{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T12:28:40Z","timestamp":1791548920947,"version":"4.3.4"},"reference-count":29,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2022,5,25]],"date-time":"2022-05-25T00:00:00Z","timestamp":1653436800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the Swedish state under the agreement between the Swedish government and the county councils, the ALF-agreement (V\u00e4sterbotten) and the National Association of the Hearing Impaired (HRF)\u2019s research fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background: Otitis media includes several common inflammatory conditions of the middle ear that can have severe complications if left untreated. Correctly identifying otitis media can be difficult and a screening system supported by machine learning would be valuable for this prevalent disease. This study investigated the performance of a convolutional neural network in screening for otitis media using digital otoscopic images labelled by an expert panel. Methods: Five experienced otologists diagnosed 347 tympanic membrane images captured with a digital otoscope. Images with a majority expert diagnosis (n = 273) were categorized into three screening groups Normal, Pathological and Wax, and the same images were used for training and testing of the convolutional neural network. Expert panel diagnoses were compared to the convolutional neural network classification. Different approaches to the convolutional neural network were tested to identify the best performing model. Results: Overall accuracy of the convolutional neural network was above 0.9 in all except one approach. Sensitivity to finding ears with wax or pathology was above 93% in all cases and specificity was 100%. Adding more images to train the convolutional neural network had no positive impact on the results. Modifications such as normalization of datasets and image augmentation enhanced the performance in some instances. Conclusions: A machine learning approach could be used on digital otoscopic images to accurately screen for otitis media.<\/jats:p>","DOI":"10.3390\/diagnostics12061318","type":"journal-article","created":{"date-parts":[[2022,5,26]],"date-time":"2022-05-26T08:50:22Z","timestamp":1653555022000},"page":"1318","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["A Machine Learning Approach to Screen for Otitis Media Using Digital Otoscope Images Labelled by an Expert Panel"],"prefix":"10.3390","volume":"12","author":[{"given":"Josefin","family":"Sandstr\u00f6m","sequence":"first","affiliation":[{"name":"Department of Public Health and Clinical Medicine, Unit of Family Medicine, Ume\u00e5 University, 901 87 Ume\u00e5, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7567-4518","authenticated-orcid":false,"given":"Hermanus","family":"Myburgh","sequence":"additional","affiliation":[{"name":"Department of Electrical, Electronic and Computer Engineering, University of Pretoria, Pretoria 0110, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claude","family":"Laurent","sequence":"additional","affiliation":[{"name":"Department of Public Health and Clinical Medicine, Unit of Medicine, Ume\u00e5 University, 901 87 Ume\u00e5, Sweden"},{"name":"Department of Speech-Language Pathology and Audiology, University of Pretoria, Pretoria 0110, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8313-1636","authenticated-orcid":false,"given":"De Wet","family":"Swanepoel","sequence":"additional","affiliation":[{"name":"Department of Speech-Language Pathology and Audiology, University of Pretoria, Pretoria 0110, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1478-4945","authenticated-orcid":false,"given":"Thorbj\u00f6rn","family":"Lundberg","sequence":"additional","affiliation":[{"name":"Department of Public Health and Clinical Medicine, Unit of Family Medicine, Ume\u00e5 University, 901 87 Ume\u00e5, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,5,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"109837","DOI":"10.1016\/j.ijporl.2019.109837","article-title":"Panel 5: Impact of otitis media on quality of life and development","volume":"130","author":"Heidemann","year":"2020","journal-title":"Int. J. Pediatr. Otorhinolaryngol."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Monasta, L., Ronfani, L., Marchetti, F., Montico, M., Brumatti, L.V., Bavcar, A., Grasso, D., Barbiero, C., and Tamburlini, G. (2012). Burden of Disease Caused by Otitis Media: Systematic Review and Global Estimates. PLoS ONE, 7.","DOI":"10.1371\/journal.pone.0036226"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1289736","DOI":"10.1080\/16549716.2017.1289736","article-title":"Survey of ENT services in sub-Saharan Africa: Little progress between 2009 and 2015","volume":"10","author":"Mulwafu","year":"2017","journal-title":"Glob. Health. Action"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Joshi, R., Alim, M., Kengne, A.P., Jan, S., Maulik, P.K., Peiris, D., and Patel, A.A. (2014). Task Shifting for Non-Communicable Disease Management in Low and Middle Income Countries\u2014A Systematic Review. PLoS ONE, 9.","DOI":"10.1371\/journal.pone.0103754"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"681","DOI":"10.2471\/BLT.18.227371","article-title":"Hearing care across the life course provided in the community","volume":"97","author":"Suen","year":"2019","journal-title":"Bull. World Health Organ."