National Science Foundation awards $900,000 in EHR research grants

Plans include new computational tools to automate EHR processing
Tools

The National Science Foundation has awarded three collaborative grants amounting to $892,587 to The University of Texas at Arlington, Southern Methodist University and the University of Texas Southwest Medical Center at Dallas to develop data mining tools for electronic health records.

The study, entitled "Robust Large-Scale Electronic Medical Record Mining Framework to Conduct Risk Stratification for Personalized Intervention" plans to develop, among other things, new computational tools to automate EHR processing and annotate unstructured free-text EHRs, predict the readmission risk of heart failure patients and support personalized intervention, and create novel methods to identify long-term patterns. The study is expected to create new algorithms to enable broader data mining, and impact other public health research and training.

"The increasingly large amounts of Electronic Medical Record (EMR) data offer unprecedented opportunities for EMR data mining to enhance health care experiences for personalized intervention, improve different diseases risk stratifications, and facilitate understanding about disease and appropriate treatment," the Foundation noted.

The National Science Foundation is an independent federal agency whose mission is to promote the progress of science and "advance national health, prosperity and welfare." The collaborative study is expected to expire in 2017.

EHRs are increasingly being recognized as a potential bonanza for conducting large scale research, improving outcomes by identifying high-risk patients and advancing public health and pinpointing epidemilogical cases, for example. However, first capabilities need to be created to handle such big data mining projects and to reduce data bias in research to improve accuracy of results.  

To learn more:
- read about the grants
- learn about the Foundation

Related Articles:
EHRs can streamline case identification for research studies
EHRs can ID phenotypes for genetic research
EHRs can ID 'missing' high risk patients
Biases in EHR data can be reduced to improve research