{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T21:53:10Z","timestamp":1787003590355,"version":"build-2736575974"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,4,21]],"date-time":"2021-04-21T00:00:00Z","timestamp":1618963200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,4,21]],"date-time":"2021-04-21T00:00:00Z","timestamp":1618963200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100013348","name":"Innosuisse-Schweizerische Agentur f\u00fcr Innovationsf\u00f6rderung","doi-asserted-by":"publisher","award":["# 6362.1 PFLS-LS"],"award-info":[{"award-number":["# 6362.1 PFLS-LS"]}],"id":[{"id":"10.13039\/501100013348","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>In this paper we analyse the performance of machine learning methods in predicting patient information such as age or sex solely from retinal imaging modalities in a heterogeneous clinical population. Our dataset consists of N\u00a0=\u00a0135,667 fundus images and N\u00a0=\u00a085,536 volumetric OCT scans. Deep learning models were trained to predict the patient\u2019s age and sex from fundus images, OCT cross sections and OCT volumes. For sex prediction, a ROC AUC of 0.80 was achieved for fundus images, 0.84 for OCT cross sections and 0.90 for OCT volumes. Age prediction mean absolute errors of 6.328 years for fundus, 5.625\u00a0years for OCT cross sections and 4.541 for OCT volumes were observed. We assess the performance of OCT scans containing different biomarkers and note a peak performance of AUC\u00a0=\u00a00.88 for OCT cross sections and 0.95 for volumes when there is no pathology on scans. Performance drops in case of drusen, fibrovascular pigment epitheliuum detachment and geographic atrophy present. We conclude that deep learning based methods are capable of classifying the patient\u2019s sex and age from color fundus photography and OCT for a broad spectrum of patients irrespective of underlying disease or image quality. Non-random sex prediction using fundus images seems only possible if the eye fovea and optic disc are visible.<\/jats:p>","DOI":"10.1038\/s41598-021-86577-5","type":"journal-article","created":{"date-parts":[[2021,4,21]],"date-time":"2021-04-21T06:44:41Z","timestamp":1618987481000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["Assessment of patient specific information in the wild on fundus photography and optical coherence tomography"],"prefix":"10.1038","volume":"11","author":[{"given":"Marion R.","family":"Munk","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Kurmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pablo","family":"M\u00e1rquez-Neila","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin S.","family":"Zinkernagel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Wolf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raphael","family":"Sznitman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,4,21]]},"reference":[{"key":"86577_CR1","doi-asserted-by":"publisher","first-page":"1170","DOI":"10.1001\/jamaophthalmol.2017.3782","volume":"135","author":"PM Burlina","year":"2017","unstructured":"Burlina, P. M. et al. Automated grading of age-related macular degeneration from color fundus images using deep convolutional neural networks. JAMA Ophthalmol. 135, 1170\u20131176 (2017).","journal-title":"JAMA Ophthalmol."},{"key":"86577_CR2","doi-asserted-by":"publisher","first-page":"13605","DOI":"10.1038\/s41598-019-49740-7","volume":"9","author":"T Kurmann","year":"2019","unstructured":"Kurmann, T. et al. Expert-level automated biomarker identification in optical coherence tomography scans. Sci. Rep. 9, 13605 (2019).","journal-title":"Sci. Rep."},{"key":"86577_CR3","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1097\/ICU.0000000000000552","volume":"30","author":"C Zheng","year":"2019","unstructured":"Zheng, C., Johnson, T. V., Garg, A. & Boland, M. V. Artificial intelligence in glaucoma. Curr. Opin. Ophthalmol. 