Development and Evaluation of a Specialized Retrieval-Augmented Generation System for Cosmetic Product Safety Assessment in Xeroderma Pigmentosum Patients
Abstract
Xeroderma Pigmentosum (XP) is a rare autosomal recessive disorder affecting about 1 in 1,000,000 individuals, characterized by extreme UV sensitivity due to impaired DNA repair. XP patients face significant challenges in choosing safe cosmetic products, as many contain photosensitizing agents that can trigger severe skin reactions. This study introduces a specialized Retrieval-Augmented Generation (RAG) system for automated safety assessment of cosmetics tailored to XP-specific constraints. The multimodal framework integrates OCR for ingredient extraction, semantic retrieval from dermatological databases, and personalized risk analysis. It draws on curated XP-focused knowledge, chemical relationship mapping, and con-textual recommendation generation. Evaluated on 847 cosmetic ingredients, the system achieved 95.27% precision for high-risk identification, perfect recall@3, and a 26.2% improvement in semantic alignment over standard LLMs. Expert reviews rated its clinical utility at 4.7/5.0, with high clarity in risk communication and strong adherence to uncertainty standards. The approach offers a replicable model for AI-driven safety support in rare disease contexts, potentially reducing XP-related dermatological crises by up to 47% and enhancing patient autonomy in daily decision-making.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.