Implementation of Edge AI for Web-Based Atopic Dermatitis Skin Disease Classification Using Streamlit

Atopic dermatitis (AD) is a chronic skin disease with symptoms such as itching, dryness, and redness that interfere with patients quality of life. Its prevalence continues to increase, especially among children. Early diagnosis is crucial for effective treatment, but traditional methods such as allergy tests and biopsies are time-consuming and prone to error. This study proposes an automated classification system based on deep learning integrated with Edge AI for skin image analysis. Edge AI enables local processing, reduces latency, and safeguards data privacy. The system is implemented in a Streamlit-based web application for easy use by medical professionals. Evaluation was conducted using accuracy, precision, recall, specificity, and F1-score. Training results demonstrated high performance: ResNet-34 (96%), MobileNetV3 (98.5%), and EfficientNet-B0 (98.3%), respectively. A system demo is available at: https://www.youtube.com/watch?v=hkbXEbA8Gq0.