Archive Page 2

Speech Recognition Goes South

South African Sunset The borders of the professional speech recognition community are expanding further South with a new member as of today:

Drs Conidaris and Partners, a private radiology group located at the Glynnwood Hospital premises in Benoni, South Africa, have completed the rollout of a Crescendo/SpeechMagic speech recognition system. After evaluating different technologies, the partners chose SpeechMagic for its wealth of built-in Radiology vocabulary and Crescendo’s unique voice streaming technology, which allows for immediate speech processing; a key feature for mission-critical environments” explains Kevin McEvoy, Managing Director, Datafer.

With the Crescendo/SpeechMagic technology, the practice was able to deliver on its initial objectives: speed up report production and reduce transcription costs. With the secretaries’ newfound ability to edit medical reports as opposed to typing them in full, fewer resources are required to process the same volume of reports. The first medical report dictated achieved over 75% accuracy and this rate is continually improving as the system learns.

“Skilled medical typists are extremely hard to find in the region, and a growing number of South African healthcare facilities welcome speech recognition technology as a reliable, cost-efficient way to address this issue. The technology has clearly matured significantly over the past few years and is delivering the expected results,” explain the radiologists at the practice.

Digital mobile recorders (Philips 9600) are used by physicians to dictate either directly from the practice or on the move. Every time the device is docked and a network connection is established, DigiService-IP automatically and securely streams completed voice files to the central server in real-time. The Secretary then uses DigiPlayer-IP, the Microsoft Word based playback and transcription application from Crescendo, to correct the document.

“South African hospitals and clinics are increasingly aware of the importance of digital technology to modernize both their practice and care delivery, and they are very selective in their purchasing process, with good reason” explains Costa Mandilaras, President, Crescendo Systems Corp. “This is why we chose a distributor, Datafer, with outstanding support services to properly deliver the Crescendo 18-year field expertise to South African customers. I believe that Drs Conidaris and Partners is the first of many more South African healthcare installations to come,” concludes Mandilaras.

Integration, Integration, Integration

Integration In a freshly inked article from Health Imaging & IT, healthcare IT executives and vendors unveil their respective visions and roadmaps for speech recognition. Integration clearly is the main course on the menu. While this is too bad for those vendors who think HL7 is the name of a 1990’s boy band, this article further confirms hospitals’ appetite for structured documentation with a direct impact on patient care.

  • Dr. Stephen Rosenthal, M.D. from the Jewish General Hospital in Montreal, QC, insists on the importance of interfaces between speech recognition and third-party systems in order to deliver the foundation for evidence-based medicine through searchable, standardized clinical data: “if speech systems aren’t relatively uniform, people will find systems on their own and use them. Then you have a hodgepodge of systems that don’t talk to each other and standardization is lost. We are much better investing in something uniform.”
  • According to Terence Matalon, MD, from the Albert Einstein Medical Center in Philadelphia, PA, speech recognition & PACS integration is a must have for Radiologists since it eliminates the need to re-enter patient information or “have two applications open to attain the same goal”. Matalon even pushes the point further by making integration expertise a competitive differentiator between vendors: “there are dozens of products that can reliably show you the current exam, prior exam and reports. The differentiating factor is how well they integrate with third parties and how well they reduce amount of work involved in interpreting reports and generating reports.”
  • On the vendor side, Klaus Stanglmayr from Philips Speech Recognition Systems explains how “interoperability and the ability to exchange data between systems and countries is becoming more and more critical in Europe. Standardized terminology would prevent the need to have data translated from one language to another.”
  • Finally, Chris Spring from MedQuist insists on vendors’ primary mission to “make it easier for the physician to accept the technology.”

Now what’s your vision? Share it on this blog!

