A1014
Title: Use of electronic health records data for research: Challenges and opportunities
Authors: Hulin Wu - University of Texas Health Science Center at Houston (United States) [presenting]
Abstract: The challenges and opportunities from the real-world Electronic Health Records (EHR) data are introduced and discussed from a Big Data perspective. In particular, we propose a 9-step procedure that describes the whole lifecycle of EHR research projects from project initiation and data extraction to the result dissemination: 1) Initiate a project: proposing a research topic with potential high-impact biomedical and clinical questions or hypotheses; 2) Data queries and data extraction; 3) Data cleaning; 4) Data processing; 5) Data preparation; 6) Data analysis, modeling and prediction; 7) Result validation; 8) Result interpretation; and 9) Publication and dissemination. This procedure is quite similar to the data mining procedure for knowledge discoveries in databases (KDD). From each of these steps, we will discuss the challenges and opportunities for statisticians. Real data examples from a large nationwide EHR database in the USA will be used to illustrate the principles and concepts of EHR data processing and analysis.
