Monthly Archives: April 2006

Anandtech: Speech Recognition

One of the holy grails of computer science and medicine has been accurate speech recognition. This seems to be a technology that is always 5 years away. Anandtech has a review of Dragon Naturally Speaking and the built-in speech recognition for Microsoft Office 2003. The short version of Anandtech’s review: Dragon is better than Microsoft but both have accuracy issues. There is also the Free and Open Source Sphinx speech recognition engine not reviewed in the Anandtech article.

The accuracy issues pointed out in the Anandtech article appear to be the same issues that have plagued this technology for years. 95-99% accuracy appears good until you realize that this means 5-1 mistakes per 100 words.

Continue reading →

Ace Reporter Shirley Joins Linux Medical News Staff

Cindy was Linux Medical News ace reporter for four years before she passed on. Despite some quirks, such as thinking everyone was a Chihuahua, she had a true talent for getting the inside track for important meetings and being around powerful people in the Free and Open Source Software in medicine scene. She has received much fan-mail over the years and a recent, temporary, omission of the link to her page was noted by many. Cindy has been missed since her departure to that great reporters heaven in the sky. However, this past week, while perusing an O’Reilly PHP and MySQL book, the staff of Linux Medical News received a cryptic message posted to the site…

Continue reading →

RSI on Slashdot and Exercise Break

Slashdot has a story on Repetitive Strain Injuries (RSI) from computer keyboard use such as carpal tunnel syndrome and tendonitis. This story brings back old hacker memories! Read on for a short trip down memory lane.

Exercise Break for Windows is a timer based exercise program to reduce stress and Repetitive Strain Injuries (RSI) that’s been around for a long time. You can get it cheaper here. It is a cool program, that won’t tax your system much at all.

Continue reading →

ClearHealth at Desktop Linux Summit

Uversa will highlight features of the RC3 release as well as training and news about the ClearHealth Office hosted solution, reseller program and more in our booth (#25) at this weeks Desktop Linux Summit (DLS) April 24 & 25 2006, at the Manchester Grand Hyatt Downtown San Diego. RSVP to clearhealth@uversainc.com to coordinate a free 1 hour training session and receive a free PDF copy of our the training guide. We look forward to seeing you there. For full information see our frontpage.

IW: Commons-based peer production and the medical information monopoly

Infoworld’s John Udell has a thoughtful piece about medical information: ‘…Medicine is, among other things, a kind of information monopoly, as are other professional fields including IT. It’s inevitable that peer production will challenge these information monopolies, and medicine is a particulary interesting test case…’ Also, there is an announcement of HealthNewsReview website, which will gauge the quality of health information news reports.

Thoughts on Linux Medical News New Look?

Dear reader, do you like the new look of LMN or hate it? What do you think should change or stay the same? Linux Medical News is now 6 years old and has had only minor changes in its look since its inception. New looks are in order for the site with the goals being less clutter and more appeal. The curved title bars are gone, the Google site search box moved and made relevant to Linux Medical News, the banner ads colors are now in synch with LMN, the icon subject list at the top is gone, icons have been freshened and the black background at the top is now white. The banner logo may be freshened up soon. I’m still trying to figure out what would be a good icon for the ubiquitous ‘Interesting Developments’ subject heading.

NF: Two FOSS Patient Record De-Identifiers

Two patient record data de-identifiers or ‘scrubbers’ are highlighted in this Newsforge report: ‘…HMS Scrubber version 1.0, was recently able to remove more than 98 percent of identifiers — such as name, address, and Social Security number — from 1,254 pathology reports processed from three hospitals. Developed by a team from the Beth Israel Deaconess Medical Center in Boston…HMS Scrubber is not the only open source scrubber program that holds promise for medical researchers. Concept-Match …uses an external list of about 80,000 approved word “doublets” that contain no identifying terms. Berman says his current list of doublets was derived from two open source medical vocabularies, and the algorithm is relatively simple.

“The method can be scripted in under 20 Perl command lines,” Berman says in his comment. “This program is free software. You can redistribute it and/or modify it under the terms of the GNU General Public License.”…’