IUPUI Informatics Professors Research Medical Record Text-Mining
Malika Mahoui and Josette Jones, both assistant professors with the IU School of Informatics at IUPUI, know that medical discoveries and health care improvements lay buried in the mountains of digital data generated daily by hospitals, clinics, doctors and nurses. Thanks to a funding grant from the National Institutes of Health, Mahoui and Jones are helping Dr. Patrick Jamieson, Logical Semantics, Inc., build computer tools to mine those data.
"These scientific innovations will revolutionize the ability of health care researchers to analyze vast repositories of clinical information currently locked up in electronic medical records, and correlate this data with new biomedical discoveries in proteonomics and genomics," explained Jamieson, the project's Principal Investigator.
The research team has already developed new statistical and machine learning methods to analyze free-text radiology reports using a text-mining tool called DataMiner. Now in Phase II, Co-Investigators Mahoui and Jones aim to improve the extraction methods by expanding their semantic knowledge base to classify at least two million new unique sentences from multiple medial institutions.
"Analyzing and processing free-text medical reports for data mining and clinical data interchange is one of the most challenging problems in medical informatics, yet it is crucial for continued research advances and improvements in clinical care," said Jamieson. "Natural language processing is an important enabling technology, but has been held back because it is difficult to understand human language, since it requires extensive domain knowledge."
Eventually, the researchers will build a commercial version of the DataMiner software, and test its functionality using researchers at the Regenstrief Institute.
"It is hoped that a useful coding standard will emerge for health care providers using DataMiner, and a second application that we are helping to develop - the SNOMED CT (Systematized Nomenclature of Medicine--Clinical Terms) coding service called SnomedCoder," said Mahoui.
The ability to codify text rapidly will extend the potential for clinical decision support beyond its narrow base of numeric and structured medical data, and enable SNOMED CT to become a useful coding standard.
"Ultimately, our goal is to offer coding and data mining services to healthcare payers, pharmaceuticals, and academic researchers," said Jones.
For additional information contact:
Malika Mahoui <http://informatics.iupui.edu/people/mmahoui>
Josette Jones <http://informatics.iupui.edu/people/jofjones>
|
