echocardiogr."},{"key":"216_CR18","doi-asserted-by":"crossref","unstructured":"Wood, P.W., Choy, J.B., Nanda, N.C. & Becher, H. Left ventricular ejection fraction and volumes: it depends on the imaging method. Echocardiography 31, 87\u2013100 (2014).","DOI":"10.1111\/echo.12331"},{"key":"216_CR19","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1186\/s12947-015-0015-6","volume":"13","author":"DD Geer","year":"2015","unstructured":"Geer, D. D., Oscarsson, A. & Engvall, J. Variability in echocardiographic measurements of left ventricular function in septic shock patients. J. Cardiovasc Ultrasound. 13, 19 (2015).","journal-title":"J. Cardiovasc Ultrasound."},{"key":"216_CR20","doi-asserted-by":"publisher","first-page":"1622","DOI":"10.1111\/jvim.14846","volume":"31","author":"A JA","year":"2017","unstructured":"JA, A. & JM, G.-S. Echocardiographic variables used to estimate pulmonary artery pressure in dogs. J. Vet. Intern. Med. 31, 1622\u20131628 (2017).","journal-title":"J. Vet. Intern. Med."},{"key":"216_CR21","unstructured":"2019 ACC\/AHA\/ASE advanced training statement on echocardiography (Revision of the 2003 ACC\/AHA Clinical Competence Statement on Echocardiography): a report of the ACC competency management committee. J. Am. Coll. Cardiol. 19, S0735\u2013S1097 (2019)"},{"key":"216_CR22","doi-asserted-by":"publisher","first-page":"26","DOI":"10.7326\/0003-4819-152-1-201001050-00007","volume":"152","author":"F MK","year":"2010","unstructured":"MK, F., WS, B. & DN, W. Systematic review: prediction of perioperative cardiac complications and mortality by the revised cardiac risk index. Ann. Intern. Med. 152, 26\u201335 (2010).","journal-title":"Ann. Intern. Med."},{"key":"216_CR23","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1001\/jamacardio.2016.3841","volume":"2","author":"H Abdel-Qadir","year":"2017","unstructured":"Abdel-Qadir, H. et al. A population-based study of cardiovascular mortality following early-stage breast cancer. JAMA Cardiol. 2, 88\u201393 (2017).","journal-title":"JAMA Cardiol."},{"key":"216_CR24","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-017-0013-1","volume":"1","author":"A Madani","year":"2018","unstructured":"Madani, A., Arnaout, R., Mofrad, M. & Arnaout, R. Fast and accurate view classification of echocardiograms using deep learning. npj Digital Med. 1, 6 (2018).","journal-title":"npj Digital Med."},{"key":"216_CR25","unstructured":"Smilkov, D., Thorat, N., Kim, B., Vi\u00e9gas, F. & Wattenberg, M. Smoothgrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825 (2017)."},{"key":"216_CR26","unstructured":"Abid, A. et al. Gradio: Hassle-free sharing and testing of ml models in the wild. in Proc. 36th International Conference on Machine Learning, Vol. 72 (JMLR.org, 2019)."},{"key":"216_CR27","doi-asserted-by":"publisher","first-page":"680","DOI":"10.1093\/ehjci\/jet284","volume":"15","author":"S Kou","year":"2014","unstructured":"Kou, S. et al. Echocardiographic reference ranges for normal cardiac chamber size: results from the norre study. Eur. Heart J. Cardiovasc. Imaging 15, 680\u2013690 (2014).","journal-title":"Eur. Heart J. Cardiovasc. Imaging"},{"key":"216_CR28","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.1161\/CIRCIMAGING.113.000690","volume":"6","author":"S Pfaffenberger","year":"2013","unstructured":"Pfaffenberger, S. et al. Size matters! Impact of age, sex, height, and weight on the normal heart size. Circ. Cardiovasc. Imaging 6, 1073\u20131079 (2013).","journal-title":"Circ. Cardiovasc. Imaging"},{"key":"216_CR29","volume":"12","author":"Z Attia","year":"2019","unstructured":"Attia, Z. et al. Age and sex estimation using artificial intelligence from standard 12-lead ecgs. Circ.: Arrhythm. Electrophysiol. 12, e007284 (2019).","journal-title":"Circ.: Arrhythm. Electrophysiol."},{"key":"216_CR30","doi-asserted-by":"publisher","first-page":"1049","DOI":"10.1016\/S0894-7317(03)00516-9","volume":"16","author":"V Munagala","year":"2003","unstructured":"Munagala, V. et al. Association of newer diastolic function parameters with age in healthy subjects: a population-based study. J. Am. Soc. Echocardiogr. 16, 1049\u20131056 (2003).","journal-title":"J. Am. Soc. Echocardiogr."