Skin disease detection using artificial intelligence

Artificial intelligence (AI) algorithms for automated classification of skin diseases are available to the consumer market. Studies of their diagnostic accuracy are rare. We assessed the diagnostic accuracy of an open-access AI application for recognition of skin diseases. The AI algorithm classifie...

Full description

Saved in:
Bibliographic Details
Main Authors: Kuzhaloli, S., Varalakshmi, L. M., Gulati, Kamal, Upadhyaya, Makarand, Bhasin, Narinder Kumar, Peroumal, Vijayakumar
Format: Conference Proceeding
Language:English
Subjects:
Accuracy
Algorithms
Artificial intelligence
Decision making
Medical personnel
Object recognition
Physicians
Signs and symptoms
Skin diseases
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Artificial intelligence (AI) algorithms for automated classification of skin diseases are available to the consumer market. Studies of their diagnostic accuracy are rare. We assessed the diagnostic accuracy of an open-access AI application for recognition of skin diseases. The AI algorithm classified the images giving 5 differential diagnoses, which were then compared to the diagnoses made clinically by the dermatologists and/or histological. The level of diagnostic accuracy varied considerably for diagnostic groups. The online application demonstrated low diagnostic accuracy compared to a dermatologist evaluation and needs further development. Input signs have been developed to classify the disorder. With the aid of experts in the area, we received symptoms of 10 skin diseases. The symptom data were trained by various classifiers. We observed that high quality AI-based support for clinical decision making enhances the accurate diagnosis of either AI or doctors alone and that less skilled physicians are better served by AI.
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0074207