Speech Recognition

Here is a rather fascinating interview of Dr. Nick van Terheyden, Chief Medical Officer for Philips Speech Recognition Systems, on the challenges facing healthcare today and the role of speech recognition, EHR and thin-client technologies in the fail-safe delivery of high quality care. Far beyond the technical aspects, Dr. van Terheyden makes us take a realistic look at healthcare today and think about what tomorrow’s hospital should look like. Here’s a sneak peak:

Douglas Brown: What does an industrial grade system deliver to the software industry that on that off-the-shelf product doesn’t?

Nick van Terheyden: You want to optimize the workflow and throughput for an entire organization. An off-the-shelf product that you install on a single desktop isn’t scaled or designed to actually deliver that. It is designed for the individual user. As soon as you start to move across an organization and need to transfer your profiles, you start to run into trouble.

We’ve focused on the professional market right from the very beginning, constantly delivering on those changing market requirements, specifically in healthcare. The breakthrough of the Citrix of application delivery infrastructure has been one of these events that triggered advances for speech recognition technology. And the other one that’s driven a lot of change is the Electronic Health Record - EHR or EMR as it’s referred to, which is aimed at improving availability and accessibility of medical information. That’s really a key component of safer, more value-added care, which is suffering in the US setting. One of the numbers that’s bandaged around fairly frequently from the Institute of Medicine report from some years ago, is the 98,000 medical errors that occur killing patients in the US every year. If you equate that to the airline industry, that’s approximately one aircraft crashing with all people on board every day.

So anything that we can do to enhance the delivery of quality information to our clinicians is going to be a key factor in that. And enhancing the EHR with the seamless integration of speech recognition, speech being the most natural form of communications, brings some significant benefits. Specifically, we’re going to bring that information to be instantly available to all the members of the team. Medicine used to be an individual specialty, where one physician treated patients. Now it’s a team approach. (…) We’ve got multiple clinicians, and not just physicians, delivering care and the communication of that data to all of the team members as quickly as possible and as accurately as possible is a key factor in delivering high quality care. Much of the errors that occur actually occur in the hand off of that information.

…Users who have access to dictation devices - either handheld devices or even PCs - with thin-client technology are more mobile and therefore can be more efficient in the delivery of that care.

…One of the failings of speech recognition historically has been the desire to take what we do with the mouse and the keyboard and try to automate that using voice. And that’s really not the optimal way to voice enable an application.

> Listen to podcast

Fall 2007 is definitely harvest season for market intelligence in our sector of interest: healthcare IT. After the MRI’s and HealthImaging Surveys, now comes the HIMSS 18th Annual Leadership Survey results. The survey “reports the opinions of information technology (IT) executives from healthcare provider organizations across the U.S. regarding the use of IT in their organizations. The study was designed to collect information about IT priorities, technology adoption, application usage and other crucial factors in the use of IT to enhance healthcare.” Here are a few interesting findings…

IT priorities

Implementing technology to reduce medical errors and to promote patient safety continues to be a top priority (35%), both now and for the future. This is being driven by a focus on quality of care and patient satisfaction, which were identified most frequently as the healthcare business drivers having the most impact in the next two years.” Workflow redesign still scores 30%.

Technology adoption

Speech recognition is on the list of technologies that survey respondents intend to implement in the next two years, although Intranet and high-speech networks have become the number one priorities:

Security technologies

Electronic signature appears as one of the top technologies to answer respondents’ primary concern regarding the security of data at their organization:

IT budgets

Nearly threequarters of respondents reported that their IT operating budget will increase in the next year. Many respondents attributed this to an overall growth in the number of systems and technologies.

Vendor satisfaction

In general, respondents were satisfied with the overall IT products/services they receive from suppliers, application vendors and consulting firms—60 percent of respondents indicated that they were satisfied.

>> Read full Survey from the HIMSS web site

I thought I’d clarify this point since I am asked this question on a regular basis. The SpeechMagic speech recognition engine from Philips is not a standalone solution that can be purchased on its own; it is typically integrated by a number of selected software vendors as part of their respective portfolios of dictation and workflow systems, EMR or PACS. These vendors bring in the equation the dictation interface and workflow management components that are as critical as the speech recognition engine itself for a complete, powerful documentation platform.

Only a selection of software companies serving the medical industry were allowed to integrate the Philips speech recognition technology with their respective systems and applications to date. Depending on each vendor’s resources and expertise, some will offer more advanced features than others, although they all have to follow strict integration guidelines upon being accepted as a SpeechMagic partner. SpeechMagic partners typically exhibit at all major healthcare IT tradeshows (i.e.: HIMSS, AHIMA, RSNA, MGMA, eHealth, JFR, etc.) and can be identified through the following logo:

Freshly inked article from Australian IT magazine reads: “Voice recognition in medico lingo”. Editor Karen Dearne interviews Chief radiologist K.C. Fan from the Westmead Children’s Hospital in Sydney West.

