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

• Published in: Journal of biomedical informatics 2020-08, Vol.108, p.103504-103504, Article 103504
• Main Authors: Sung, Han-Yu, Chi, Yu-Liang
• Format: Article
• Language: English
• Subjects: Open data; Over-the-counter medicine; Self-medication; Semantic Web; SPARQL
• ISSN: 1532-0464; 1532-0480
• DOI: 10.1016/j.jbi.2020.103504

[Display omitted] •An improved medicine query system has been developed especially for self-medication users.•A pilot experiment for skin ailments was implemented.•Users who are unable to utilize the keyword-based search can manipulate inference-based search instead.•The search is comprised of three successive processes of symptom identification, ailment inference and identification, and retrieving medicinal products. This study developed a medicine query system based on Semantic Web and open data especially for self-medication users to search over-the-counter (OTC) medicines. Most existing medicine query systems are based on keyword searches. If users are uncertain about the exact search words, these query systems do not offer effective help. Furthermore, most systems provide inadequate explanations of symptoms and ailments for users to use with confidence. To remedy these issues, this study builds a knowledge base to enable inference-based searches and data mashup for integrating information from across the Web. Three components were identified: (1) building an ontology model to describe the relationships between ailments and symptoms; (2) upgrading medicinal product datasets to link them with the ontology model on a semantic level; and (3) developing a data mashup to integrate web resources to help users to find references. Furthermore, the aim was to develop a web-based application that utilizes inference mechanisms to provide users with tools for interactive manipulation. A pilot experiment for skin ailments was implemented to learn the problem-solving skills of the system. Finally, two experts utilized a content validity index to rate a four-dimension 15-item scale. The evaluation results show that experts found the proposed system excellent for content validity.