More Implementation Tips

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

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:

• Alegent Health, Omaha, Nebraska, USA
• Staten Island University Hospital, Staten Island, USA
• Jewish General Hospital, Montreal, Canada
• Aberdeen Royal Infirmary (ARI), Aberdeen, UK
• Ulleval University Hospital, Oslo, Norway
• Bornholm Hospital, Bornholm, Denmark
• Helsinki University Central Hospital, Helsinki, Finland

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

More Comments on the 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

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?

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)

The Nordic Example

With an industrial history firmly rooted in technology, the Nordics have always been early hi-tech adopters, clearly ahead of new market trends. While, in the early 2000’s, the rest of Europe was still getting used to the very concept of online transactions, these guys were already buying books by the dozen from Amazon.com over broadband connections. The fact that Norvegian healthcare is about to roll-out the world’s largest speech recognition installation therefore comes as no surprise.

As announced yesterday, over 1,000 physicians from the Ulleval University Hospital in Oslo – Norway’s largest clinical center – will be using SpeechMagic to generate reports across all medical specialties as of 2009. This is expected to be the world’s largest deployment of front-end speech recognition at one single hospital site. > More…

On the other side of the northern border, their Finnish neighbours also decided to step aboard the speech recognition ship with zero drowning reported so far. Instead, a rather impressive use case from the Palokka healthcare joint authority, who has been using a speech recognition system powered by SpeechMagic since December 2003. The system allowed the authority to “speed up patient care and improve data security at the same time. Patient data is always in the right place at the right time, which avoids unnecessary processing and reduces the need for doctors to consult each other.” > More

Medical Times Middle East features Speech Recognition

Medical Times Middle East recently dedicated an article to healthcare speech recognition based on interviews conducted at ArabHealth. Editor Vernon Baxter starts off the article by questioning Bill Gates’ 1997 prediction (“in this 10-year time frame…we will have perfected speech recognition and speech output”) in the light of present achievements.

“Gates may have been a little optimistic with his prediction, but voice-recognition is finally making inroads into healthcare (…) With the increasing presence of electronic medical records in clinics, the potential benefits of a voice-activated interface have never been greater.

Baxter goes on to comment the state-of-the-union between vendors and client healthcare organizations, quoting top vendor executives along the way, including:

– Koen Schoof, senior product manager, dictation and healthcare, EMEA, Nuance Communication.

– Costa Mandilaras, president, Crescendo Systems Corporation.

– James McPherson, project and client manager, Voice Technologies.

> Read article

MedQuist settles $7.5M class-action suit

I had promised an update on the MedQuist Saga outcome. Well, here it is; Season one’s grand finale. On March 10, MedQuist executed a $7,537,001.83 million settlement with “the plaintiffs and certain other putative class members represented by plaintiffs’ counsel in the South Broward customer class action.”

This settlement closes the putative class action that was filed on September 9, 2004 against the company. Plaintiffs alleged that the company overcharged certain non-federal governmental hospitals and medical centers for transcription services.

The settling parties will release the company and all individual defendants from any and all claims and dismiss the action in its entirety with prejudice.

The settlement is subject to formal documentation by the parties. Because the parties are not settling on a class-wide basis, no class will be certified, and thus there is no requirement to give notice. Neither the company, nor any of the individual defendants, has admitted or will admit to liability or any wrongdoing in connection with the proposed settlement.

> Read full press release

> Watch previous episodes

From Recognized Text To Clinically-Actionable Data

In a recent article from Health Imaging & IT, the respective Chief Medical Officers of Philips Speech Recognition Systems and Health Language shed light on the future of speech recognition technology for healthcare. Beyong speech-to-text conversion, SR is clearly turning into a full enterprise solution with a direct impact on both clinical decision-making and the actual cost of healthcare.

Nick van Terheyden, MD, CMO, Philips Speech Recognition Systems:

Speech recognition can reduce costs by 30 to 40 percent, and early users will have a very high competitive advantage.

Providing clinically actionable data is the key to solving fundamental challenges with EMRs such as: capturing data at the source to input into the EMR, supporting clinical decision-making with clinically actionable data, and providing tools that enable the capability to catch errors before they’re committed.

