HERB GUARD AI- AN AI - BASED HERB-DRUG INTERACTION PREDICTION USING NATURAL LANGUAGE PROCESS

Abstract: The growing concurrent use of Ayurvedic and Allopathic medicines has significantly increased the risk of herb–drug interactions (HDIs), many of which remain undetected due to the absence of centralized prediction systems. This paper presents HerbGuard AI, an AI-based system that leverages Natural Language Processing (NLP) to extract interaction-related information from biomedical and traditional Ayurvedic literature. A Knowledge Graph is employed to model and represent structured relationships between herbs, pharmaceutical drugs, and their interaction mechanisms. The proposed system predicts potential interaction risks, thereby improving patient safety and supporting informed clinical decision-making in integrative healthcare. The system is particularly relevant to India's pluralistic health culture, where patients frequently combine modern and traditional medicines without physician supervision. Experimental scenarios demonstrate the system's ability to generate actionable interaction warnings and recommend safe herb–drug combinations.

Keywords: Herb–Drug Interaction, Natural Language Processing, Knowledge Graph, Ayurveda, Artificial Intelligence, Pharmacovigilance, Integrative Medicine, Clinical Decision Support