Development of an artificial intelligence algorithm for the diagnosis of infantile hemangiomas.

April J ZhangNick LindbergSarah L ChamlinAnita N HaggstromAnthony J ManciniDawn H SiegelBeth A Drolet

Published in: Pediatric dermatology (2022)

Prompt and accurate diagnosis of infantile hemangiomas is essential to prevent potential complications. This can be difficult due to high rates of misdiagnosis and poor access to pediatric dermatologists. In this study, we trained an artificial intelligence algorithm to diagnose infantile hemangiomas based on clinical images. Our algorithm achieved a 91.7% overall accuracy in the diagnosis of facial infantile hemangiomas.

Keyphrases

artificial intelligence
deep learning
machine learning
big data
convolutional neural network
high resolution
risk assessment
resistance training
climate change
human health
mass spectrometry
young adults