},{"key":"216_CR31","doi-asserted-by":"crossref","first-page":"1001","DOI":"10.1111\/echo.12217","volume":"30","author":"A D\u2019Andrea","year":"2013","unstructured":"D\u2019Andrea, A. et al. Left atrial volume index in healthy subjects: clinical and echocardiographic correlates. Echocardiography 30, 1001\u20131007 (2013).","journal-title":"Echocardiography"},{"key":"216_CR32","doi-asserted-by":"publisher","first-page":"2211","DOI":"10.1056\/NEJMoa1000367","volume":"363","author":"K Bhaskaran","year":"2010","unstructured":"Bhaskaran, K., dos Santos Silva, I., Leon, D. A., Douglas, I. J. & Smeeth, L. Body-mass index and mortality among 1.46 million white adults. N. Engl. J. Med. 363, 2211\u20132219 (2010).","journal-title":"N. Engl. J. Med."},{"key":"216_CR33","doi-asserted-by":"publisher","first-page":"944","DOI":"10.1016\/S2213-8587(18)30288-2","volume":"6","author":"B de Gonzalez A","year":"2018","unstructured":"de Gonzalez A, B., P, H. & JR, C. Association of BMI with overall and cause-specific mortality: a population-based cohort study of 3.6 million adults in the UK. Lancet Diabetes Endocrinol. 6, 944\u2013953 (2018).","journal-title":"Lancet Diabetes Endocrinol."},{"key":"216_CR34","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2018.4587","volume":"1","author":"H Xu","year":"2018","unstructured":"Xu, H., Cupples, L. A. & Stokes, A., & Liu, C.T. et al. Association of obesity with mortality over 24 years of weight history findings from the framingham heart study. JAMA Netw. Open 1, e184587 (2018).","journal-title":"JAMA Netw. Open"},{"key":"216_CR35","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1378\/chest.117.3.657","volume":"117","author":"EC Madu","year":"2000","unstructured":"Madu, E. C. Transesophageal dobutamine stress echocardiography in the evaluation of myocardial ischemia in morbidly obese subjects. Chest. 117, 657\u2013661 (2000).","journal-title":"Chest."},{"key":"216_CR36","unstructured":"Medical Advisory Secretariat. Use of contrast agents with echocardiography in patients with suboptimal echocardiography. Ont. Health Technol. Assess. Ser. 10, 1\u201317 (2010)."},{"key":"216_CR37","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.116.005093","volume":"6","author":"H K\u00e4lsch","year":"2017","unstructured":"K\u00e4lsch, H. et al. Aortic calcification onset and progression: Association with the development of coronary atherosclerosis. J Am Heart Assoc. 6, e005093 (2017).","journal-title":"J Am Heart Assoc."},{"key":"216_CR38","doi-asserted-by":"crossref","unstructured":"Eleid, M.F., Foley, T.A., Said, S.M., Pislaru, S.V. & Rihal, C.S. Severe mitral annular calcification: multimodality imaging for therapeutic strategies and interventions. JACC: Cardiovas. Imaging 9, 1318\u20131337 (2016).","DOI":"10.1016\/j.jcmg.2016.09.001"},{"key":"216_CR39","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1161\/CIRCIMAGING.108.826602","volume":"2","author":"G Aurigemma","year":"2009","unstructured":"Aurigemma, G. et al. Left atrial volume and geometry in healthy aging: the cardiovascular health study. Circ. Cardiovasc. Imaging 2, 282\u2013289 (2009).","journal-title":"Circ. Cardiovasc. Imaging"},{"key":"216_CR40","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1038\/s42256-019-0019-2","volume":"1","author":"GA Bello","year":"2019","unstructured":"Bello, G. A. et al. Deep-learning cardiac motion analysis for human survival prediction. Nat. Mach. Intell. 1, 95 (2019).","journal-title":"Nat. Mach. Intell."},{"key":"216_CR41","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1038\/s41591-019-0447-x","volume":"25","author":"D Ardila","year":"2019","unstructured":"Ardila, D. et al. End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nat. Med. 25, 954\u2013961 (2019).","journal-title":"Nat. Med."},{"key":"216_CR42","unstructured":"Virnig, B.A. et al. Trends in the Use of Echocardiography. Echocardiography Trends. Data Points #20 (prepared by the University of Minnesota DEcIDE Center, under Contract No. HHSA29020100013I). Rockville, MD: Agency for Healthcare Research and Quality; May 2014. AHRQ Publication No. 14-EHC034-EF (2007\u20132011)."