5 ways voice recognition tech cuts costs

By Steff Deschenes
05:48 AM

Many may think of data in terms of numbers and text, but not only does voice documentation have a place in the array of data collection tools that can be used by healthcare companies, it offers financial benefits. 

Documentation with voice isn't just about capturing information, which is historically how people have thought about it. "It's now doing it in such a way that the document can be reused throughout an organization's downstream for other efforts like billing, quality assurance functions and medical and utilization reviews," explained Mike Raymer, senior vice president of solutions management at M*Modal, a company that provides clinical transcription services, documentation workflow solutions and unstructured data analytics. "Voice is about turning information into a language of understanding," he said. "It takes unstructured text and brings meaning to it that's transferrable from system to system."

[See also: UPMC, Nuance aim to take speech recognition to new level]

According to Raymer, there are five financial benefits that come with using voice recognition technology.

1. Reusable data
Voice data can be reused like any other data can be. "Studies show that two-thirds of U.S. hospitals are going to be absorbing a lot of penalties from readmissions. Data that's most predictive of readmission are ones bound in free text that's then been transcribed," said Raymer. The reusability that voice offers means accurately-coded and documented care that's immediately available for billing purposes.

2. Flexibility
Voice recognition isn't linked to a single device. "With today's technology there are cloud-based apps that allow the user to share a single profile across the board, so no matter where it's being used physicians have the ability to plug-in," said Raymer. From a reimbursement standpoint, the closer an organization is between delivery-of-care and recording-of-care the more accurate the information is, and the fewer challenges are likely to arise from an audit because the clinical documentation more succinctly matches.

3. Better clinical hand-off means fewer medical errors
The history behind clinical documentation started when a physician referred a patient to another physician. "There needed to be a good way to hand-off care and provide understanding to one physician around the thought processes and actions of the original clinician," Raymer said. The best way to capture that was to record information with words. Unfortunately, organizations began to create templates that forced a patient's story into a structured format using drop-down lists, radio buttons and checkboxes. Those documents no longer service the hand-off from doctor to doctor, because they don't capture the essence of what's happening. "Think of the most critical conversations in your life," said Raymer. "You want to use your own voice, tone and words to express or explain yourself." The accuracy of that clinical hand-off is critical too, because that's where errors occur. Eliminating medical errors – which can be very costly – by using something like voice is better for the patient, better for the budget.

[See also: 5 tips for speech recognition software from RSNA]

4. Productivity
As EMRs are implemented, the underlying assumption is that physicians will be less productive. "However," Raymer said, "there's been several recent studies that have shown that physicians that document via voice transcription are actually able to see more patients thereby increasing their billing for more hours worked." Some physicians believe they can see one-third more patients by using voice transcription then working with a structured template within the EMR. And with baby boomers coming into the later years of their life and the shortage of physicians expected due to the increase in patients from Medicare, it is going to be crucial that physicians are as productive as possible.

5. "One and done"
According to Raymer, the accuracy rates using voice recognition technology are unparalleled. "Rather than a physician waiting for a transcriptionist, the accuracy levels are so high that they can use the product themselves to capture the information they need directly into their work station or mobile device. They can then see what they said, make small corrections, sign the documentation, then send it off. This 'one and done' advantage eliminates the need for multiple steps and people involved, and makes clinical observations immediately available to everyone else," said Raymer


[See also: M*Modal to integrate speech understanding in Merge technology]