An AI-Driven Diagnostic System for Early Skin Disease Detection

Abstract

Skin diseases are among the most prevalent health conditions worldwide, necessitating timely and accurate diagnostic tools. This paper presents a comprehensive AI-driven diagnostic system for early skin disease detection, implemented as a web-based application (Ai Skin) that leverages the OpenAI GPT-4o multimodal vision model. The proposed system supports two primary analysis modes: single-image skin analysis and dual-image comparative analysis for tracking disease progression. It integrates structured prompt engineering to extract clinically meaningful outputs including disease classification, severity scoring, skin type assessment, and contextual diagnostic recommendations. To evaluate system performance, controlled experiments were conducted using 200 annotated skin images across five disease categories (Acne, Eczema, Psoriasis, Rosacea, and Fungal Infection), sourced from the publicly available HAM10000 and DermNet datasets. The system achieved an overall accuracy of 91.5%, with a macro-average precision of 90.8%, recall of 89.6%, and F1-score of 90.2%. These results underscore the effectiveness of vision-language models in supporting dermatological decision-making and highlight the practical utility of the Ai Skin system as a non-invasive, accessible screening tool.