A deep learning system for differential diagnosis of skin diseases
By Yuan Liu, Ayush Jain, Clara Eng, David H. Way, Kang Lee, P. Bui, K. Kanada, Guilherme de Oliveira Marinho, J. Gallegos, Sara Gabriele and 12 more. 2019
760 citations recorded by the source corpus.
Skin conditions affect 1.9 billion people. Because of a shortage of dermatologists, most cases are seen instead by general practitioners with lower diagnostic accuracy. We present a deep learning system (DLS) to provide a differential diagnosis of skin conditions using 16,114 de-identified cases (photographs and clinical data) from a teledermatology practice serving 17 sites. The DLS distinguishes between 26 common skin conditions, representing 80% of cases seen in primary care, while also providing a secondary prediction covering 419 skin conditions. On 963 validation cases, where a rotating panel of three board-certified dermatologists defined the reference standard, the DLS was non-inferior to six other dermatologists and superior to six primary care physicians (PCPs) and six nurse practitioners (NPs) (top-1 accuracy: 0.66 DLS, 0.63 dermatologists, 0.44 PCPs and 0.40 NPs). These results highlight the potential of the DLS to assist general practitioners in diagnosing skin conditions. A deep learning system able to identify the most common skin conditions may help clinicians in making more accurate diagnoses in routine clinical practice
Subfields: Computer Vision and Pattern Recognition, Dermatology, Infectious Diseases, Oncology, Medical Imaging, Medical & Health AI
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Trevor Darrell
- Dacheng Tao
- Xiaogang Wang
- Ming-Hsuan Yang
- Andrew Zisserman
- Jitendra Malik
- Bernt Schiele
In Dermatology
In Oncology
In Medical & Health AI
Citations in the corpus
- Big Self-Supervised Models Advance Medical Image Classification (2021, methodology): “Our primary metrics for the dermatology task are top-1 accuracy and Area Under the Curve (AUC) following [29].”
- Disparities in dermatology AI performance on a diverse, curated clinical image set (2021, methodology): “Many previously published algorithms have relied on visual consensus labels from a small group of dermatologists (4, 5, 19).”
- Integrated multimodal artificial intelligence framework for healthcare applications (2022, background): “Recently, AI/ML models leveraging multiple data modalities have been demonstrated for the domains of cardiology 7 – 9 , dermatology 10 , gastroenterology 11 , gynecology 12 , hematology 13 , immunology 14 , nephrology 15 , neurology 16,17 , oncology 18 – 20 , ophthalmology 21 , psychiatry 22 ,…”
- Towards accurate differential diagnosis with large language models (2023, positive): “Deep learning has been applied to promising effect for generating DDx in a number of specialties including radiology 4 , ophthalmology 5 and dermatology 3 , but such systems lack the interactive capabilities to fluently assist a user through communication in natural language.”