Computer Scientist Shows How to Make Good Use of EHR Data

For years, the healthcare industry has been struggling to get data into an electronic format. Now, as more providers implement electronic health records, leaders are asking: What’s next?

Lian Duan, a New Jersey Institute of Technology computer scientist, has stepped up to the plate with some direction. In an article published in the March issue of the IEEE Journal of Biomedical and Health Informatics, Duan demonstrates how advanced data mining can turn the vast amount of patient information available from U.S. electronic health records into valuable clinical intelligence.

"Large collections of electronic patient records have long provided abundant, but under-explored information on the real-world use of medicines. But when used properly these records can provide longitudinal observational data which is perfect for data mining," Duan said. "Although such records are maintained for patient administration, they could provide a broad range of clinical information for data analysis. A growing interest has been drug safety."

Duan’s article, "Adverse Drug Effect Detection," spotlights a new and promising way of using a combination of commonly used existing algorithms to obtain more information about adverse drug reactions from the data contained in electronic health records. More specifically, the research found that by combining three algorithms, “one can get better, more diverse results.” The new pattern, which when compared against the most commonly used existing sole algorithm, showed an almost 25 percent improvement in outcomes.