A new technique developed by researchers at Vanderbilt University may allow data from health records to be used for medical studies while protecting patients' privacy, according to findings published yesterday in the Proceedings of the National Academy of Sciences.
In the study, researchers illustrated the privacy problem posed by electronic medical records by identifying 96 percent of more than 2,600 patients using diagnoses codes. As a solution, the team designed an algorithm that searches records for information pertaining to a specific research question while simultaneously disguising medical details irrelevant to the query.
Scientific American's Observations reports:
[Researchers] tested the algorithm's data protection performance against simulated malicious computer hacker attacks using actual information from more than 2,600 patients, assuming a potential hacker knew a patient's identity, some or all of a patient's ICD codes, and whether the patient record was included in released data. The technique foiled attempts to uncover a patient's private information...and maintained the data integrity necessary to retain useful information for validating genome-wide studies.
Previously: Mining electronic medical records for research insights
Photo by alimander