{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T12:28:39Z","timestamp":1791548919087,"version":"4.3.4"},"reference-count":52,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2022,3,15]],"date-time":"2022-03-15T00:00:00Z","timestamp":1647302400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003354","name":"Garnett Passe and Rodney Williams Memorial Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003354","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020021","name":"Avant Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020021","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Clinical Otolaryngology"],"published-print":{"date-parts":[[2022,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To summarise the accuracy of artificial intelligence (AI) computer vision algorithms to classify ear disease from otoscopy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>Systematic review and meta\u2010analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Using the PRISMA guidelines, nine online databases were searched for articles that used AI computer vision algorithms developed from various methods (convolutional neural networks, artificial neural networks, support vector machines, decision trees and k\u2010nearest neighbours) to classify otoscopic images. Diagnostic classes of interest: normal tympanic membrane, acute otitis media (AOM), otitis media with effusion (OME), chronic otitis media (COM) with or without perforation, cholesteatoma and canal obstruction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Main outcome measures<\/jats:title>\n                    <jats:p>Accuracy to correctly classify otoscopic images compared to otolaryngologists (ground truth). The Quality Assessment of Diagnostic Accuracy Studies Version 2 tool was used to assess the quality of methodology and risk of bias.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Thirty\u2010nine articles were included. Algorithms achieved 90.7% (95%CI: 90.1\u201391.3%) accuracy to difference between normal or abnormal otoscopy images in 14\u00a0studies. The most common multiclassification algorithm (3 or more diagnostic classes) achieved 97.6% (95%CI: 97.3\u201397.9%) accuracy to differentiate between normal, AOM and OME in three studies. AI algorithms outperformed human assessors to classify otoscopy images achieving 93.4% (95%CI: 90.5\u201396.4%) versus 73.2% (95%CI: 67.9\u201378.5%) accuracy in three studies. Convolutional neural networks achieved the highest accuracy compared to other classification methods.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>AI can classify ear disease from otoscopy. A concerted effort is required to establish a comprehensive and reliable otoscopy database for algorithm training. An AI\u2010supported otoscopy system may assist health care workers, trainees and primary care practitioners with less otology experience identify ear disease.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/coa.13925","type":"journal-article","created":{"date-parts":[[2022,3,7]],"date-time":"2022-03-07T01:35:07Z","timestamp":1646616907000},"page":"401-413","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":62,"title":["Artificial intelligence to classify ear disease from otoscopy: A systematic review and meta\u2010analysis"],"prefix":"10.1111","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6327-4648","authenticated-orcid":false,"given":"Al\u2010Rahim","family":"Habib","sequence":"first","affiliation":[{"name":"Faculty of Medicine and Health University of Sydney  Sydney New South Wales Australia"},{"name":"Department of Otolaryngology \u2013 Head and Neck Surgery Princess Alexandra Hospital  Woolloongabba Queensland Australia"},{"name":"Department of Otolaryngology \u2010 Head and Neck Surgery Westmead Hospital  Westmead New South Wales Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Majid","family":"Kajbafzadeh","sequence":"additional","affiliation":[{"name":"Faculty of Medicine and Health University of Sydney  Sydney New South Wales Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zubair","family":"Hasan","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology \u2010 Head and Neck Surgery Westmead Hospital  Westmead New South Wales Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5799-5083","authenticated-orcid":false,"given":"Eugene","family":"Wong","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology \u2010 Head and Neck Surgery Westmead Hospital  Westmead New South Wales Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hasantha","family":"Gunasekera","sequence":"additional","affiliation":[{"name":"Faculty of Medicine and Health University of Sydney  Sydney New South Wales Australia"},{"name":"The Children\u2019s Hospital at Westmead  Westmead New South Wales Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chris","family":"Perry","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology \u2013 Head and Neck Surgery Princess Alexandra Hospital  Woolloongabba Queensland Australia"},{"name":"University of Queensland Medical School  Brisbane Queensland Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raymond","family":"Sacks","sequence":"additional","affiliation":[{"name":"Faculty of Medicine and Health University of Sydney  Sydney New South Wales Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashnil","family":"Kumar","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering Faculty of Engineering University of Sydney  Sydney New South Wales Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Narinder","family":"Singh","sequence":"additional","affiliation":[{"name":"Faculty of Medicine and Health University of Sydney  Sydney New South Wales Australia"},{"name":"Department of Otolaryngology \u2010 Head and Neck Surgery Westmead Hospital  Westmead New South Wales Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,3,15]]},"reference":[{"key":"e_1_2_12_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijporl.2008.01.030"},{"key":"e_1_2_12_3_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2273.1995.tb00014.x"},{"key":"e_1_2_12_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsurg.2015.07.011"},{"key":"e_1_2_12_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_2_12_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature21056"},{"issue":"1","key":"e_1_2_12_7_1","first-page":"10","article-title":"Deep learning versus human graders for classifying diabetic retinopathy severity in a nationwide screening program","volume":"2","author":"Raumviboonsuk P","year":"2019","journal-title":"NPJ Digit Med"},{"key":"e_1_2_12_8_1","doi-asserted-by":"publisher","DOI":"10.1093\/jtm\/taaa008"},{"issue":"21","key":"e_1_2_12_9_1","first-page":"1","article-title":"Effect of a comprehensive deep\u2010learning model on the accuracy of chest x\u2010ray interpretation by radiologists: a retrospective, multireader multicase study","volume":"7500","author":"Seah JCY","year":"2021","journal-title":"Lancet Digit Health"},{"key":"e_1_2_12_10_1","doi-asserted-by":"publisher","DOI":"10.1177\/0194599818809337"},{"key":"e_1_2_12_11_1","doi-asserted-by":"publisher","DOI":"10.1258\/jtt.2012.gth114"},{"key":"e_1_2_12_12_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1000097"},{"key":"e_1_2_12_13_1","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-155-8-201110180-00009"},{"key":"e_1_2_12_14_1","unstructured":"HigginsJ&GreenS.Cochrane handbook for systematic reviews of interventions version 5.1.0 [Internet].2011. Accessed February 18 2021.www.cochrane\u2010handbook.org"},{"key":"e_1_2_12_15_1","volume-title":"Modelling and analysis of active biopotential signals in healthcare","author":"Simon C","year":"2020"},{"issue":"1","key":"e_1_2_12_16_1","first-page":"1","article-title":"Convolutional neural network approach for automatic tympanic membrane detection and classification","volume":"56","author":"Basaran E","year":"2020","journal-title":"Biomed Signal Process Control"},{"key":"e_1_2_12_17_1","unstructured":"GoshtasbiK.Machine learning models to predict diagnosis and surgical outcomes in otolaryngology [Internet]. University of California Irvine;2020. Accessed January 3 2021.https:\/\/escholarship.org\/uc\/item\/1tr0c2p0"},{"key":"e_1_2_12_18_1","doi-asserted-by":"publisher","DOI":"10.1097\/MAO.0000000000003210"},{"key":"e_1_2_12_19_1","unstructured":"Mironic\u01ceI VertanC GheorgheDC.Automatic pediatric otitis detection by classification of global image features. 2011 E\u2010Health and Bioengineering Conference EHB 2011.2011;1\u20104."},{"key":"e_1_2_12_20_1","doi-asserted-by":"publisher","DOI":"10.1542\/peds.2020-034546"},{"key":"e_1_2_12_21_1","first-page":"1","article-title":"Deep learning for classification of pediatric otitis media","volume":"131","author":"Wu Z","year":"2020","journal-title":"Laryngoscope"},{"key":"e_1_2_12_22_1","doi-asserted-by":"crossref","unstructured":"HuangYK HuangCP.A depth\u2010first search algorithm based otoscope application for real\u2010time otitis media image interpretation. Parallel and Distributed Computing Applications and Technologies PDCAT Proceedings. 