The artcicle starts with a bit of history on professional speech recognition, quoting Dr. Fan’s experience:

…the technology has taken a while to achieve the accuracy they require. Fan says early versions were inaccurate and too slow. The processing time for computers to turn voice into text reduced the potential for productivity gains.

Tailored dictation products began to surface a couple of years ago, and the most successful voice recognition applications have been in structured environments, in which vocabulary and context can be built into transcription engines.

The author goes on to describe the actual project in place at the Radiology Department of the Children’s Hospital, with a very accurate insight from Dr. Fan on “how the limitations of general speech systems are actually strengths in specialised applications, such as radiology reporting:”

In day-to-day usage, short words such as to could also be two or too. The software has to guess what you mean and try to put the correct word into the context of your sentence. That’s not a major problem in radiology because specialist medical terms are long and complex. That’s an advantage, as it’s easier for the speech recognition system to pick them up.

A word such as interceception (inverted gut) comprises five syllables, for example, providing a clear, machine-readable pattern. Conversely, Fan says, most people unfamiliar with the term would misspell it. That sort of accuracy is a challenge to humans, but not to the system software.

When it comes to the difficulty of finding skilled medical transcriptionists, the situation in Australia seems very similar to that in the USA:

A good medical typist will get it right most of the time, but it’s hard to find skilled people.

On the dictation side, Dr. Fan stressed the importance of a dictation etiquette:

It is important for users to be consistent in their dictation. If you change the way you speak, you can teach the system bad things and the accuracy will drop. If people are consistent, it doesn’t matter whether they have an Indian, Chinese or Irish accent, the system will adapt.

You can read the full article, with further details on RIS integration and benefits, directly from the Australian IT web site.

More survey results! The Medical Records Institute just published the results of its ninth annual survey of Electronic Medical Records Trends and Usage, “an annual poll of IT usage among healthcare providers of various sizes and types.” This year, the survey was co-sponsored by Philips Speech Recognition Systems, with a total of 1011 respondents. The MRI to increase relevancy and diminish bias, responses from vendors and consultants are not included in the results, reducing the total database to 819. Here are a few interesting highlights:

Why EMRs are being implemented

The following are most cited as priorities for strategic decisions in IT.

• The need to improve clinical processes or workflow efficiency.
• The need to improve quality of care.

Speech recognition technology adoption

The following are most cited as very important factors driving installation of speech recognition (SR) technology.

• Improve productivity
• Reduce turnaround time
• Reduce transcription costs
• Facilitate real-time healthcare documentation
• Improve clinical workflow

The types of SR reported as most in use are

• Dictation system with SR that automatically uploads to EMR
• Direct dictation into EMR (seamless integration)
• Stand-alone SR (no integration with EMR)

The majority of those using speech recognition to generate reports report using only front-end SR with no medical editor or other person involved.

> More survey results

In the October issue of Health Imaging & IT, Lisa Fratt analyzes the top trends and priorities in healthcare IT for the year to come. Here is a sneak peek at the survey results:

Workflow as a top priority

Nearly 70% of respondents rated improving workflow as a “very important” priority, and large hospitals (500+beds) rate it the #1 priority. Most aim to tackle patient scheduling and registration and many plan to focus on physician and technicians’ productivity.

First time investment

68% of facilities that do not have clinical IT yet say they are currently evaluating speech recognition technology:

Replacements / upgrades

IT solutions that rank high in the 2008 purchase or replacement cycle include enterprise image management, voice recognition and enterprise data storage (to handle that extra image volume). Voice recognition ranks second with 33% of responses:

Ways to improve productivity

Number 3 on the list is physician productivity.

Nearly 40% of healthcare facilities claim DRA cuts encourage them to try to work more efficiently by investing in technology designed to increase productivity/efficiency.

> Read full survey

Live from the Philadelphia Convention Center, where AHIMA is being held this year, you will find me at the Crescendo booth (#855) from October 8 to 11. On the menu: speech recognition, speech recognition and more speech recognition. Dressings to your liking, as always: front-end, back-end, PACS interfaces, workflow management, electronic signature, and more. Also, not to be missed, our new interactive module for clinical notes, an industry first that concentrates voice commands, front-end SR, macros, drop-down menus, check boxes and templates into one single application. I look forward to seeing you there!

This year, the Philips Speech Recognition Systems Partner Event was held at the Hotel Concorde in Berlin, Germany; a jewel of modern architecture and design where over 150 attendees gathered to discuss the latest advancements and use cases in professional speech recognition.

