{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T00:25:52Z","timestamp":1778286352694,"version":"3.51.4"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T00:00:00Z","timestamp":1693267200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T00:00:00Z","timestamp":1693267200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Research Foundation of Beijing Friendship Hospital, Capital Medical University","award":["yyqdkt2018-33"],"award-info":[{"award-number":["yyqdkt2018-33"]}]},{"DOI":"10.13039\/501100010270","name":"Capital Health Research and Development of Special Fund","doi-asserted-by":"publisher","award":["2020-1-2052"],"award-info":[{"award-number":["2020-1-2052"]}],"id":[{"id":"10.13039\/501100010270","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science & Technology Project of Beijing Municipal Science & Technology Commission","award":["Z201100005520045, Z181100001818003"],"award-info":[{"award-number":["Z201100005520045, Z181100001818003"]}]},{"DOI":"10.13039\/501100009601","name":"Beijing Municipal Administration of Hospitals\u2019 Ascent Plan","doi-asserted-by":"crossref","award":["DFL20150201"],"award-info":[{"award-number":["DFL20150201"]}],"id":[{"id":"10.13039\/501100009601","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82071005"],"award-info":[{"award-number":["82071005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Special Fund of the Pediatric Medical Coordinated Development Center of Beijing Hospitals Authority","award":["XTCX201824"],"award-info":[{"award-number":["XTCX201824"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Screening for hyperthyroidism using gold-standard diagnostic criteria in the general population is not cost-effective, leading to a relatively high rate of undiagnosed and untreated patients. This study aimed to establish a deep learning-based system to detect hyperthyroidism based on retinal photographs.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>The multicenter, observational study included retinal photographs taken from participants in two hospitals and 24 health care centers throughout China. We first trained two models to identify hyperthyroidism: in model #1, the non-hyperthyroidism individuals were randomly selected, while in model #2, the non-hyperthyroidism group was matched for age and gender with the hyperthyroidism group. After internal validation, we selected the better model for further evaluation using external validation datasets.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>The study included 22,940 retinal photographs of 11,409 participants for the model development, and 3862 retinal photographs (1870 participants) which were obtained from two hospitals and four medical centers as the external validation datasets. Model #1 achieved a higher area under the receiver operator curve (AUC) than model #2 (0.907, 95% CI: 0.894\u20130.918 versus 0.850, 95% CI: 0.832\u20130.866) in the internal validation so that model #1 was used for further evaluation. In external datasets, model #1 reached AUCs ranging from 0.816 (95% CI 0.789\u20130.846) to 0.849 (95% CI 0.824\u20130.874) and achieved accuracies between 0.735 (95% CI 0.700\u20130.773) and 0.796 (95% CI 0.765\u20130.824). Heatmaps showed a focus of the DL-algorism on large fundus vessels and the optic nerve head.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>Retinal fundus photographs may serve for DL systems for a cost-effective and non-invasive method to detect hyperthyroidism.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s40537-023-00777-6","type":"journal-article","created":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T16:03:07Z","timestamp":1693324987000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Retinal photograph-based deep learning system for detection of hyperthyroidism: a multicenter, diagnostic study"],"prefix":"10.1186","volume":"10","author":[{"given":"Li","family":"Dong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lie","family":"Ju","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiqi","family":"Hui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lihua","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xue","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihan","family":"Nie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenda","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heyan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jost B.","family":"Jonas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuzhong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaohui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianxiong","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongyuan","family":"Ge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbin","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4226-662X","authenticated-orcid":false,"given":"Dongmei","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,29]]},"reference":[{"issue":"2","key":"777_CR1","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1152\/physrev.00030.2013","volume":"94","author":"R Mullur","year":"2014","unstructured":"Mullur R, Liu YY, Brent GA. Thyroid hormone regulation of metabolism. Physiol Rev. 2014;94(2):355.","journal-title":"Physiol Rev"},{"key":"777_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(16)00278-6","author":"S De Leo","year":"2016","unstructured":"De Leo S, Lee SY, Braverman LE. Hyperthyroidism. Lancet. 