SkinLearn: A YOLO11-Driven App for Automated Skin Disease Diagnosis from Smartphone Images

Abstract

This study presents SkinLearn, a YOLO11-powered deep learning-based smartphone application (app) designed for real-time skin disease classification using images captured by smartphone cameras. The proposed system addresses critical challenges in mobile-based dermatological diagnosis, such as the diversity of skin conditions, varying image qualities, and computational constraints. By leveraging the enhanced architecture of YOLO11, SkinLearn achieves superior accuracy and speed compared to existing models, making it suitable for on-device deployment in low-resource settings. The model was trained using an open-source skin disease dataset and demonstrated robust performance across multiple disease classes. The YOLO11 model exhibited a 98.3% classification accuracy for skin diseases. The results validate the potential of the system as a practical diagnostic aid for early skin disease identification and clinical decision support. This study contributes to the growing sector of AI-driven mobile healthcare by offering an accessible and scalable solution for dermatological screening.