Archive for December, 2007

Out of Blog Alert…

Best wishes everyone from snowed-under Quebec!
I will see you in January 2008 for more fresh snow speech recognition news…

Merry Xmas!

Speech Recognition More Accurate Than Transcription…

Bilingual Speech Recognition Who would have thought so just 3 or 4 years ago? According to a scientific presentation at RSNA 2007, the annual meeting of the Radiological Society of North America, transcribed reports show higher error rates than the ones returned from speech recognition applications. The study, conducted at the Radiology Consultants of Iowa, a non-academic radiology group in Cedar Rapids, Iowa, compiled error rates for 498 reports created with a system powered by SpeechMagic and compared those with error rates for the same reports transcribed in a traditional manner.

The traditionally transcribed reports included at least one error in 13 percent of the total, while the speech recognition reports demonstrated one error in only 9 percent of the total studies.

The rate for significant errors, requiring the preparation of an addendum, was 0.6 percent for speech recognition and 2 percent for traditional transcription,” reports Floyd, RCI partner.

He shared that the accuracy rate for speech recognition reported by RCI was confirmed by an independent analysis conducted at one of the two acute care hospitals that the group services. The facility’s evaluation of 514 reports conducted in September produced an overall transcription error rate of 9.7 percent for both automated and traditional report generation, and that an addendum was required for 0.6 percent of the reports.

The report cohort consisted of 20 to 25 studies involving CR, MR, and general radiographic procedures from each of the 24 radiologists in the practice.

> Read full article

Independent Research Firm Recognizes SpeechMagic Leadership

Independent Research Firm Recognizes SpeechMagic Leadership Frost & Sullivan announced yesterday that Philips Speech Recognition Systems (Philips SRS) won the 2007 Global Excellence Award in speech recognition technology. The award recognizes the Austrian firm for its “demonstrated leadership in the field of speech recognition technologies for the healthcare market.” Research Analyst Nikolopoulos goes even further by saying SpeechMagic is “becoming the ‘de-facto’ standard document creation platform in healthcare throughout the world.”

Decades of experience, a portfolio of 25 recognition languages and more than 150 specialised vocabularies, coupled with over 8,000 installations of its flagship product – SpeechMagic – across 50 countries, bear testimony to Philips SRS’s position as a global market leader.

“SpeechMagic is a client/server-based, professional speech recognition package, which can be fully integrated with other healthcare IT solutions such as RIS, HIS/EPR and PAS,” notes Frost & Sullivan Research Analyst Konstantinos Nikolopoulos. “It is suitable for both small and large systems, and by supporting distributed networks it ensures that dictation, recognition and correction can be done independently of the location, across a local or wide area network or the Internet.”

“Intelligent speech interpretation technology assures that the system not only recognises words but also understands their meaning,” adds Nikolopoulos. “SpeechMagic formats text and recognises headers, hesitations and punctuations, thus reducing human involvement in the generation of medical documents to a minimum.”

The latest version of SpeechMagic pays special focus on the security needs of large installations. SpeechMagic is protected against instabilities in the overall IT system and loss of network connections. Security is further increased by Speaker Detection – a feature which protects individual speakers’ settings by detecting discrepancies between author and voice profile.

> View press release

Radiology: white noise can increase speech recognition accuracy

white noise can increase speech recognition accuracy I came across the following article from Health Imaging & IT magazine this morning. According to a recent study conducted at the University of Maryland Medical Center, the introduction of white noise as part of the acoustic background has a positive impact on speech recognition accuracy…

Although radiology practices pay significant attention to the environment for diagnostic image interpretation, few give as much consideration to the acoustic workspace in which the physicians dictate their clinical report.

According to Joseph Zwemmer, MD, who presented the results of the research at the 93rd annual meeting of the Radiological Society of North America (RSNA), speech recognition technology is now used by almost half of the academic and approximately 25 percent of private practices in diagnostic radiology.

Zwemmer reported that dictated reports were compared to the original report to determine the number of errors present. The researchers found that the mean baseline transcription error rate (TER) was 11.6 percent (range 6.5 percent26.1 percent). However, the TER at the four white noise levels was 10.3 percent, 12.3 percent, 13 percent and 13.5 percent, respectively.

> Read full article

Cause of Death: Sloppy Handwriting

Sloppy Handwriting Here is a Time Magazine article from earlier this year where author Jeremy Caplan digs further into the preventable medication mistakes statistics. Caution, coarse figures ahead…

Doctors’ sloppy handwriting kills more than 7,000 people annually. It’s a shocking statistic, and, according to a July 2006 report from the National Academies of Science’s Institute of Medicine (IOM), preventable medication mistakes also injure more than 1.5 million Americans annually. Many such errors result from unclear abbreviations and dosage indications and illegible writing on some of the 3.2 billion prescriptions written in the U.S. every year.

“Thousands of people are dying, and we’ve been talking about this problem for ages,” says Glen Tullman, CEO of Allscripts, a Chicago-based health care technology company, that initiated the project. “This is crazy. We have the technology today to prevent these errors, so why aren’t we doing it?”

Although some doctors have been prescribing electronically for years, many still use pen and paper. This is the first national effort to make a Web-based tool free for all doctors. Tullman says that even though 90% of the country’s approximately 550,000 doctors have access to the Internet, fewer than 10% of them have invested the time and money required to begin using electronic medical records or e-prescriptions.

SureScripts CEO Kevin Hutchinson says one key to reducing medication errors is to get the most prolific prescribers to transition to electronic processing. “Not a lot of people understand that 15% of physicians in the U.S. write 50% of the prescription volume,” Hutchinson says. “And 30% of them write 80%. So it’s not about getting 100% of physicians to e-prescribe. It’s about getting those key 30% who prescribe the most. Then you’ve automated the process.”

> Read full article


Blog Stats

  • 96,081 hits