2016. https:\/\/doi.org\/10.1016\/S0140-6736(16)00278-6.","journal-title":"Lancet"},{"issue":"2","key":"777_CR3","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1210\/jcem.87.2.8182","volume":"87","author":"JG Hollowell","year":"2002","unstructured":"Hollowell JG, Staehling NW, Flanders WD, et al. Serum TSH, T(4), and thyroid antibodies in the United States population (1988 to 1994) national health and nutrition examination survey (NHANES III). J Clin Endocrinol Metab. 2002;87(2):489.","journal-title":"J Clin Endocrinol Metab"},{"issue":"10","key":"777_CR4","doi-asserted-by":"publisher","first-page":"1343","DOI":"10.1089\/thy.2016.0229","volume":"26","author":"DS Ross","year":"2016","unstructured":"Ross DS, Burch HB, Cooper DS, et al. 2016 american thyroid association guidelines for diagnosis and management of hyperthyroidism and other causes of thyrotoxicosis. Thyroid. 2016;26(10):1343.","journal-title":"Thyroid"},{"issue":"3","key":"777_CR5","doi-asserted-by":"publisher","first-page":"923","DOI":"10.1210\/jc.2013-2409","volume":"99","author":"A Garmendia Madariaga","year":"2014","unstructured":"Garmendia Madariaga A, Santos Palacios S, Guill\u00e9n-Grima F, Galofr\u00e9 JC. The incidence and prevalence of thyroid dysfunction in Europe: a meta-analysis. J Clin Endocrinol Metab. 2014;99(3):923.","journal-title":"J Clin Endocrinol Metab"},{"issue":"3","key":"777_CR6","doi-asserted-by":"publisher","first-page":"506","DOI":"10.1097\/SLA.0000000000002922","volume":"268","author":"A Asban","year":"2018","unstructured":"Asban A, Chung SK, Tresler MA, et al. Hyperthyroidism is underdiagnosed and undertreated in 3336 patients: an opportunity for improvement and intervention. Ann Surg. 2018;268(3):506.","journal-title":"Ann Surg"},{"issue":"7553","key":"777_CR7","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436.","journal-title":"Nature"},{"issue":"3","key":"777_CR8","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1038\/s41551-018-0195-0","volume":"2","author":"R Poplin","year":"2018","unstructured":"Poplin R, Varadarajan AV, Blumer K, et al. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nature Biomed Eng. 2018;2(3):158.","journal-title":"Nature Biomed Eng"},{"issue":"7","key":"777_CR9","doi-asserted-by":"publisher","first-page":"2861","DOI":"10.1167\/iovs.18-23887","volume":"59","author":"AV Varadarajan","year":"2018","unstructured":"Varadarajan AV, Poplin R, Blumer K, et al. Deep learning for predicting refractive error from retinal fundus images. Invest Ophthalmol Visual Sci. 2018;59(7):2861.","journal-title":"Invest Ophthalmol Visual Sci"},{"issue":"6","key":"777_CR10","doi-asserted-by":"publisher","first-page":"714","DOI":"10.1016\/j.eururo.2019.08.032","volume":"76","author":"E Shkolyar","year":"2019","unstructured":"Shkolyar E, Jia X, Chang TC, et al. Augmented bladder tumor detection using deep learning. Eur Urol. 2019;76(6):714.","journal-title":"Eur Urol"},{"issue":"22","key":"777_CR11","doi-asserted-by":"publisher","first-page":"2402","DOI":"10.1001\/jama.2016.17216","volume":"316","author":"V Gulshan","year":"2016","unstructured":"Gulshan V, Peng L, Coram M, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA. 2016;316(22):2402.","journal-title":"JAMA"},{"issue":"1","key":"777_CR12","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1038\/s41551-019-0487-z","volume":"4","author":"A Mitani","year":"2020","unstructured":"Mitani A, Huang A, Venugopalan S, et al. Detection of anaemia from retinal fundus images via deep learning. Nat Biomed Eng. 2020;4(1):18.","journal-title":"Nat Biomed Eng"},{"key":"777_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(20)30288-0","author":"W Xiao","year":"2021","unstructured":"Xiao W, Huang X, Wang JH, et al. Screening and identifying hepatobiliary diseases through deep learning using ocular images: a prospective, multicentre study. Lancet Digit Health. 2021. https:\/\/doi.org\/10.1016\/S2589-7500(20)30288-0.","journal-title":"Lancet Digit Health"},{"key":"777_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(20)30216-8","author":"TH Rim","year":"2020","unstructured":"Rim TH, Lee G, Kim Y, et al. Prediction of systemic biomarkers from retinal photographs: development and validation of deep-learning algorithms. Lancet Digit Health. 2020. https:\/\/doi.org\/10.1016\/S2589-7500(20)30216-8.","journal-title":"Lancet Digit Health"},{"key":"777_CR15","first-page":"1556","volume":"1409","author":"K Simonyan","year":"2014","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. ArXiv. 2014;1409:1556.","journal-title":"ArXiv"},{"key":"777_CR16","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"777_CR17","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, et al. 2016. Rethinking the inception architecture for computer vision. Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2016.308"},{"key":"777_CR18","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. Proceedings of the IEEE conference on computer vision and pattern recognition 2017.","DOI":"10.1109\/CVPR.2017.243"},{"key":"777_CR19","first-page":"6980","volume":"1412","author":"DP Kingma","year":"2014","unstructured":"Kingma DP, Ba J. Adam a method for stochastic optimization. arXiv. 