Multi-Attribute Deep Learning–Based Approach for Detecting Skin Diseases with Medical Plant Recommendations

Skin diseases are among the most common health problems affecting people of all age groups across the world. Conditions such as melanoma, dermatitis, fungal infections, and keratosis require early diagnosis to avoid severe complications. However, many patients visit hospitals even for minor skin issues, leading to overcrowding and increased healthcare costs. In rural and remote areas, access to dermatologists is limited, which further delays diagnosis. Recent advancements in artificial intelligence, particularly deep learning, have shown great potential in medical image analysis. This paper proposes a multi-attribute deep learning–based framework for automated skin disease detection using image processing techniques. The system employs a Convolutional Neural Network (CNN) to extract multiple visual attributes such as color variation, texture patterns, and lesion structure from skin images. The model is trained to classify multiple skin diseases including melanoma, dermatitis, fungal infections, and benign lesions. Along with disease prediction, the system integrates a medical plant recommendation module to support preliminary care using traditional herbal knowledge. The proposed solution is implemented as a web-based application using Python and Flask, allowing users to upload images and receive instant diagnostic results. Experimental evaluation demonstrates reliable accuracy, fast response time, and improved accessibility. This approach effectively combines modern artificial intelligence with traditional medicine awareness to provide a smart, cost-effective healthcare support system.