INFOTECH SOFT, INC. — Department of Health and Human Services SBIR Phase II: The proposed Epidemiology Data Integration and Analysis platform, EpiDIA, is designed to e

Description

The proposed Epidemiology Data Integration and Analysis platform, EpiDIA, is designed to enable integration of the diverse datasets used in epidemiology research and enable the design of user-defined queries, data mining and investigator-initiated analysis. It will enable the deployment of data both as a physical and as a virtual data warehousing solution. The platform will feature an M-ETL engine that applies a Semantic Web data modeling feature interactively during the design of the data extraction, transformation and loading procedures. The innovative approach will be used to analyze the ontology models of data sources and related biomedical ontologies and identify matching definitions to guide the ETL process to build a more efficient data warehouse. EpiDIA will also feature a semantically-enabled data analysis framework within a Web-based user interface for the semantic connection of proven statistical, hylogenetic and sequence analysis tools. The achievement of this objective requires the definition of a standardized representation of analysis tools and the establishment of a mechanism to provide semantic annotations to such standardized representations and to reference concepts from semantic models such as ontologies. During Phase I, prototypes of the EpiDIA components will be created and evaluated to demonstrate feasibility of the proposed approach.