},{"key":"216_CR43","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J. & Wojna, Z. Rethinking the inception architecture for computer vision. In Proc. of the IEEE conference on computer vision and pattern recognition, 2818\u20132826 (IEEE, 2016).","DOI":"10.1109\/CVPR.2016.308"},{"key":"216_CR44","unstructured":"Abadi, M. et al. Tensorflow: A system for large-scale machine learning. In 12th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 16) 265\u2013283 (2016)."},{"key":"216_CR45","unstructured":"Kingma, D.P. & Ba, J. Adam: a method for stochastic optimization. 3rd International Conference on Learning Representations, {ICLR} 2015, (San Diego, CA, USA, 2015) Conference Track Proceedings."},{"key":"216_CR46","unstructured":"Krogh, A. & Hertz, J.A. A simple weight decay can improve generalization. In Advances in neural information processing systems, 950\u2013957 (1992)."},{"key":"216_CR47","doi-asserted-by":"crossref","unstructured":"Huber, P.J. Robust estimation of a location parameter. in Breakthroughs in statistics, 492\u2013518 (Springer, 1992).","DOI":"10.1007\/978-1-4612-4380-9_35"},{"key":"216_CR48","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K. & Doll\u00e1r, P. Focal loss for dense object detection. In Proc. of the IEEE international conference on computer vision, 2980\u20132988 (IEEE, 2017).","DOI":"10.1109\/ICCV.2017.324"},{"key":"216_CR49","unstructured":"Perez, L. & Wang, J. The effectiveness of data augmentation in image classification using deep learning. arXiv preprint arXiv:1712.04621 (2017)."},{"key":"216_CR50","unstructured":"Lim, S., Kim, I., Kim, T., Kim, C. & Kim, S. Fast AutoAugment In Advances in Neural Information Processing Systems, 6662\u20136672 (2019)."},{"key":"216_CR51","first-page":"1803","volume":"11","author":"D Baehrens","year":"2010","unstructured":"Baehrens, D. et al. How to explain individual classification decisions. Journal of Machine Learning Research 11, 1803\u20131831 (2010).","journal-title":"Journal of Machine Learning Research"},{"key":"216_CR52","unstructured":"Simonyan, K., Vedaldi, A. & Zisserman, A. Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)."},{"key":"216_CR53","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140","volume":"10","author":"S Bach","year":"2015","unstructured":"Bach, S. et al. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PloS ONE 10, e0130140 (2015).","journal-title":"PloS ONE"},{"key":"216_CR54","unstructured":"Shrikumar, A., Greenside, P. & Kundaje, A. Learning important features through propagating activation differences. In Proc. of the 34th International Conference on Machine Learning, vol. 70, 3145\u20133153 (JMLR, 2017)"},{"key":"216_CR55","unstructured":"Sundararajan, M., Taly, A. & Yan, Q. Axiomatic attribution for deep networks. in Proc. 34th International Conference on Machine Learning, Vol. 70, 3319\u20133328 (JMLR. org, 2017)."},{"key":"216_CR56","doi-asserted-by":"crossref","unstructured":"Ghorbani, A., Abid, A. & Zou, J. Interpretation of neural networks is fragile. In Proc. of the AAAI Conference on Artificial Intelligence, Vol. 33, 3681\u20133688 (AAAI.org, 2019).","DOI":"10.1609\/aaai.v33i01.33013681"},{"key":"216_CR57","unstructured":"Levine, A., Singla, S. & Feizi, S. Certifiably robust interpretation in deep learning. arXiv preprint arXiv:1905.12105 (2019)."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-019-0216-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-019-0216-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-019-0216-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,30]],"date-time":"2024-07-30T13:23:15Z","timestamp":1722345795000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-019-0216-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,24]]},"references-count":57,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2020,12]]}},"alternative-id":["216"],"URL":"https:\/\/doi.org\/10.1038\/s41746-019-0216-8","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/681676","asserted-by":"object"}]},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1,24]]},"assertion":[{"value":"25 June 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 December 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 January 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}],"article-number":"10"}}