Nuance to buy eScription

After Dictaphone in 2006, it is eScription’s turn to merge with Nuance. Here is an X-ray of the transaction that is about to take place in the speech-recognition-vendor supermarket:

  • Seller: eScription, a software vendor specializing in transcription, back-end speech recognition and workflow management applications for healthcare.
  • Buyer: Nuance Communications, giant provider of speech technology solutions – such as Dictaphone and Dragon Naturally Speaking – for consumers and businesses around the world.
  • Value: $400 million (compared to $357 million paid for Dictaphone in February 2006)
  • Payment:
    • $340 million in cash
    • $23 million in Nuance common stock
    • Assumption of vested employee options with a value of about $37 million
  • Time frame: deal is expected to close in Nuance’s fiscal third quarter of 2008.
  • Claimed objectives:
    • “Enhance Nuance’s ability to provide advanced transcription solutions”
    • “Evolve healthcare documentation and lower transcription costs by more than $1 billion over the next few years.”

The piece of news went public yesterday in the form of an official press release. The question is not so much whether this new deal will shake the competitive landscape, but more along the lines of a deeper, truly existential concern: “who’s next on Nuance’s shopping list?”

> Read press release

More Implementation Tips

Implementation Fairy The Best-Practice Fairy is back with a fascinating article by Jeff Kelly on successful speech recognition implementation. No doubt that Mr. Kelly knows what he is talking about: before joining Inland Imaging, a 60-member private radiology group in Spokane, WA, as director of clinical applications, he used to perform RIS market analysis and consulting work for MedQuist on voice recognition implementation. As Kelly puts it in a 2007 AuntMinnie article, one question – “What’s in it for me?” – is the key to a speech recognition project’s success. His article sheds the most promising light on the implementation brain-teaser. Here are a few soothing extracts:

Strong support and leadership

Consider pulling in this diverse group of representatives into a VR task force that can meet at defined intervals to address issues and help break down barriers to success. Then use this task force to educate its members on voice recognition — keeping in mind that this is usually new technology for 90% of those involved. This task force can also function as the decision-making body behind the implementation.

Maximize benefit, minimize effort

A typical radiologist statement that must be addressed is, “I am not a transcriptionist.” You can respond to this statement on three levels. First, stress the improvement in patient care when the radiologists are able to review and edit the report at the same time as reviewing the films. No longer do they need to recall whether it was a left or a right shoulder MRI. The accuracy of the report immediately increases.

Second, by editing at the time of the report, they eliminate the time-consuming process of logging into the RIS/HIS at a later time and reviewing the report. Third, the ability to send to transcription still exists if they so desire.

Provide sufficient internal support

At Inland Imaging, an in-house trainer was designated to be with each radiologist for the first three days when they began using the technology. This level of support tapered to half of every day for the next three days, then reached a point in which only a phone call was necessary to check in on each radiologist. Keep in mind that each radiologist will be unique — some needing more support and some needing less.

Set realistic expectations

As stated before, the radiologists are going from a traditional bicycle they’ve ridden their entire life to a shiny new two-seater that they are going to share with a friend. This is no easy task. It’s important to be frank and honest with staff and radiologists about the implementation process. There will be application bugs. There will be times when the application or workstation stops responding. There will be days when they love the system, and days when they feel like throwing the whole thing out the window. Set these expectations up front, then address them as quickly as possible when they arise.

Making change last

Finally, maintain the health of the system. Continue to refresh hardware as necessary to optimize both client- and server-side performance. Maintain error logs and database optimization jobs. Continue to accept version upgrades. Don’t allow neglect of system maintenance responsibilities to have a damaging impact upon the workflow of its users.

> Read full article (registration required – free)

> More threads like this

Front-end SpeechMagic Installations

What is a Speech Recognition Context ? Someone asked me to provide a few examples of healthcare facilities having deployed SpeechMagic in the front-end (process whereby the recognized text appears on screen as the physician dictates). It is my pleasure to oblige:

For more information on front-end/back-end speech recognition workflows, see this thread.

More Comments on the SpeechMagic/Dragon Comparison

Risking a SpeechMagic-Dragon Comparison? More comments came up over the weekend from Eric and David, which I would like to address here this morning.

Dear Eric, Dear David,

Eric is not the only one confused here. Actually, the bluriness that still prevails between consumer and professional speech recognition technology is what started this blog in the first place.