2014;1412:6980.","journal-title":"arXiv"},{"key":"777_CR20","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-2766-4","volume-title":"Introduction to pytorch Deep learning with python","author":"N Ketkar","year":"2017","unstructured":"Ketkar N. Introduction to pytorch Deep learning with python. Berlin: Springer; 2017."},{"key":"777_CR21","doi-asserted-by":"crossref","unstructured":"Selvaraju RR, Cogswell M, Das A, et al. Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE international conference on computer vision 2017.","DOI":"10.1109\/ICCV.2017.74"},{"key":"777_CR22","doi-asserted-by":"publisher","DOI":"10.1002\/9781119505969","volume-title":"Mathematical statistics with resampling and R","author":"LM Chihara","year":"2018","unstructured":"Chihara LM, Hesterberg TC. Mathematical statistics with resampling and R. Hoboken: John Wiley & Sons; 2018."},{"issue":"10","key":"777_CR23","doi-asserted-by":"publisher","first-page":"e526","DOI":"10.1016\/S2589-7500(20)30216-8","volume":"2","author":"TH Rim","year":"2020","unstructured":"Rim TH, Lee G, Kim Y, et al. Prediction of systemic biomarkers from retinal photographs: development and validation of deep-learning algorithms. Lancet Digit Health. 2020;2(10):e526.","journal-title":"Lancet Digit Health"},{"issue":"1","key":"777_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.biopha.2009.02.007","volume":"64","author":"W Sato","year":"2010","unstructured":"Sato W, Hoshi K, Kawakami J, et al. Assisting the diagnosis of graves\u2019 hyperthyroidism with bayesian-type and som-type neural networks by making use of a set of three routine tests and their correlation with free T4. Biomed Pharmacother. 2010;64(1):1.","journal-title":"Biomed Pharmacother"},{"issue":"2","key":"777_CR25","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.biopha.2010.10.005","volume":"65","author":"S Aoki","year":"2011","unstructured":"Aoki S, Hoshi K, Kawakami J, et al. Assisting the diagnosis of Graves\u2019 hyperthyroidism with pattern recognition methods and a set of three routine tests parameters, and their correlations with free T4 levels extension to male patients. Biomed Pharmacother. 2011;65(2):95.","journal-title":"Biomed Pharmacother"},{"issue":"7","key":"777_CR26","doi-asserted-by":"publisher","first-page":"918","DOI":"10.1111\/ceo.13525","volume":"47","author":"FHP Lai","year":"2019","unstructured":"Lai FHP, Iao TWU, Ng DSC, et al. Choroidal thickness in thyroid-associated orbitopathy. Clin Exp ophthalmol. 2019;47(7):918.","journal-title":"Clin Exp ophthalmol"},{"issue":"6","key":"777_CR27","doi-asserted-by":"publisher","first-page":"1863","DOI":"10.1167\/iovs.18-25941","volume":"60","author":"T Zhang","year":"2019","unstructured":"Zhang T, Xiao W, Ye H, et al. Peripapillary and macular vessel density in dysthyroid optic neuropathy an optical coherence tomography angiography study. Invest Ophthalmol Vis Sci. 2019;60(6):1863.","journal-title":"Invest Ophthalmol Vis Sci."},{"issue":"3","key":"777_CR28","doi-asserted-by":"publisher","first-page":"312","DOI":"10.4158\/EP-2019-0328","volume":"26","author":"N Mihailovic","year":"2020","unstructured":"Mihailovic N, Lahme L, Rosenberger F, et al. Altered retinal perfusion in patients with inactive graves ophthalmopathy using optical coherence tomography angiography. Endocr Pract. 2020;26(3):312.","journal-title":"Endocr Pract"},{"key":"777_CR29","doi-asserted-by":"publisher","DOI":"10.1186\/s12886-020-01692-7","author":"L Yu","year":"2020","unstructured":"Yu L, Jiao Q, Cheng Y, et al. Evaluation of retinal and choroidal variations in thyroid-associated ophthalmopathy using optical coherence tomography angiography. BMC Ophthalmol. 2020. https:\/\/doi.org\/10.1186\/s12886-020-01692-7.","journal-title":"BMC Ophthalmol"},{"issue":"14","key":"777_CR30","first-page":"5106","volume":"52","author":"L Teo","year":"2011","unstructured":"Teo L, Cheung C, Tay WT, Wong TY. Associations between thyroid dysfunction and retinal microvascular changes. Invest Ophthalmol Vis Sci. 2011;52(14):5106.","journal-title":"Invest Ophthalmol Vis Sci"},{"issue":"2","key":"777_CR31","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1016\/j.emc.2013.12.001","volume":"32","author":"D Devereaux","year":"2014","unstructured":"Devereaux D, Tewelde SZ. Hyperthyroidism and thyrotoxicosis. Emerg Med Clin North Am. 2014;32(2):277.","journal-title":"Emerg Med Clin North Am"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-023-00777-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40537-023-00777-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-023-00777-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,19]],"date-time":"2023-11-19T16:04:00Z","timestamp":1700409840000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-023-00777-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,29]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["777"],"URL":"https:\/\/doi.org\/10.1186\/s40537-023-00777-6","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,29]]},"assertion":[{"value":"20 January 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 May 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Authors Lie Ju, Xin Wang, Xin Zhao, Chao He, Yu Zhong Chen, were employed by the company Beijing Airdoc Technology Co., Ltd. Beijing, China. Authors Zhao Hui Wang and Jian Xiong Gao were employed by the company iKang Guobin Healthcare Group Co., Ltd, Beijing, China. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential competing of interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"134"}}