30, 97\u2013103 (2019).","journal-title":"Curr. Opin. Ophthalmol."},{"key":"86577_CR4","doi-asserted-by":"publisher","first-page":"6724","DOI":"10.1167\/iovs.15-17042","volume":"56","author":"MR Munk","year":"2015","unstructured":"Munk, M. R. et al. Differentiation of diabetic macular edema from pseudophakic cystoid macular edema by spectral- domain optical coherence tomography. Invest. Ophthalmol. Vis. Sci. 56, 6724\u20136733 (2015).","journal-title":"Invest. Ophthalmol. Vis. Sci."},{"key":"86577_CR5","doi-asserted-by":"publisher","first-page":"4173","DOI":"10.1167\/iovs.17-21878","volume":"58","author":"WD Vogl","year":"2017","unstructured":"Vogl, W. D. et al. Analyzing and predicting visual acuity outcomes of anti-VEGF therapy by a longitudinal mixed effects model of imaging and clinical data. Invest. Ophthalmol. Vis. Sci. 58, 4173\u20134181 (2017).","journal-title":"Invest. Ophthalmol. Vis. Sci."},{"key":"86577_CR6","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1016\/j.ophtha.2017.08.031","volume":"125","author":"D Zur","year":"2018","unstructured":"Zur, D. et al. OCT biomarkers as functional outcome predictors in diabetic macular edema treated with dexamethasone implant. Ophthalmology 125, 267\u2013275 (2018).","journal-title":"Ophthalmology"},{"key":"86577_CR7","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1007\/978-3-319-66179-7_34","volume-title":"Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2017","author":"S Apostolopoulos","year":"2017","unstructured":"Apostolopoulos, S., De Zanet, S., Ciller, C., Wolf, S. & Sznitman, R. Pathological OCT retinal layer segmentation using branch residual u-shape networks. In Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2017 (eds Descoteaux, M. et al.) 294\u2013301 (Springer International Publishing, 2017)."},{"key":"86577_CR8","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1167\/tvst.6.2.3","volume":"6","author":"E Tsikata","year":"2017","unstructured":"Tsikata, E. et al. Automated brightness and contrast adjustment of color fundus photographs for the grading of age-related macular degeneration. Transl. Vis. Sci. Technol. 6, 3 (2017).","journal-title":"Transl. Vis. Sci. Technol."},{"key":"86577_CR9","first-page":"1224","volume":"2018","author":"AS Coyner","year":"2018","unstructured":"Coyner, A. S. et al. Deep learning for image quality assessment of fundus images in retinopathy of prematurity. AMIA Annu. Symp Proc 2018, 1224\u20131232 (2018).","journal-title":"AMIA Annu. Symp Proc"},{"key":"86577_CR10","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\u2013164 (2018).","journal-title":"Nat. Biomed. Eng."},{"key":"86577_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-56847-4","volume":"10","author":"YD Kim","year":"2020","unstructured":"Kim, Y. D. et al. Effects of hypertension, diabetes, and smoking on age and sex prediction from retinal fundus images. Sci. Rep. 10, 1\u201314 (2020).","journal-title":"Sci. Rep."},{"key":"86577_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-65794-4","volume":"10","author":"N Gerrits","year":"2020","unstructured":"Gerrits, N. et al. Age and sex affect deep learning prediction of cardiometabolic risk factors from retinal images. Sci. Rep. 10, 1\u20139 (2020).","journal-title":"Sci. Rep."},{"key":"86577_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770\u2013778 (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"86577_CR14","unstructured":"Kingma, D. P. & Ba, J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"86577_CR15","doi-asserted-by":"crossref","unstructured":"Selvaraju, R. R. et al. Grad-cam: Visual explanations from deep networks via gradient-based localization. in Proceedings of the IEEE International Conference on Computer Vision, 618\u2013626 (2017).","DOI":"10.1109\/ICCV.2017.74"},{"key":"86577_CR16","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1159\/000495622","volume":"241","author":"M