Speech recognition and natural language understanding bridges the gap between clinicians and technology

Brian Levy, MD, CMO of Health Language:

The language engine works simultaneously with the speech engine allowing for real-time conversion of text to standards. In addition, an EMR may be set up to allow smaller sections of dictations for various components of the record such as history, problem lists, medications, and so on. The EMR or other application may then permit the clinician to select more specific or additional codes to further standardize the information.

The current interaction with the patient usually occurs separately from the ability to look up referential material pertinent to the patient. But the introduction of speech and conversion to standards within an electronic medical record enables real-time information.

> Read full article

Movers & Shakers Interview

Marcel Wassink, Managing Director, Philips Speech Recognition Systems, speaks out in a recent interview conducted by HealthTechWire’s Armin Scheuer. Wassink shares his vision of market achievements and challenges, technology trends and the role to be played by speech recognition in the overall EMR agenda. Here is a sneak peek:

Challenges

The challenges in our field are indeed immense. We are expecting technology to cope with two highly complex issues: first, it has to capture and understand unstructured spoken information. Secondly, it has to turn this information into structured text, which takes into account that this is going to be used for sensitive healthcare purposes and life-affecting decisions. This requires in-depth expertise, plus detailed customer and clinical insight in order to achieve the accuracy, convenience and efficiency levels required in the healthcare industry. This focus has lead to the current massive adoption of speech recognition throughout healthcare sectors all over the world.

Speech Recognition and the EMR

Once radiology is up to speed, the entire hospital starts realizing the change which usually generates direct user demand for our technologies and services. Another trend that benefits our business is the introduction of electronic health record systems. They are seen as a key component to raise patient safety and reduce medical errors. However, physicians’ resistance is still high because of inflexible and inconvenient data capturing. Enabling verbal interaction between physicians and EHR is expected to eliminate adoption barriers, which is why we are especially active in EHR-friendly markets, such as the US, Scandinavia or Germany.

Beyond Speech Recognition: Standardizing Medical Language

Currently, we are researching solutions that integrate third-party applications, such as medical databases, diagnostic reference systems or coding applications – all of which aim to make healthcare documentation more accurate, convenient and efficient. We are looking at systems that increase patient safety during the process of capturing information in EHR systems, for example, by issuing a warning if physicians prescribe medication to a pregnant patient that is forbidden during pregnancy.

We are also working on standardizing language to support the interoperability of information systems. All healthcare applications must have a common, standardized language that allows them to share information among each other, thus giving access to critical information at the point-of-care: because knowledge is safety – in healthcare even more so than in any other field.

> Read full interview

HIMSS08 Wrap-up

Looks like speech recognition has left Star Trek to enter the mainstream. Hot like the southern breeze itself this year in Orlando, SR attracted crowds like never before. While physician skepticism seems to have vanished like a David Copperfield act, an increasing number of healthcare facilities came by the Crescendo and Philips booths to discuss technology advancements and upcoming implementation projects. These projects are bigger than ever, with a number of large healthcare groups looking to equip hundreds of physicians from multiple specialties with back-end SR, front-end SR, or both, by the end of the year. In this regard, attendee interest shifted from “does the technology work?” towards “how are other hospitals and clinics actually implementing it?”

Crescendo booth Philips booth

No wonder crowds gathered in front of the Philips booth on Wednesday to listen to Dr. Stephen Rosenthal’s presentation on wireless speech recognition in the ER. For those who couldn’t make it, here is a little video best of (download may take a while):

This wireless speech recognition project provides an exciting preview of tomorrow’s connected hospital, in which speech recognition plays more than one role. Beyond the productivity improvements for physicians, SR also delivers a reliable foundation for the electronic chart and evidence-based medicine by creating reliable, clinically-actionable content. HealthImaging & IT will be covering these topics in their April issue, which will feature an article on the future trends in speech recognition. Check the blog for a sneak peek!

In the meantime, there are more healthcare IT shows on the North American agenda. We look forward to seeing you there!