August 20, 2007

Finding Its Voice
By Annie Macios
For The Record
Vol. 19 No. 17 P. 24

Despite a checkered past, the use of speech recognition technology in conjunction with electronic medical records is making a strong comeback in improving productivity and patient care.

Speech recognition (SR) technology in the healthcare arena was introduced in the early 1990s. While there was excitement about the potential of replacing handwritten notes and simple dictation for medical records, the expectations outweighed performance, and healthcare facilities adopted something of a “once bitten, twice shy” attitude.

Because SR’s introduction wasn’t as successful as hoped, healthcare facilities have been somewhat reluctant to give it another try—that is, until recently. The advent of newer and more successful technology has sparked renewed interest in SR.

Fortunately, technology has evolved to a point where SR can now be used to successfully shuttle the narrative, structured, and encoded information from the dictation between the electronic medical record (EMR) and HIM applications, leading to improved decision support, reporting, and information sharing. This provides a win-win situation for doctors, healthcare facilities, and patients.

Past Performance
“Historically, [SR has] been disappointing because it couldn’t deliver on expectation,” says Nick van Terheyden, MD, chief medical officer at Philips Speech Recognition Systems in Washington, D.C., who likens the former expectations to a Hollywood notion reminiscent of old sci-fi shows. “When Philips introduced SpeechMagic in 1993, there was an overwhelming response, but because it was still in early stages, the results were disappointing.” He noted, however, that during the last 10 years, there have been great improvements, and the technology has reached a “tipping point” as far as benefits and efficacy for EMRs.

SR’s Resurgence
“The medical profession is overwhelmed with data,” says van Terheyden, who estimates the amount of data doubles every 18 months. “A typical patient looks to his healthcare provider to know what is best for him. But the idea that they know the latest and greatest information is impossible.”

The EMR is a critical piece of technology that can corral patient data into one complete record. Implementation of it, however, is often difficult for financial reasons, as well as because of resistance from physicians who fear substantial interruption in their workflow. But according to Eric Fishman, MD, founder of EMRconsultant.com, the EMR acceptance rate “goes up astronomically when physicians know that SR will be part of the implementation.”

Thus, in an effort to keep pace with the information overload created by the need for strong documentation, healthcare facilities are once again turning to SR to increase productivity and, in the long run, improve overall patient care.

Implementing SR With the EMR
While experts agree that the use of SR in conjunction with EMRs is an important technology, they have varying opinions on exactly how SR can best serve the physician, patient, and healthcare facility. Nonetheless, experts concur that from their experiences, improving workflow and patient care and reducing costs are among the top benefits.

“There is no one perfect solution,” says Fishman. Finding technology that works best for an organization can include using a combination of dictation, SR, templates, and revisionists (also known as medical transcriptionists).

Kathy LePar, RN, MBA, a senior manager at Beacon Partners in Boston, has guided many healthcare organizations in the search-and-selection process for SR and EMR technology. LePar, who has also helped implement the technology, has seen its prevalence rise over the last several years. “Many of the software vendors demonstrate the use of it for physician practices with ambulatory EMR applications,” she says.

Paul Egerman, CEO of eScription Inc., a Needham, Mass.-based company specializing in background SR technology for medical transcription, believes that SR’s two main roles are to reduce the costs associated with transcription, which can be substantial, and standardize EMR documents so they look the same. He says that once the documents are standardized, it becomes easy for physicians to extract the data they need in making patient care decisions.

Carle Clinic in Urbana, Ill., is a facility that has successfully made the change to SR technology. Tricia Truscott, MBA, RHIA, CHP, Carle Clinic’s HIM director, was directly involved in the move to SR and the facility’s quest to make medical record improvements. “We were moving to an EMR and needed to find a way to capture the information that was currently in handwritten notes, which meant moving to full dictation. But the cost was staggering,” she says.

With 330 physicians in 11 locations, Carle Clinic moved to dictated notes to capture information for its EMR. At the same time, it decided to switch to SR technology in an attempt to stem the huge costs associated with dictating each patient note. On a recommendation from its chief information officer, Carle Clinic chose a software solution from eScription.

Because physicians were dictating more notes—notes that were formerly handwritten—Carle Clinic found itself in a situation where the transcription volume grew from approximately 15 million lines per year to 40 million lines per year. As a result of the SR implementation, the average transcriptionist’s productivity increased by roughly 90% because the new model automatically produced accurate and fully formatted first draft documents from clinicians’ dictations, which the medical transcriptionists review and edit. In turn, the productivity gain lowered transcription costs. Moving to background SR improved Carle Clinic’s ability to handle more volume, as well as reduce costs significantly.

Changing to the eScription technology has also provided consistency in the EMR. Previously, doctors used different templates for straight dictation, but now they work on only a few consistent templates. To date, the information is structured but not discreet, so Carle Clinic is not creating reports from the information or using data fields.

Fishman sees this as the way most facilities currently use SR: using the dictation for parts of the record (eg, the history and final assessment) in combination with the templates to fill the diagnostic information, which he says creates a good EMR.

Additional Applications
Applying the dictated information directly into the EMR for physicians is another way some healthcare facilities are using SR technology.

According to van Terheyden, voice recognition used solely as a narrative note doesn’t achieve optimal results following EMR integration because it doesn’t always link data points to the record and can’t be queried. “Speech is the most natural form of communication,” says van Terheyden. “SpeechMagic takes speech, extracts the data, and ‘pops’ it into the medical record. It moves away from a redundant process.”

