Ontology based semantic representation for Public Health data integration

Many health care providers have adopted Electronic Health Records to represent patient's health conditions. A patient visits many health care facilities like hospitals, private practices or primary health care centres for treatment of different ailments. There is a need to integrate the patient's health data from various sources, to provide a comprehensive view of the patient's health status. This data integration has to be seamless and unaffected by technology issues related to the data representation or exchange. The authors modeled data requirements and designed a Public Health Ontology to represent domain knowledge. The relational health data was mapped into instances of the Public Health Ontology to form a knowledge base of health records. The quality of the ontology and the knowledge base was analyzed using a metric based approach. The semantic representation enables interoperability and results prove that the knowledge base is rich in detail and diversity. The Public Health Ontology uses standardized medical terminology and unique patient identifiers to enable data integration which can enable a complete new level of reasoning over health data. However the public health knowledge base is fairly isolated and it needs to be connected to well-known ontology for meaningful use of the public health knowledge base.