Niestrata-Ortiz","year":"2019","unstructured":"Niestrata-Ortiz, M., Fichna, P., Stankiewicz, W. & Stopa, M. Sex-related variations of retinal and choroidal thickness and foveal avascular zone in healthy and diabetic children assessed by optical coherence tomography imaging. Ophthalmologica 241, 173\u2013177. https:\/\/doi.org\/10.1159\/000495622 (2019).","journal-title":"Ophthalmologica"},{"key":"86577_CR17","doi-asserted-by":"publisher","first-page":"2188","DOI":"10.1097\/IAE.0000000000000847","volume":"35","author":"WA Samara","year":"2015","unstructured":"Samara, W. A. et al. Correlation of foveal avascular zone size with foveal morphology in normal eyes using optical coherence tomography angiography. Retina 35, 2188\u20132195. https:\/\/doi.org\/10.1097\/IAE.0000000000000847 (2015).","journal-title":"Retina"},{"key":"86577_CR18","doi-asserted-by":"publisher","first-page":"OCT224","DOI":"10.1167\/iovs.15-18869","volume":"57","author":"CS Tan","year":"2016","unstructured":"Tan, C. S. et al. Optical coherence tomography angiography evaluation of the parafoveal vasculature and its relationship with ocular factors. Investig. Ophthalmol. Vis. Sci. 57, OCT224\u2013OCT234. https:\/\/doi.org\/10.1167\/iovs.15-18869 (2016).","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"86577_CR19","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1016\/j.ophtha.2019.09.019","volume":"127","author":"D Li","year":"2020","unstructured":"Li, D. et al. Sex-specific differences in circumpapillary retinal nerve fiber layer thickness. Ophthalmology 127, 357\u2013368. https:\/\/doi.org\/10.1016\/j.ophtha.2019.09.019 (2020).","journal-title":"Ophthalmology"},{"key":"86577_CR20","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1210\/er.2015-1137","volume":"37","author":"A Kautzky-Willer","year":"2016","unstructured":"Kautzky-Willer, A., Harreiter, J. & Pacini, G. Sex and gender differences in risk, pathophysiology and complications of type 2 diabetes mellitus. Endocr. Rev. 37, 278\u2013316 (2016).","journal-title":"Endocr. Rev."},{"key":"86577_CR21","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1167\/iovs.14-15147","volume":"56","author":"P Benitez-Aguirre","year":"2014","unstructured":"Benitez-Aguirre, P. et al. Sex differences in retinal microvasculature through puberty in type 1 diabetes: Are girls at greater risk of diabetic microvascular complications?. Invest. Ophthalmol. Vis. Sci. 56, 571\u2013577 (2014).","journal-title":"Invest. Ophthalmol. Vis. Sci."},{"key":"86577_CR22","doi-asserted-by":"publisher","first-page":"1034","DOI":"10.1016\/j.ajo.2015.07.027","volume":"160","author":"R Bafiq","year":"2015","unstructured":"Bafiq, R. et al. Age, sex, and ethnic variations in inner and outer retinal and choroidal thickness on spectral-domain optical coherence tomography. Am. J. Ophthalmol. 160, 1034-1043.e1. https:\/\/doi.org\/10.1016\/j.ajo.2015.07.027 (2015).","journal-title":"Am. J. Ophthalmol."},{"key":"86577_CR23","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/j.ajo.2018.07.030","volume":"195","author":"NM Bressler","year":"2018","unstructured":"Bressler, N. M. et al. Early response to anti-vascular endothelial growth factor and two-year outcomes among eyes with diabetic macular edema in protocol T. Am. J. Ophthalmol. 195, 93\u2013100. https:\/\/doi.org\/10.1016\/j.ajo.2018.07.030 (2018).","journal-title":"Am. J. Ophthalmol."