Michael Finke, CEO of M*Modal in Pittsburgh, agrees, but also describes the unique business potential offered by today’s plethora of information: “Today’s medical infrastructure can better be served through a synergistic ‘speech recognition and understanding’ software platform integrated with an enterprisewide EMR system. The doctor still dictates as usual, but the physician’s narrative is automatically transformed into a very accurate, completely formatted, structured, and encoded meaningful clinical document—which includes a transcript of the physician’s spoken words along with values, terms, and phrases that have been tagged as significant content.”

Egerman believes that a balance of textual and objective data can be the most valuable, as there is always anecdotal data from a patient consultation that can’t be captured on a typical “point-and-click” screen that physicians use. He points out how a patient’s social situation is an important aspect that can’t always be captured in the objective data. “For example, a healthy, 96-year-old woman may be at the physician’s office for her yearly check-up,” says Egerman. That noteworthy anecdotal data is important to be aware of, but, nonetheless, may not be included on a physician’s transcript if only EMR objective data is used.

Possible Pitfalls
LePar also stresses the importance of getting the most from the new technology. To integrate the SR technology with an EMR in an optimal way, she says it is vital that physicians use SR in conjunction with entering information into the required data fields.

“Physicians are so comfortable with SR and the dictating process that, often times, the narrative documentation replaces the point-and-click process of entering data elements, which is necessary to derive outcome data,” says LePar. Many programs already have the capacity to extract meaningful data embedded into their systems, and therefore, it is important to use the narrative fields in conjunction with inputting the data points, she says.

Egerman also mentions that SR on its own is simply a technology that should be used as an aid in working toward a complete EMR. “SR is a technology just as a database or keyboard is a technology,” he says, that when used together make the EMR data valuable.

Improving Patient Care
Dictation takes longer to see through completion with more processes involved, including corrections and getting the information into the chart. With SR, if a physician is doing a consultation dictation, results and referral requests are achieved faster in real time, and patient safety improves. “There is no waiting for the transcribed note to make its way to the chart,” LePar says.

Because information is documented immediately, patient information can be sent in real time to doctors, referrals can be made quickly, and the possibility of medical errors is reduced. From a management standpoint, transcription costs are reduced, and billing can be done in a timelier manner because documentation is completed sooner.

“To really get to value, you need to understand what physicians dictate. If a physician wants to take actions [regarding a patient case], the EMR must describe the content in a structured way,” says Finke. With M*Modal’s speech understanding technology, the benefits flow directly from maintaining the same workflow process but repurposing it for something of bigger value to achieve better results. “Nothing changes except the additional benefit of being able to use data to improve patient care,” says Finke.

SR, when integrated into the EMR, “ties it back to clinically actionable data,” says van Terheyden, and can tie it in with clinical coding. He believes this is the future of SR because it drives actions that physicians are desperate for. It also keeps physicians up-to-date on the most current information, thus improving patient care.

Benefits to Healthcare Organizations
Aside from the obvious benefits of improved workflow and information exchange, healthcare organizations can expect a substantial return on investment in several ways, including productivity, more accurate billing, and avoidance of some transcription costs.

At first, physicians may view integrating SR technology with EMRs as a cost because it appears to take more time. However, reports are actually turned around more quickly and have better data from which to draw patient care information.

In addition, because patient information is delivered to the EMR more quickly, physicians can bill almost instantaneously. “The reality is, you have to pay bills, so now you don’t miss any information and get fair compensation for work done by capturing it at point of care,” says van Terheyden.

Also, healthcare organizations can add monies to their coffers by using voice recognition to negate transcription costs associated with unnecessary text. “Across the whole of a hospital, they can expect a 30% to 40% savings over using conventional dictation and transcription to text,” says van Terheyden. For transcriptionists, or “revisionists” as Fishman says they are now called, background SR technology allows them to become medical language specialists, a role—in which they validate the text’s accuracy—that secures their position as a valued member of the HIM community.

Evolving Process
The latest versions of SR technology for use in conjunction with EMRs have “made more of an impact than what was available several years ago,” according to LePar. While she says it takes on average five to 10 hours of use to “train” a physician’s voice, the time spent is well worth the effort in the long run.

“It’s much easier than it used to be,” says LePar. She sees that physicians are feeling more comfortable and confident using SR technology because they are already used to dictation. With background SR, such as in use at Carle Clinic, there is no explicit training for clinicians or change to their workflow. The transition is often seamless to them.

“I see it being used much more frequently than in the past. This technology is what many of the physicians are requesting,” says LePar.

“Speech recognition, when combined with the EMR, provides key input in successful patient care,” says van Terheyden. “It doesn’t completely solve the problem, but it is an essential piece of the puzzle in conjunction with other facets of healthcare management. It’s a definitive part of the solution.”

“SR on its own is a great technology tool. It’s a piece of the puzzle, but an important piece of the puzzle,” adds Egerman.

— Annie Macios is a freelance medical writer based in Doylestown, Pa.

On the Horizon
In an effort to standardize the most common types of dictated clinical documents, a project known as CDA (Clinical Document Architecture) for Common Document Types (CDA4CDT) is working to create implementation guidelines for the most common types of dictated documents. The guides will use the Health Level Seven (HL7) CDA, the same framework used by the American Society for Testing and Materials/HL7 Continuity of Care Document.

Large transcription companies, as well as provider organizations, are already on board with the program. The first documents being considered for standardization are an Implementation Guide for History & Physical reports, with consult notes and operative notes next on the list.

It is thought that by standardizing the sections within core document types, new opportunities are created for better decision support and patient safety. “The challenge is to get an EMR [electronic medical record] to make use of richer documents,” says Michael Finke, CEO of M*Modal. With several millions of documents generated monthly using hundreds of formats and thousands of different systems, standardization can help create a more comprehensive EMR that will be available across the continuum of care for any given patient.

For more information, contact Liora Alschuler, project manager of CDA4CDT, at liora@alschulerassociates.com.

— AM