An Artificial Intelligence Computer-vision Algorithm to Triage Otoscopic Images From Australian Aboriginal and Torres Strait Islander Children. Issue 4 (2nd April 2022)

• Record Type: Journal Article
• Authors: Habib, Al-Rahim; Crossland, Graeme; Patel, Hemi; Wong, Eugene; Kong, Kelvin; Gunasekera, Hasantha; Richards, Brent; Caffery, Liam; Perry, Chris; Sacks, Raymond; Kumar, Ashnil; Singh, Narinder
• Is Part Of: Otology & neurotology. Volume 43:Issue 4(2022)
• Page Start: 481
• Page End: 488
• Publication Date: 2022-04-02
• Subjects: Artificial intelligence -- Computer-vision -- Deep learning -- Image classification -- Machine learning -- Otitis media -- Otoscopy -- Triage; Otology -- Periodicals; Ear -- Diseases -- Periodicals; Skull base -- Surgery -- Periodicals; 617.8005
• DOI: 10.1097/MAO.0000000000003484
• Languages: English
• ISSNs: 1531-7129

Abstract

Abstract : Objective: To develop an artificial intelligence image classification algorithm to triage otoscopic images from rural and remote Australian Aboriginal and Torres Strait Islander children. Study Design: Retrospective observational study. Setting: Tertiary referral center. Patients: Rural and remote Aboriginal and Torres Strait Islander children who underwent tele-otology ear health screening in the Northern Territory, Australia between 2010 and 2018. Intervention(s): Otoscopic images were labeled by otolaryngologists to classify the ground truth. Deep and transfer learning methods were used to develop an image classification algorithm. Main Outcome Measures: Accuracy, sensitivity, specificity, positive predictive value, negative predictive value, area under the curve (AUC) of the resultant algorithm compared with the ground truth. Results: Six thousand five hundred twenty seven images were used (5927 images for training and 600 for testing). The algorithm achieved an accuracy of 99.3% for acute otitis media, 96.3% for chronic otitis media, 77.8% for otitis media with effusion (OME), and 98.2% to classify wax/obstructed canal. To differentiate between multiple diagnoses, the algorithm achieved 74.4 to 92.8% accuracy and an AUC of 0.963 to 0.997. The most common incorrect classification pattern was OME misclassified as normal tympanic membranes. Conclusions: The paucity of access to tertiary otolaryngology care for rural and remote Aboriginal and Torres Strait Islander communities may contribute to an under-identification of ear disease. Computer vision image classification algorithms can accurately classify ear disease from otoscopic images of Indigenous Australian children. In the future, a validated algorithm may integrate with existing telemedicine initiatives to support effective triage and facilitate early treatment and referral.