Illinois Institute of Technology (IIT) associate professor of computer science Shlomo Argamon will help develop a software system to improve health care by automatic identification of research results relevant to individual patients in a project funded by the National Institutes of Health. Argamon will collaborate on the project with a team at Parity Computing (San Diego, CA) headed by Chris Rosin, as well as Jordan Hupert and Alan Schwartz of the University of Illinois at Chicago Medical School.
This project has the potential to improve healthcare outcomes and cost-effectiveness on a large scale. The current approach to using medical research to improve care requires continual labor-intensive efforts by physicians to identify and study new evidence relevant to their patients, efforts that are increasingly infeasible given the exponential growth of the medical research literature.
“Current tools to help physicians are incomplete and limited to applying simplified, pre-digested guidelines to pre-structured patient data,” says Argamon. “They can miss important complexities in the original research, as well as many significant patient details that are expressed in the original clinical record text.”
The new system will overcome these limitations by automatically identifying published research studies that contain the evidence most relevant to specific patient clinical records, including information originally recorded only in narrative text.
It will automate critical aspects of evidence-based medicine by generating structured representations of trial results and patient records, and then quantitatively comparing them to find matches that could help inform individual patient care decisions. The project integrates research from Argamon’s group on automatic summarization of medical research articles with Parity Computing’s new technology for summarizing clinical record narratives.