Please use this identifier to cite or link to this item:
https://wslhd.intersearch.com.au/wslhdjspui/handle/1/4461
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Habib, Al-Rahim | - |
dc.contributor.author | Crossland, G. | - |
dc.contributor.author | Patel, H. | - |
dc.contributor.author | Wong, E. | - |
dc.contributor.author | Kong, K. | - |
dc.contributor.author | Gunasekera, H. | - |
dc.contributor.author | Richards, B. | - |
dc.contributor.author | Caffery, L. | - |
dc.contributor.author | Perry, C. | - |
dc.contributor.author | Sacks, R. | - |
dc.contributor.author | Kumar, A. | - |
dc.contributor.author | Singh, Narinder | - |
dc.date.accessioned | 2022-08-15T07:14:58Z | - |
dc.date.available | 2022-08-15T07:14:58Z | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | Otology & Neurotology 43(4):481-488, 2022 | - |
dc.identifier.uri | https://wslhd.intersearch.com.au/wslhdjspui/handle/1/4461 | - |
dc.description.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. INTERVENTIONS: 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. | - |
dc.title | An Artificial Intelligence Computer-vision Algorithm to Triage Otoscopic Images From Australian Aboriginal and Torres Strait Islander Children | - |
dc.type | Journal Article | - |
dc.identifier.doi | https://dx.doi.org/10.1097/MAO.0000000000003484 | - |
dc.subject.keywords | Australia | - |
dc.subject.keywords | Computers | - |
dc.subject.keywords | Ear Diseases | - |
dc.subject.keywords | Native Hawaiian or Other Pacific Islander | - |
dc.subject.keywords | Otitis Media | - |
dc.identifier.journaltitle | Otology & Neurotology | - |
dc.identifier.pmid | 35239622 | - |
dc.contributor.wslhd | Habib, Al-Rahim | - |
dc.contributor.wslhd | Singh, Narinder | - |
dc.identifier.facility | Westmead | - |
dc.type.studyortrial | Observational Study | - |
dc.type.studyortrial | Research Support, Non-U.S. Gov't | - |
Appears in Collections: | Westmead Hospital 2019 - 2024 |
Files in This Item:
There are no files associated with this item.
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.