Software developed by computer scientists at the University of Illinois could help to ensure that sensitive data in patient medical records is not shared against a patient's wishes. The tool, according to MIT Technology Review, uses a machine-learning analysis of other medical records to help determine information--such as prior drug abuse--that a patient might want to keep private, and may eventually be able to extract such information automatically.
"Electronic health records at the moment have no facility--none--to break the record into parts," John Halamka, CIO at Boston-based Beth Israel Deaconess, told Technology Review. "You either get the record or you don't."
The tool was created as part of a project supported by the Office of the National Coordinator for Health IT aimed at reducing security and privacy barriers to the use of health IT. Article