},{"key":"86577_CR24","doi-asserted-by":"publisher","unstructured":"Pichi, F., Invernizzi, A., Tucker, W. R. & Munk, M. R. Optical coherence tomography diagnostic signs in posterior uveitis. https:\/\/doi.org\/10.1016\/j.preteyeres.2019.100797 (2020).","DOI":"10.1016\/j.preteyeres.2019.100797"},{"key":"86577_CR25","doi-asserted-by":"publisher","unstructured":"Dysli, M., R\u00fcckert, R. & Munk, M. R. Differentiation of underlying pathologies of macular edema using spectral domain optical coherence tomography (SD-OCT). https:\/\/doi.org\/10.1080\/09273948.2019.1603313 (2019).","DOI":"10.1080\/09273948.2019.1603313"},{"key":"86577_CR26","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1007\/s00417-017-3590-4","volume":"255","author":"R Saleh","year":"2017","unstructured":"Saleh, R., Karpe, A., Zinkernagel, M. S. & Munk, M. R. Inner retinal layer change in glaucoma patients receiving anti-VEGF for neovascular age related macular degeneration. Graefe\u2019s Arch. Clin. Exp. Ophthalmol. 255, 817\u2013824. https:\/\/doi.org\/10.1007\/s00417-017-3590-4 (2017).","journal-title":"Graefe\u2019s Arch. Clin. Exp. Ophthalmol."},{"key":"86577_CR27","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1136\/bjophthalmol-2016-308367","volume":"101","author":"MR Munk","year":"2017","unstructured":"Munk, M. R. et al. Quantification of retinal layer thickness changes in acute macular neuroretinopathy. Br. J. Ophthalmol. 101, 160\u2013165. https:\/\/doi.org\/10.1136\/bjophthalmol-2016-308367 (2017).","journal-title":"Br. J. Ophthalmol."},{"key":"86577_CR28","doi-asserted-by":"publisher","first-page":"708","DOI":"10.1097\/IAE.0000000000001689","volume":"38","author":"RF Spaide","year":"2018","unstructured":"Spaide, R. F. Disease expression in nonexudative age-related macular degeneration varies with choroidal thickness. Retina 38, 708\u2013716. https:\/\/doi.org\/10.1097\/IAE.0000000000001689 (2018).","journal-title":"Retina"},{"key":"86577_CR29","doi-asserted-by":"publisher","unstructured":"Agrawal, R. et al. Exploring choroidal angioarchitecture in health and disease using choroidal vascularity index. Prog. Retin. Eye Res. 77100829 (2020).\nhttps:\/\/doi.org\/10.1016\/j.preteyeres.2020.100829","DOI":"10.1016\/j.preteyeres.2020.100829"},{"key":"86577_CR30","doi-asserted-by":"publisher","unstructured":"McGeechan, K. et al. Prediction of Incident Stroke Events Based on Retinal Vessel Caliber: A Systematic Review and Individual-Participant Meta-Analysis.Am. J. Epidemiol. 170, 1323\u20131332. https:\/\/doi.org\/10.1093\/aje\/kwp306 (2009). https:\/\/academic.oup.com\/aje\/article-pdf\/170\/11\/1323\/268241\/kwp306.pdf.","DOI":"10.1093\/aje\/kwp306"},{"key":"86577_CR31","doi-asserted-by":"publisher","unstructured":"Benke, K. K. & Arslan, J. Deep learning algorithms and the protection of data privacy. JAMA Ophthalmol. 138, 1024-1025 https:\/\/doi.org\/10.1001\/jamaophthalmol.2020.2766 (2020). https:\/\/jamanetwork.com\/journals\/jamaophthalmology\/articlepdf\/2768910\/jamaophthalmology_benke_2020_ic_200026.pdf.","DOI":"10.1001\/jamaophthalmol.2020.2766"},{"key":"86577_CR32","unstructured":"Data anonymisation - a key enabler for clinical data sharing - Workshop report. Tech. Rep. (2018)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-86577-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-86577-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-86577-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T01:58:35Z","timestamp":1670032715000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-86577-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,21]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["86577"],"URL":"https:\/\/doi.org\/10.1038\/s41598-021-86577-5","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,21]]},"assertion":[{"value":"22 September 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 April 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"R.S. has received speaker fees from Bayer AG and is a shareholder of RetinAI Medical AG. M.R.M is a consultant for Zeiss, Bayer, Novartis and Lumithera. M.Z. is a consultant for Heidelberg, Bayer and Novartis. S.W. reports other from Bayer AG, other from Allergan, other from Novartis Pharma, other from Heidelberg Engineering, other from Zeiss, other from Chengdu Kanghong and other from Roche. The other authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"8621"}}