Ohio State's Department of Biomedical Informatics has received a $1.3 million grant from the National Library of Medicine to support development of technology that will piece together patients' medical history within EHRs to speed recruitment for clinical trials.
This "information fusion," as the university calls it, combines data stored in narrative text fields and multiple data sets, and binds various events together to create a medical portrait for individual patients, according to a university announcement.
The funding is part of $67 million awarded in five-year grants to 14 universities to further training in biomedical informatics.
"Electronic health records are composed of multiple data sources that are often redundant or inconsistent, stored in uncoordinated and unstructured clinical narratives and structured data. These characteristics make EHRs difficult to use for matching patients against the complex event and temporal criteria of clinical trials protocols," said Albert Lai, research assistant professor at the College of Medicine and principal investigator.
He said the "fused" information should not only reduce staff time in recruiting patients into clinical trials, but also make the whole process faster.
Researchers have been looking for ways to accelerate patient recruitment for trials, including signing people up online and through mobile devices. Ohio State University and the University of Cincinnati recently collaborated on a study of the effectiveness of EHR alerts in recruiting patients, finding them useful, but subject to alert fatigue.
Software vendor Oracle this summer released a set of cloud-based applications it calls its Health Sciences Network to help health systems and pharmaceutical companies pull de-identified patient data from various databases, including electronic health records.
Meanwhile, Archimedes' modeling algorithms take a different approach, creating a "virtual clinical trial" using multiple scenarios based on different kinds of patient populations, specified health conditions and various treatment regimens. It combines decision and predictive modeling to comparative effectiveness studies that would be expensive and take longer to conduct than traditional clinical trials.