{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T14:02:45Z","timestamp":1790344965591,"version":"4.1.0"},"reference-count":35,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2023,1,15]],"date-time":"2023-01-15T00:00:00Z","timestamp":1673740800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Journal of Diabetes"],"published-print":{"date-parts":[[2023,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To determine whether nailfold capillary images, acquired using video capillaroscopy, can provide diagnostic information about diabetes and its complications.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Research Design and Methods<\/jats:title>\n                    <jats:p>Nailfold video capillaroscopy was performed in 120 adult patients with and without type 1 or type 2 diabetes, and with and without cardiovascular disease. Nailfold images were analyzed using convolutional neural networks, a deep learning technique. Cross\u2010validation was used to develop and test the ability of models to predict five5 prespecified states (diabetes, high glycosylated hemoglobin, cardiovascular event, retinopathy, albuminuria, and hypertension). The performance of each model for a particular state was assessed by estimating areas under the receiver operating characteristics curves (AUROC) and precision recall curves (AUPR).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 5236 nailfold images were acquired from 120 participants (mean 44 images per participant) and were all available for analysis. Models were able to accurately identify the presence of diabetes, with AUROC 0.84 (95% confidence interval [CI] 0.76, 0.91) and AUPR 0.84 (95% CI 0.78, 0.93), respectively. Models were also able to predict a history of cardiovascular events in patients with diabetes, with AUROC 0.65 (95% CI 0.51, 0.78) and AUPR 0.72 (95% CI 0.62, 0.88) respectively.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This proof\u2010of\u2010concept study demonstrates the potential of machine learning for identifying people with microvascular capillary changes from diabetes based on nailfold images, and for possibly identifying those most likely to have diabetes\u2010related complications.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/1753-0407.13354","type":"journal-article","created":{"date-parts":[[2023,1,15]],"date-time":"2023-01-15T17:23:37Z","timestamp":1673803417000},"page":"145-151","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Nailfold capillaroscopy and deep learning in diabetes"],"prefix":"10.1111","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3350-6206","authenticated-orcid":false,"given":"Reema","family":"Shah","sequence":"first","affiliation":[{"name":"Population Health Research Institute, McMaster University and Hamilton Health Sciences Hamilton Ontario Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeremy","family":"Petch","sequence":"additional","affiliation":[{"name":"Population Health Research Institute, McMaster University and Hamilton Health Sciences Hamilton Ontario Canada"},{"name":"Centre for Data Science and Digital Health Hamilton Health Sciences Hamilton Ontario Canada"},{"name":"Institute for Health Policy, Management and Evaluation University of Toronto Toronto Ontario Canada"},{"name":"Division of Cardiology McMaster University Hamilton Ontario Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Walter","family":"Nelson","sequence":"additional","affiliation":[{"name":"Centre for Data Science and Digital Health Hamilton Health Sciences Hamilton Ontario Canada"},{"name":"Department of Statistical Sciences University of Toronto Toronto Ontario Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karsten","family":"Roth","sequence":"additional","affiliation":[{"name":"Cluster of Excellence Machine Learning University of T\u00fcbingen T\u00fcbingen Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1464-159X","authenticated-orcid":false,"given":"Michael D.","family":"Noseworthy","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering McMaster University Hamilton Ontario Canada"},{"name":"McMaster School of Biomedical Engineering Hamilton Ontario Canada"},{"name":"Department of Radiology McMaster University Hamilton Ontario Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marzyeh","family":"Ghassemi","sequence":"additional","affiliation":[{"name":"Vector Institute Toronto Ontario Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8072-2836","authenticated-orcid":false,"given":"Hertzel C.","family":"Gerstein","sequence":"additional","affiliation":[{"name":"Population Health Research Institute, McMaster University and Hamilton Health Sciences Hamilton Ontario Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,1,15]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2015.7008"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2213-8587(20)30431-9"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(20)32374-6"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2019.3471"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2213-8587(13)70025-1"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.2337\/dbi17-0044"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neubiorev.2018.04.003"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104599"},{"key":"e_1_2_9_10_1","unstructured":"MedicalO.Optilia digital capillaroscopy system extensive kit.http:\/\/www.optiliamedical.eu\/products\/2\/capillaroscope\/11\/Optilia%20Digital%20Capillaroscopy%20System %20Extensive%20kit\/.2015."},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.berh.2013.03.001"},{"key":"e_1_2_9_12_1","first-page":"8024","volume-title":"Advances in Neural Information Processing Systems 32","author":"Paszke A","year":"2019"},{"key":"e_1_2_9_13_1","doi-asserted-by":"crossref","unstructured":"MarcelS RodriguezY.2010.Torchvision the Machine\u2010Vision Package of Torch. !8th International Conference on Multimedia; Firenze Italy: Association for Computing Machinery; pp. 1485\u20138.","DOI":"10.1145\/1873951.1874254"},{"issue":"85","key":"e_1_2_9_14_1","first-page":"2825","article-title":"Scikit\u2010learn: machine learning in python","volume":"12","author":"Pedregosa F","year":"2011","journal-title":"J Mach Learn Res"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-018-1088-1"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-8b375195-003"},{"key":"e_1_2_9_17_1","unstructured":"LiawR LiangE NishiharaR MoritzP GonzalezJE StoicaI.Tune: A Research Platform for Distributed Model Selection and Training. ICML AutoML Workshop; 2018."},{"key":"e_1_2_9_18_1","doi-asserted-by":"crossref","unstructured":"RibaE MishkinD PonsaD RubleeE BradskiG.Kornia: an open source differentiable computer vision library for PyTorch. IEEE Winter Conference on Applications of Computer Vision (WACV) 2020 Vision Library for PyTorch; 2020. pp. 3663\u201372.","DOI":"10.1109\/WACV45572.2020.9093363"},{"key":"e_1_2_9_19_1","unstructured":"ProvostF FawcettT KohaviR.The case against accuracy estimation for comparing induction algorithms. Fifteenth International Conference on Machine Learning; 2001: Morgan Kaufmann; 2001. pp. 445\u201353."},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3"},{"key":"e_1_2_9_21_1","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1093\/oso\/9780199541362.003.0002","volume-title":"Diabetes: The Biography","author":"Tattersall R","year":"2009"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.2337\/dc10-1206"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1210\/clinem\/dgaa815"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.2337\/dc18-2483"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.2337\/dc12-1311"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1093\/rheumatology\/kel310"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1464-5491.2011.03325.x"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1177\/000331979004101205"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1006\/mvre.1996.2003"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1177\/000331979204300504"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1186\/1472-6823-13-41"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1159\/000178975"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/0002-9343(92)90193-F"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-021-00745-6"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1167\/iovs.18-23887"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mvr.2020.104036"}],"container-title":["Journal of Diabetes"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/1753-0407.13354","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/1753-0407.13354","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/1753-0407.13354","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T14:30:35Z","timestamp":1701700235000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/1753-0407.13354"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,15]]},"references-count":35,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,2]]}},"alternative-id":["10.1111\/1753-0407.13354"],"URL":"https:\/\/doi.org\/10.1111\/1753-0407.13354","archive":["Portico"],"relation":{},"ISSN":["1753-0393","1753-0407"],"issn-type":[{"value":"1753-0393","type":"print"},{"value":"1753-0407","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,15]]},"assertion":[{"value":"2022-07-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-12-21","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-01-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}