Work

Facilitating Cohort Discovery by Enhancing Ontology Exploration, Query Management and Query Sharing for Large Clinical Data Repositories.

Year: 2017

Type: article

Abstract: To help researchers better access clinical data, we developed a prototype query engine called DataSphere for exploring large-scale integrated clinical data repositories. DataSphere expedites data importing using a NoSQL data management system and dynamically renders its user interface for concept-based querying tasks. DataSphere provides an interactive query-building interface together with query translation and optimization strategies, which enable users to build and execute queries effectively and efficiently. We successfully loaded a dataset of one million patients for University of Kentucky (UK) Healthcare into DataSphere with more than 300 million clinical data records. We evaluated DataSphere by comparing it with an instance of i2b2 deployed at UK Healthcare, demonstrating that DataSphere provides enhanced user experience for both query building and execution.

Source: PubMed Central

Authors: Shiqiang Tao, Licong Cui, Xi Wu, Guo-Qiang Zhang

Institution: University of Kentucky

Language: English

Topic: Electronic Health Records Systems

Subfield: Health Information Management

Field: Health Professions

Domain: Health Sciences

SDG: Good health and well-being

Open Access status: green

Funder: National Institutes of Health

Award: Kentucky Center for Clinical and Translational Science