A deep learning system for differential diagnosis of skin diseases

A deep learning system for differential diagnosis of skin diseases. Liu, Y., Jain, A., Eng, C., Way, D. H., Lee, K., Bui, P., Kanada, K., de Oliveira Marinho, G., Gallegos, J., Gabriele, S., Gupta, V., Singh, N., Natarajan, V., Hofmann-Wellenhof, R., Corrado, G. S., Peng, L. H., Webster, D. R., Ai, D., Huang, S. J., Liu, Y., Dunn, R. C., & Coz, D. Nature Medicine, 26(6):900–908, June, 2020.

Paper doi abstract bibtex

Skin conditions affect 1.9 billion people. Because of a shortage of dermatologists, most cases are seen instead by general practitioners with lower diagnostic accuracy. We present a deep learning system (DLS) to provide a differential diagnosis of skin conditions using 16,114 de-identified cases (photographs and clinical data) from a teledermatology practice serving 17 sites. The DLS distinguishes between 26 common skin conditions, representing 80% of cases seen in primary care, while also providing a secondary prediction covering 419 skin conditions. On 963 validation cases, where a rotating panel of three board-certified dermatologists defined the reference standard, the DLS was non-inferior to six other dermatologists and superior to six primary care physicians (PCPs) and six nurse practitioners (NPs) (top-1 accuracy: 0.66 DLS, 0.63 dermatologists, 0.44 PCPs and 0.40 NPs). These results highlight the potential of the DLS to assist general practitioners in diagnosing skin conditions.

@article{liu_deep_2020,
	title = {A deep learning system for differential diagnosis of skin diseases},
	volume = {26},
	issn = {1078-8956, 1546-170X},
	url = {http://www.nature.com/articles/s41591-020-0842-3},
	doi = {10/ghjtjw},
	abstract = {Skin conditions affect 1.9 billion people. Because of a shortage of dermatologists, most cases are seen instead by general practitioners with lower diagnostic accuracy. We present a deep learning system (DLS) to provide a differential diagnosis of skin conditions using 16,114 de-identified cases (photographs and clinical data) from a teledermatology practice serving 17 sites. The DLS distinguishes between 26 common skin conditions, representing 80\% of cases seen in primary care, while also providing a secondary prediction covering 419 skin conditions. On 963 validation cases, where a rotating panel of three board-certified dermatologists defined the reference standard, the DLS was non-inferior to six other dermatologists and superior to six primary care physicians (PCPs) and six nurse practitioners (NPs) (top-1 accuracy: 0.66 DLS, 0.63 dermatologists, 0.44 PCPs and 0.40 NPs). These results highlight the potential of the DLS to assist general practitioners in diagnosing skin conditions.},
	language = {en},
	number = {6},
	urldate = {2020-11-13},
	journal = {Nature Medicine},
	author = {Liu, Yuan and Jain, Ayush and Eng, Clara and Way, David H. and Lee, Kang and Bui, Peggy and Kanada, Kimberly and de Oliveira Marinho, Guilherme and Gallegos, Jessica and Gabriele, Sara and Gupta, Vishakha and Singh, Nalini and Natarajan, Vivek and Hofmann-Wellenhof, Rainer and Corrado, Greg S. and Peng, Lily H. and Webster, Dale R. and Ai, Dennis and Huang, Susan J. and Liu, Yun and Dunn, R. Carter and Coz, David},
	month = jun,
	year = {2020},
	pages = {900--908},
}