Of all presentations, I would like to highlight two that are of particular interest to us here:

Dr. Stephen Rosenthal, Associate Director, ER Department and Director of Medical Informatics at the Montreal Jewish General Hospital explained how the combined use of wireless and speech recognition technologies in the Emergency Department accelerates and secures the delivery of medical reports while allowing physicians to save significant charting time. Thanks to a HL7 interface and a dedicated application for Window Mobile, physicians can access up-to-date patient information and dictate directly from their PDA. Completed dictations are immediately streamed to the speech recognition server through the wireless connection, resulting in final reports being available prior to the physician leaving at the end of his shift. > View presentation (500 kB)

Mary Radley, from the Children’s Hospital in Boston explained how the hospital reduced report turnaround time by implementing speech recognition following the Six Sigma Methodology. Since the implementation of the speech recognition system, the hospital reports a turnaround time of less than one day for 85% of the reports as well as a 33% increase in transcription productivity.

Also attending were Philips SRS marketing allies including Citrix, Map of Medicine and Health Language. This only confirms Philips’ commitment to engage on the interoperability path and provide healthcare professionals with structured, standardized clinical information that can be accessed through improved network infrastructure.

The professional speech recognition community is definitely here to stay, making noise and growing. In Berlin this year, Philips and partners clearly reinforced their commitment to the healthcare sector in the long term, and with a hospital-wide penetration of close to 100% in some Scandinavian countries, gave further proof of a clear market leadership.

> Read related article in Healthcare IT News

Hi! I’m the Best-Practice Fairy. My mission is to dig up articles that cover the implementation aspect of speech recognition technology within healthcare settings. Here is one.

In the October issue of Health Imaging & IT, Journalist Beth Walsh interviews a number of key North American healthcare executives about their experience deploying speech recognition technology. This article really caught my attention as I believe it offers what healthcare professionals really want: a way to learn from each other. Whether it is in a Radiology or ER setting, implementation tips converge: all respondents insist on the importance of a gradual rollout, as well as on a the importance of interfaces to make sure that the technology fits the way physicians work, and not the other way round. This is particularly key when it comes to using speech recognition in the ER, where mobility is the name of the game. Here are a few extracts:

Implement Voice for the Right Reasons

Implement voice for the right reasons, says Selle. “Our goal was not to make money off the system, but to provide a service to the facility and improve our marketability to the community and referring physicians.”

Emergency department notes must be relatively up-to-date, says Rosenthal. “In other areas, you can wait to see notes.” And since two-thirds of the hospital’s ED volume occurs outside of the standard 9-to-5 day shift, “voice recognition offers a good opportunity to do notes whenever we need them,” he says.

Project Set-up

Both Selle and Rosenthal say that the implementation of voice recognition warrants a thorough evaluation of workflow and an infrastructure geared to the technology. “Interfaces needed to be set up between facilities’ management systems to generate orders,” says Selle. That way, you’ll have the same patients on the voice worklist as are on the PACS or other systems clinicians are reading off of. He recommends setting up destinations for reports once they are dictated and physicians have signed off. “Set up network printers in the ED that will print reports directly to clinicians,” Selle says. “There’s also the interface on the backend to send the reports electronically into the facility’s systems so that they’re accessible and combined with patient information.”

Rosenthal says it’s common for hospitals to underestimate the setup required for voice recognition. “You need a vision of where [the technology] will go,” he says. For example, if your bandwidth is too slow, people won’t want to use the system. Plus, you won’t have the capability to eventually expand to nurses using voice recognition and performing electronic documentation, for example.

Overcoming Resistance

Rosenthal says that new technology will only be successful if it adapts to the way people already function. “You can buy the nicest solutions, but if people have to go out of their way to work in a different manner, they won’t use it.” That principle has played out, he says, as vendors are offering more ways to use voice recognition and bringing it into various applications. “The technology is fitting more into the way people work.” High failure rates in the early days of voice recognition were due to systems that asked busy clinicians to do things they wouldn’t normally do, he says.

Aurora Health Care, a 14-hospital, not-for-profit system covering eastern Wisconsin (…) purposely implemented voice recognition on a gradual basis. One reason for that was physician resistance, Hartig says. “I think resistance is normal. Most people resist change. We wanted the end-users to embrace it. We didn’t want to force it on them.” The organization still had its old system from Dictaphone so the physicians could opt to use that system or the new PowerScribe solution. The doctors who did use PowerScribe were able to reduce their report turn-around times very quickly, Hartig reports.

Gradual Implementation

Rosenthal says it’s very important to implement voice in phases. “Don’t deploy [it] on a large basis until you’ve run a good pilot and it’s functioning well,” he advises. His facility has been using voice for follow-up notes and is in the process of progressing to more complex documentation. Rosenthal has noticed that people are more willing to share their experience and knowledge about technology than they were in the early days of voice. “What we’ve done in the ED is now being deployed elsewhere in the hospital. Why reinvent the wheel each time? If somebody else can benefit, I think that’s good.”

> Read full article