NSF grant compiles Big Data for healthier living

A UT Arlington computer scientist is leading a new, National Science Foundation project to mine electronic medical records data to help physicians personalize patient treatment, predict health care needs and identify risks that can lead to readmission.

Heng Huang, an associate professor of the Computer Science & Engineering Department, is the leading principal investigator on an $461,098 grant titled "Robust Large-Scale Electronic Medical Record Data Mining Framework to Conduct Risk Stratification for Personalized Intervention." The work is part of a $892,587 collaborative research project with UT Southwestern Medical Center and Southern Methodist University.

"If collecting and deciphering this data can give doctors better information so they can give patients better health care, it will make a big difference," Huang said. "We especially want to predict possible readmission dates for heart failure patients because timing is extremely important to them. It can be the difference between life and death."

Huang also said the work also could help health care professionals find the balance between patient hospital stays and insurance company's need to control hospital costs.

Last year, the Obama Administration announced the National Big Data Research and Development Initiative to address challenges and opportunities associated with "Big Data." These are such massively large and complex data sets that they can't be processed by traditional computer methods. Special algorithms are needed. The Big Data Initiative initially featured more than $200 million in new commitments from six federal departments and agencies. College of Engineering Dean Khosrow Behbehani said Huang's work is a leading project in the emerging field of health informatics research.

"Big data is becoming more and more a part of our lives. This research would help us and our physicians make important health-care decisions," Behbehani said. "Dr. Huang's work makes use of the increasingly large amounts of data being generated in the health care community and will use it to develop systems that help us live healthier, longer lives."

Behbehani said the research could lead to solving increasingly difficult big data problems in the areas of climate prediction, safer manufacturing and cybersecurity."

In the ongoing work, Huang teamed with the University of Indiana, Purdue University and the University of Pennsylvania on big data mining concerning the effects of drugs on patients by using the electronic medical records.