Downloads: 0

{"_id":"APL3EsfCt8qd32TRX","bibbaseid":"liu-jain-eng-way-lee-bui-kanada-deoliveiramarinho-etal-adeeplearningsystemfordifferentialdiagnosisofskindiseases-2020","author_short":["Liu, Y.","Jain, A.","Eng, C.","Way, D. H.","Lee, K.","Bui, P.","Kanada, K.","de Oliveira Marinho, G.","Gallegos, J.","Gabriele, S.","Gupta, V.","Singh, N.","Natarajan, V.","Hofmann-Wellenhof, R.","Corrado, G. S.","Peng, L. H.","Webster, D. R.","Ai, D.","Huang, S. J.","Liu, Y.","Dunn, R. C.","Coz, D."],"bibdata":{"bibtype":"article","type":"article","title":"A deep learning system for differential diagnosis of skin diseases","volume":"26","issn":"1078-8956, 1546-170X","url":"http://www.nature.com/articles/s41591-020-0842-3","doi":"10/ghjtjw","abstract":"Skin conditions affect 1.9 billion people. Because of a shortage of dermatologists, most cases are seen instead by general practitioners with lower diagnostic accuracy. We present a deep learning system (DLS) to provide a differential diagnosis of skin conditions using 16,114 de-identified cases (photographs and clinical data) from a teledermatology practice serving 17 sites. The DLS distinguishes between 26 common skin conditions, representing 80% of cases seen in primary care, while also providing a secondary prediction covering 419 skin conditions. On 963 validation cases, where a rotating panel of three board-certified dermatologists defined the reference standard, the DLS was non-inferior to six other dermatologists and superior to six primary care physicians (PCPs) and six nurse practitioners (NPs) (top-1 accuracy: 0.66 DLS, 0.63 dermatologists, 0.44 PCPs and 0.40 NPs). These results highlight the potential of the DLS to assist general practitioners in diagnosing skin conditions.","language":"en","number":"6","urldate":"2020-11-13","journal":"Nature Medicine","author":[{"propositions":[],"lastnames":["Liu"],"firstnames":["Yuan"],"suffixes":[]},{"propositions":[],"lastnames":["Jain"],"firstnames":["Ayush"],"suffixes":[]},{"propositions":[],"lastnames":["Eng"],"firstnames":["Clara"],"suffixes":[]},{"propositions":[],"lastnames":["Way"],"firstnames":["David","H."],"suffixes":[]},{"propositions":[],"lastnames":["Lee"],"firstnames":["Kang"],"suffixes":[]},{"propositions":[],"lastnames":["Bui"],"firstnames":["Peggy"],"suffixes":[]},{"propositions":[],"lastnames":["Kanada"],"firstnames":["Kimberly"],"suffixes":[]},{"propositions":["de"],"lastnames":["Oliveira","Marinho"],"firstnames":["Guilherme"],"suffixes":[]},{"propositions":[],"lastnames":["Gallegos"],"firstnames":["Jessica"],"suffixes":[]},{"propositions":[],"lastnames":["Gabriele"],"firstnames":["Sara"],"suffixes":[]},{"propositions":[],"lastnames":["Gupta"],"firstnames":["Vishakha"],"suffixes":[]},{"propositions":[],"lastnames":["Singh"],"firstnames":["Nalini"],"suffixes":[]},{"propositions":[],"lastnames":["Natarajan"],"firstnames":["Vivek"],"suffixes":[]},{"propositions":[],"lastnames":["Hofmann-Wellenhof"],"firstnames":["Rainer"],"suffixes":[]},{"propositions":[],"lastnames":["Corrado"],"firstnames":["Greg","S."],"suffixes":[]},{"propositions":[],"lastnames":["Peng"],"firstnames":["Lily","H."],"suffixes":[]},{"propositions":[],"lastnames":["Webster"],"firstnames":["Dale","R."],"suffixes":[]},{"propositions":[],"lastnames":["Ai"],"firstnames":["Dennis"],"suffixes":[]},{"propositions":[],"lastnames":["Huang"],"firstnames":["Susan","J."],"suffixes":[]},{"propositions":[],"lastnames":["Liu"],"firstnames":["Yun"],"suffixes":[]},{"propositions":[],"lastnames":["Dunn"],"firstnames":["R.","Carter"],"suffixes":[]},{"propositions":[],"lastnames":["Coz"],"firstnames":["David"],"suffixes":[]}],"month":"June","year":"2020","pages":"900–908","bibtex":"@article{liu_deep_2020,\n\ttitle = {A deep learning system for differential diagnosis of skin diseases},\n\tvolume = {26},\n\tissn = {1078-8956, 1546-170X},\n\turl = {http://www.nature.com/articles/s41591-020-0842-3},\n\tdoi = {10/ghjtjw},\n\tabstract = {Skin conditions affect 1.9 billion people. Because of a shortage of dermatologists, most cases are seen instead by general practitioners with lower diagnostic accuracy. We present a deep learning system (DLS) to provide a differential diagnosis of skin conditions using 16,114 de-identified cases (photographs and clinical data) from a teledermatology practice serving 17 sites. The DLS distinguishes between 26 common skin conditions, representing 80\\% of cases seen in primary care, while also providing a secondary prediction covering 419 skin conditions. On 963 validation cases, where a rotating panel of three board-certified dermatologists defined the reference standard, the DLS was non-inferior to six other dermatologists and superior to six primary care physicians (PCPs) and six nurse practitioners (NPs) (top-1 accuracy: 0.66 DLS, 0.63 dermatologists, 0.44 PCPs and 0.40 NPs). These results highlight the potential of the DLS to assist general practitioners in diagnosing skin conditions.},\n\tlanguage = {en},\n\tnumber = {6},\n\turldate = {2020-11-13},\n\tjournal = {Nature Medicine},\n\tauthor = {Liu, Yuan and Jain, Ayush and Eng, Clara and Way, David H. and Lee, Kang and Bui, Peggy and Kanada, Kimberly and de Oliveira Marinho, Guilherme and Gallegos, Jessica and Gabriele, Sara and Gupta, Vishakha and Singh, Nalini and Natarajan, Vivek and Hofmann-Wellenhof, Rainer and Corrado, Greg S. and Peng, Lily H. and Webster, Dale R. and Ai, Dennis and Huang, Susan J. and Liu, Yun and Dunn, R. Carter and Coz, David},\n\tmonth = jun,\n\tyear = {2020},\n\tpages = {900--908},\n}\n\n\n\n","author_short":["Liu, Y.","Jain, A.","Eng, C.","Way, D. H.","Lee, K.","Bui, P.","Kanada, K.","de Oliveira Marinho, G.","Gallegos, J.","Gabriele, S.","Gupta, V.","Singh, N.","Natarajan, V.","Hofmann-Wellenhof, R.","Corrado, G. S.","Peng, L. H.","Webster, D. R.","Ai, D.","Huang, S. J.","Liu, Y.","Dunn, R. C.","Coz, D."],"key":"liu_deep_2020","id":"liu_deep_2020","bibbaseid":"liu-jain-eng-way-lee-bui-kanada-deoliveiramarinho-etal-adeeplearningsystemfordifferentialdiagnosisofskindiseases-2020","role":"author","urls":{"Paper":"http://www.nature.com/articles/s41591-020-0842-3"},"metadata":{"authorlinks":{}},"downloads":0,"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/apolea","dataSources":["f9QNc6eirHM3cmhSh"],"keywords":[],"search_terms":["deep","learning","system","differential","diagnosis","skin","diseases","liu","jain","eng","way","lee","bui","kanada","de oliveira marinho","gallegos","gabriele","gupta","singh","natarajan","hofmann-wellenhof","corrado","peng","webster","ai","huang","liu","dunn","coz"],"title":"A deep learning system for differential diagnosis of skin diseases","year":2020}