A knowledge-based system to find over-the-counter medicines for self-medication

Area of Science:

• Health Informatics
• Semantic Web Technologies
• Computational Medicine

Background:

• Existing medicine query systems often rely on basic keyword searches, limiting usability for users uncertain about exact terms.
• Inadequate explanations of symptoms and ailments in current systems hinder user confidence in self-medication decisions.

Purpose of the Study:

• To develop an advanced medicine query system for self-medication users, focusing on over-the-counter (OTC) medicines.
• To overcome limitations of keyword-based searches by enabling inference-based queries and data mashup.
• To improve user confidence through comprehensive information integration and interactive tools.

Main Methods:

• Developed an ontology model to map relationships between ailments and symptoms.
• Semantically linked medicinal product datasets to the ontology.
• Created a data mashup to integrate web resources for comprehensive information retrieval.
• Built a web-based application with inference mechanisms for interactive user support.

Main Results:

• A pilot experiment for skin ailments demonstrated the system's problem-solving capabilities.
• Expert evaluation using a content validity index rated the system as excellent.
• The system effectively integrates information and supports inference-based searches.

Conclusions:

• The developed Semantic Web-based medicine query system significantly improves information access for self-medication.
• The system's inference capabilities and data integration enhance user understanding and confidence.
• The expert-validated system shows high content validity and potential for practical application.