First, it is important to place my original thread in its context. I wrote this thread after I attended a congress on ER medicine where one doctor was explaining how he was using the off-the-shelf Dragon engine as an enterprise solution; an initiative that only reveals the overall market turmoil. To address users’ confusion, the best way is probably to analyze the reasons behind it. I believe the products’ respective sales models account for most of the blurriness:

  • Dragon is sold both directly (you can buy it from your local Electronics store) and through integration partners. What this doctor did was use the out-of-the box software thinking he was using an enterprise solution. And who could blame him? I would be lost myself if I were in his shoes.
  • SpeechMagic is not sold directly, but only through integration partners (workflow/dictation vendors). It is Philips policy to rely on their integration partners to provide the workflow management, interfacing and security aspects, which they consider as being as important as the speech recognition engine itself. The role of SpeechMagic in the overall EMR agenda will thereby depend on the way the partner interfaces the whole speech/system with the rest of the hospital’s IT infrastructure.

This whole dichotomy in the sales approach is not without its historic explanations. As Eric rightly points out, both products come from different worlds, addressing different markets in the first place:

  • Dragon comes from the consumer world. It was later “extended” to the professional arena through the addition of medical dictionaries and, later on, integration partners. It can therefore be installed on a single user’s PC or in a network configuration. This “consumer” background might also explain why the recognition accuracy is a central point in Dragon’s marketing speech.
  • SpeechMagic comes from the professional end of the spectrum and has always refused to reach out to the consumer market. It is designed for groups of users as part of a department or multi-facility approach, for which the recognition accuracy is just as important as other feature such as shared correction, acoustic adaptation and failover mechanisms. This is why David is right when he points out that SpeechMagic is not en enterprise solution; simply one that’s, in my opinion, more geared towards professional use. I will therefore rephrase that in my original post. SpeechMagic, just like Dragon, becomes an enterprise solution once integrated, depending on the workflow management features offered by its integration partner(s).

Regarding initial training: I am not sure which version of Dragon this doctor was using. I am only reporting his experience of using Dragon, which involved, in his own words, significant training time. Then again I am not questioning Dragon’s marketing speech here (who would I be to do so?), but only relaying a user specific testimonial.

Finally, David is rightly mentioning Enterprise Express (powered by Dragon) as an enterprise solution, which should be added to the list I provided on Friday.

May I conclude by inviting actual end users of any of the above systems to share their experience on this blog? I look forward to publishing your stories.

SpeechMagic / Dragon Comparison – Response to Reader Comment

Risking a SpeechMagic-Dragon Comparison? I would like to reply to the following comment from Eric Jacques: “Wouldn’t it make more sense to compare SpeechMagic to PowerScribe?” in response to the following thread: “Risking a SpeechMagic-Dragon Comparison?

Dear Eric,

Comparing SpeechMagic and PowerScribe would be like comparing an engine to a car. It is indeed important to differentiate:

  • The speech recognition engine technologies
  • The enterprise solutions that integrate the above technologies and are offered to healthcare facilities as part of a comprehensive dictation/workflow management package.

In today’s marketplace, vendors of dictation/workflow solutions are typically powered by one of the two major speech recognition engines: Dragon or SpeechMagic. Hence the importance to compare these two in the first place.

What makes it slightly more confusing in the case of PowerScribe is that:

  • PowerScribe is a Dictaphone product
  • PowerScribe is powered by Dragon
  • Dragon is a Scansoft product
  • Scansoft bought Nuance in 2005 but chose to keep on doing business under the name Nuance
  • Nuance acquired Dictaphone in 2006.

Still following?
Wait, is that you?

So if PowerScribe was to be compared to any system, it would be to a range of enterprise solutions such as:

  • Crescendo Speech Processing (powered by SpeechMagic)
  • Dolbey Fusion Speech (powered by SpeechMagic)
  • MedQuist SpeechQ (powered by SpeechMagic)
  • Dictaphone Enterprise Express (powered by Dragon)
  • SoftMed Speech Recognition (now powered by SpeechMagic since 3M merger)

Blog Stats

  • 95,622 hits