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1177\/1357633X14541038","article-title":"Video-otoscopy recordings for diagnosis of childhood ear disease using telehealth at primary health care level","volume":"20","author":"Biagio","year":"2014","journal-title":"J. Telemed. Telecare"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"327515","DOI":"10.1155\/2013\/327515","article-title":"Automated Diagnosis of Otitis Media: Vocabulary and Grammar","volume":"2013","author":"Kuruvilla","year":"2013","journal-title":"Int. J. Biomed. Imaging"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1016\/j.ebiom.2016.02.017","article-title":"Otitis Media Diagnosis for Developing Countries Using Tympanic Membrane Image-Analysis","volume":"5","author":"Myburgh","year":"2016","journal-title":"EBioMedicine"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1606","DOI":"10.1007\/s11605-017-3518-7","article-title":"An Evaluation of Artificial Neural Networks in Predicting Pancreatic Cancer Survival","volume":"21","author":"Walczak","year":"2017","journal-title":"J. Gastrointest. Surg."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1038\/s41746-019-0172-3","article-title":"Deep learning algorithm predicts diabetic reti-nopathy progression in individual patients","volume":"2","author":"Arcadu","year":"2019","journal-title":"NPJ Digit Med."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.bspc.2017.07.015","article-title":"Towards low cost automated smartphone- and cloud-based otitis media diagnosis","volume":"39","author":"Myburgh","year":"2018","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1186\/s40463-019-0389-9","article-title":"Building an Otoscopic screening prototype tool using deep learning","volume":"48","author":"Livingstone","year":"2019","journal-title":"J. Otolaryngol. Head Neck Surg."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Lee, J.Y., Choi, S.H., and Chung, J.W. (2019). Automated Classification of the Tympanic Membrane Using a Convolutional Neural Net-work. Appl. Sci., 9.","DOI":"10.3390\/app9091827"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1016\/j.ebiom.2019.06.050","article-title":"Automated diagnosis of ear disease using ensemble deep learning with a big otoendoscopy image database","volume":"45","author":"Cha","year":"2019","journal-title":"EBioMedicine"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1038\/s41746-019-0094-0","article-title":"Automated classification platform for the identification of otitis media using optical coherence tomography","volume":"2","author":"Monroy","year":"2019","journal-title":"NPJ Digit. Med."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Viscaino, M., Maass, J.C., Delano, P.H., Torrente, M., Stott, C., and Cheein, F.A. (2020). Computer-aided diagnosis of external and middle ear conditions: A machine learning approach. PLoS ONE, 15.","DOI":"10.1371\/journal.pone.0229226"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1408","DOI":"10.1002\/lary.28292","article-title":"Otoscopic diagnosis using computer vision: An automated machine learning approach","volume":"130","author":"Livingstone","year":"2019","journal-title":"Laryngoscope"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1001\/archpedi.155.10.1137","article-title":"Assessing Diagnostic Accuracy and Tympanocentesis Skills in the Management of Otitis Media","volume":"155","author":"Pichichero","year":"2001","journal-title":"Arch. Pediatr. Adolesc. Med."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1016\/j.ijporl.2008.01.030","article-title":"Recognition of paediatric otopathology by General Practitioners","volume":"72","author":"Buchanan","year":"2008","journal-title":"Int. J. Pediatr. Otorhinolaryngol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1111\/j.1651-2227.2005.tb01912.x","article-title":"Accuracy of acute otitis media diagnosis in community and hospital settings","volume":"94","author":"Asher","year":"2007","journal-title":"Acta Paediatr."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.ijporl.2007.09.010","article-title":"Clinical qualitative evaluation of the diagnosis of acute otitis media in general practice","volume":"72","author":"Legros","year":"2008","journal-title":"Int. J. Pediatr. Otorhinolaryngol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"e964","DOI":"10.1542\/peds.2012-3488","article-title":"The Diagnosis and Management of Acute Otitis Media","volume":"131","author":"Lieberthal","year":"2013","journal-title":"Pediatrics"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"16063","DOI":"10.1038\/nrdp.2016.63","article-title":"Otitis media","volume":"2","author":"Schilder","year":"2016","journal-title":"Nat. Rev. Dis. Primers"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7\u201312). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision snd Pattern Recognition 2015, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1016\/j.neunet.2018.07.011","article-title":"A systematic study of the class imbalance problem in convolutional neural networks","volume":"106","author":"Buda","year":"2018","journal-title":"Neural Netw."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.ijporl.2009.10.029","article-title":"How to improve the accuracy of diagnosing otitis media with effusion in a pediatric population","volume":"74","author":"Lee","year":"2009","journal-title":"Int. J. Pediatr. Otorhinolaryngol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1111\/coa.13925","article-title":"Artificial intelligence to classify ear disease from otoscopy: A systematic review and meta-analysis","volume":"47","author":"Habib","year":"2022","journal-title":"Clin. Otolaryngol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.bbe.2019.11.001","article-title":"Fusing fine-tuned deep features for recognizing different tympanic membranes","volume":"40","year":"2020","journal-title":"Biocybern. Biomed. Eng."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/12\/6\/1318\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:18:44Z","timestamp":1760138324000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/12\/6\/1318"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,25]]},"references-count":29,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2022,6]]}},"alternative-id":["diagnostics12061318"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics12061318","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,25]]}}}