Domain ontology development of knowledge base in cardiovascular personalized health management

In China, cardiovascular disease has become the leading killer in recent years, and mortality from cardiovascular disease is continuing to rapidly increase. Extant medical research has proven that personal health management (prevention, intervention, and recuperation) of chronic diseases, such as cardiovascular diseases, is the best strategy for their prevention and treatment. Currently, the public can obtain health management knowledge through the Internet, newspapers, books, and other channels. However, with the explosive growth of available information, the public is limited to obtain effective health management guidance due to the characteristics of multiple sources, uneven accuracy (even some contradictory knowledge) and a major paucity of personalization, especially for the general public who lack professional medical knowledge. To address these problems, this paper proposes a knowledge base framework (i.e. domain ontology library) of health management programs based on the cardiovascular disease domain, which can standardize knowledge of health management programs both logically and structurally. In order to satisfy the needs of personalized health management, the core ontology of the domain ontology library is health-management-program ontology. In addition to common ontologies (e.g. disease ontology, drug ontology, etc.), basic ontologies include the ontology of individual health characteristics (e.g. individual-health-characteristics and environmental-characteristics ontology), and ontologies comprising diet and sport (e.g. ingredients, recipes, physical exercise, etc.). We then construct the ontology library through the professional ontology tool, Protege. With a case study, we translate a piece of text health management knowledge into instances of an ontology library. At the same time, we present a personalized health management program recommendation algorithm based on the ontology library, and a recommendation case is realized according to this algorithm. As a basic research, the results of this paper can also support other health management applications in the future.