2018;2017\u2010Decem:170\u20135.","DOI":"10.1109\/PDCAT.2017.00036"},{"key":"e_1_2_12_23_1","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/327515"},{"key":"e_1_2_12_24_1","first-page":"2845","article-title":"Otitis media vocabulary and grammar","volume":"2012","author":"Kuruvilla A","year":"2012","journal-title":"Proc Int Conf Image Proc"},{"key":"e_1_2_12_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102034"},{"key":"e_1_2_12_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/lary.28292"},{"key":"e_1_2_12_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.03.023"},{"key":"e_1_2_12_28_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2020-041139"},{"key":"e_1_2_12_29_1","doi-asserted-by":"publisher","DOI":"10.3390\/jcm10153198"},{"key":"e_1_2_12_30_1","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2021.810427"},{"key":"e_1_2_12_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijporl.2004.10.013"},{"key":"e_1_2_12_32_1","unstructured":"GeronA G\u00e9ronA.Hands\u2010on machine learing with scikit\u2010learn & tensor flow [Internet]. O\u2019Reilly Media;2017:760. Accessed March 18 2021.http:\/\/arxiv.org\/abs\/1412.3919"},{"key":"e_1_2_12_33_1","unstructured":"KasherMS.Otitis media analysis\u2010an automated feature extraction and image classification system.2018. Accessed November 10 2018.https:\/\/www.theseus.fi\/handle\/10024\/144562"},{"key":"e_1_2_12_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2021.102065"},{"key":"e_1_2_12_35_1","doi-asserted-by":"publisher","DOI":"10.1542\/peds.2020-049584"},{"key":"e_1_2_12_36_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.17216"},{"key":"e_1_2_12_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2018.01.034"},{"key":"e_1_2_12_38_1","doi-asserted-by":"publisher","DOI":"10.1177\/00034894800890S317"},{"key":"e_1_2_12_39_1","article-title":"The theory behind overfitting, cross validation, regularization, bagging, and boosting: tutorial","author":"Ghojogh B","year":"2019","journal-title":"arXiv"},{"key":"e_1_2_12_40_1","doi-asserted-by":"publisher","DOI":"10.1021\/ci025626i"},{"key":"e_1_2_12_41_1","doi-asserted-by":"publisher","DOI":"10.1214\/09-SS054"},{"key":"e_1_2_12_42_1","doi-asserted-by":"publisher","DOI":"10.1080\/14992027.2021.1983217"},{"key":"e_1_2_12_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2017.07.015"},{"key":"e_1_2_12_44_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.2293297"},{"key":"e_1_2_12_45_1","doi-asserted-by":"publisher","DOI":"10.1097\/MAO.0000000000001897"},{"issue":"2017","key":"e_1_2_12_46_1","first-page":"101341X","article-title":"Autoscope: automated otoscopy image analysis to diagnose ear pathology and use of clinically motivated eardrum features","volume":"10134","author":"Senaras C","year":"2017","journal-title":"Med Imaging 2017: Compu\u2010Aided Diagnosis"},{"key":"e_1_2_12_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2016.02.017"},{"key":"e_1_2_12_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2015.03.025"},{"key":"e_1_2_12_49_1","unstructured":"ShieCK ChangHT FanFC et al.A hybrid feature\u2010based segmentation and classification system for the computer aided self\u2010diagnosis of otitis media. In: 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society EMBC 2014.2014:4655\u20134658."},{"key":"e_1_2_12_50_1","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/327515"},{"key":"e_1_2_12_51_1","first-page":"2845","article-title":"Otitis media vocabulary and grammar","author":"Kuruvilla A","year":"2012","journal-title":"IEEE"},{"key":"e_1_2_12_52_1","unstructured":"Mironic\u01ceI VertanC GheorgheDC.Automatic pediatric otitis detection by classification of global image features. 2011 E\u2010Health and Bioengineering Conference EHB 2011.2011:1\u20134."},{"key":"e_1_2_12_53_1","doi-asserted-by":"crossref","unstructured":"VertanC GheorgheDC IonescuB Eardrum color content analysis in video\u2010otoscopy images for the diagnosis support of pediatric otitis. ISSCS 2011 \u2010 International Symposium on Signals Circuits and Systems Proceedings.2011;129\u201332.","DOI":"10.1109\/ISSCS.2011.5978676"}],"container-title":["Clinical Otolaryngology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/coa.13925","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/coa.13925","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/coa.13925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T23:23:22Z","timestamp":1692833002000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/coa.13925"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,15]]},"references-count":52,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["10.1111\/coa.13925"],"URL":"https:\/\/doi.org\/10.1111\/coa.13925","archive":["Portico"],"relation":{"has-review":[{"id-type":"doi","id":"10.1111\/COA.13925\/v1\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1111\/COA.13925\/v2\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1111\/COA.13925\/v1\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1111\/COA.13925\/v1\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1111\/COA.13925\/v2\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1111\/COA.13925\/v2\/review2","asserted-by":"object"}]},"ISSN":["1749-4478","1749-4486"],"issn-type":[{"value":"1749-4478","type":"print"},{"value":"1749-4486","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,15]]},"assertion":[{"value":"2021-11-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-02-27","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-03-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}