Clinical Computing and Informatics News

Automated de-identification of free-text medical records
We have developed a pattern-matching de-identification system based on dictionary look-ups, regular expressions, and heuristics. Evaluation based on two different sets of nursing notes collected from a U.S. hospital suggests that, in terms of recall, the software out-performs a single human de-identifier (0.81) and performs at least as well as a consensus of two human de-identifiers (0.94). The system is currently tuned to de-identify PHI in nursing notes and discharge summaries but is sufficiently generalized and can be customized to handle text files of any format. Although the accuracy of the algorithm is high, it is probably insufficient to be used to publicly disseminate medical data. The open-source de-identification software and the gold standard re-identified corpus of medical records have therefore been made available to researchers via the PhysioNet website to encourage improvements in the algorithm.

Presence in Virtual Worlds Could Help Health Plans Achieve Real-World Behavior Change
Second Life is a virtual world of avatars, sims and Linden dollars, and CIGNA, Corp., Partners HealthCare System, Inc. and the Centers for Disease Control and Prevention (CDC) are among the first health organizations to establish beachheads on its shores. But it's not, they say, because Second Life and other social networking media (e.g., Web sites) are new and flashy. Rather, their ventures are a response to changes in the way consumers are communicating and accessing health information.

DNA databases blocked from the public
The National Institutes of Health quietly blocked public access to databases of patient DNA profiles after learning of a study that found the genetic information may not be as anonymous as previously believed. The study that sparked the move, published in today's edition of the journal Public Library of Science, revealed the ability of a new type of forensic DNA analysis to identify a person's DNA even if it were found in minute quantities and mixed with that of hundreds of other people.

Nationwide EHR implementation price tag estimated at $150 billion
Full implementation of networked e-health records in U.S. doctors’ offices and hospitals could cost around $150 billion over eight years. Miller’s projections call for hospitals to spend $35 billion to acquire and expand EHR systems and $55 billion in new operating costs over eight years. He said this level of spending would bring hospitals’ IT spending closer to that of other industries.