Evaluating the generalizability of deep learning image classification algorithms to detect middle ear disease using otoscopy

To evaluate the generalizability of artificial intelligence (AI) algorithms that use deep learning methods to identify middle ear disease from otoscopic images, between internal to external performance. 1842 otoscopic images were collected from three independent sources: (a) Van, Turkey, (b) Santiag...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Scientific reports Ročník 13; číslo 1; s. 5368 - 9
Hlavní autoři: Habib, Al-Rahim, Xu, Yixi, Bock, Kris, Mohanty, Shrestha, Sederholm, Tina, Weeks, William B., Dodhia, Rahul, Ferres, Juan Lavista, Perry, Chris, Sacks, Raymond, Singh, Narinder
Médium: Journal Article
Jazyk:angličtina
Vydáno: London Nature Publishing Group UK 01.04.2023
Nature Publishing Group
Nature Portfolio
Témata:
692/308/575
692/700/139
692/700/478
Algorithms
Artificial Intelligence
Deep Learning
Ear diseases
Ear Diseases - diagnostic imaging
Humanities and Social Sciences
Humans
Middle ear
multidisciplinary
Otoscopy - methods
Science
Science (multidisciplinary)
Teaching methods
ISSN:2045-2322, 2045-2322
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:To evaluate the generalizability of artificial intelligence (AI) algorithms that use deep learning methods to identify middle ear disease from otoscopic images, between internal to external performance. 1842 otoscopic images were collected from three independent sources: (a) Van, Turkey, (b) Santiago, Chile, and (c) Ohio, USA. Diagnostic categories consisted of (i) normal or (ii) abnormal. Deep learning methods were used to develop models to evaluate internal and external performance, using area under the curve (AUC) estimates. A pooled assessment was performed by combining all cohorts together with fivefold cross validation. AI-otoscopy algorithms achieved high internal performance (mean AUC: 0.95, 95%CI: 0.80–1.00). However, performance was reduced when tested on external otoscopic images not used for training (mean AUC: 0.76, 95%CI: 0.61–0.91). Overall, external performance was significantly lower than internal performance (mean difference in AUC: −0.19, p ≤ 0.04). Combining cohorts achieved a substantial pooled performance (AUC: 0.96, standard error: 0.01). Internally applied algorithms for otoscopy performed well to identify middle ear disease from otoscopy images. However, external performance was reduced when applied to new test cohorts. Further efforts are required to explore data augmentation and pre-processing techniques that might improve external performance and develop a robust, generalizable algorithm for real-world clinical applications.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-023-31921-0