Communications of the ACM
Health Care of the Future
MIT's William Long
Photo courtesy of Jason Dorfman
A new system developed by researchers at the Massachusetts Institute of Technology's (MIT's) Computer Science and Artificial Intelligence Laboratory (CSAIL) can provide clues about the condition of a patient by scanning unstructured medical records.
The technology makes use of natural language processing techniques and is comprised of several programs that parse through pages of electronic nurses reports and intensive care unit (ICU) discharge summaries searching for certain keywords and phrases. MIT's William Long used information from the Uniform Medical Language System, a compilation of more than 150 medical dictionaries, to program the system to identify a comprehensive list of terms and key concepts. The technology has been used for clinical research and diagnostic purposes so far.
MIT professor Peter Szolovits is looking for new ways to use artificial intelligence in the diagnostic process. One CSAIL researcher has used data collected on ICU admissions to a Boston hospital to create predictive models that estimate how patients are likely to fare in the future each time there is a significant change in their health condition.
From Computing Community Consortium
View Full Article
Abstracts Copyright © 2011 Information Inc. 
, Bethesda, Maryland, USA
No entries found