Success of Speech Recognition in the Healthcare Industry
Today thousands of physicians use speech recognition software to create patient charts, referral correspondence, and email with-in their existing applications such as Microsoft Word. Many of these physicians are now moving to using a speech enabled EMR/Electronic Medical Records Systems. While many EMR products have not had the wide spread success of Speech Recognition Software in the Medical Industry, the marriage of the two technologies can be very beneficial for the healthcare provider. The information below discusses the advantages of utilizing speech recognition in the healthcare industry.
The Case for Speech Recognition
"Industry estimates from physicians and chief information officers at hospitals expect that 50% of physicians will utilize this technology (speech recognition) within 5 years."
With this front-end solution, the doctor dictates in front of the personal computer (PC) and usually does his or her own editing. Advantages include immediate generation of records and low costs. One clear-cut instance where speech recognition will prevail is for office notes, in which perfection is not required but documentation is important for ongoing care and billing purposes.
A quickly growing use of speech recognition is for e-mail physician-to-physician and physician-to-patient communication. Dictation of e-mail is many times faster than handwriting and America On Line (AOL) has included AOL Speaks in its Version 6 release. Physicians, however, need professional versions of speech recognition optimized for their needs.
Editing aside, nothing beats speech recognition for the office visit of the nursing home patient, the admitting note in the evening, or any instance where documentation is immediately needed, such as in the emergency room, ICU, and for STAT consults and reports when TAT is precluded. Weekend work, after-hour emergencies, and admissions often cannot wait even 24 hours for transcription solutions. Nursing homes often want reports sent back with the patient at the time of the visit.
From an administrative viewpoint, it is much less expensive to invest in a notebook computer, software, and training for a physician to use front-end speech recognition than to pay for on-going transcription services. Return on investment can be seen in as little as 2 months.
True labor costs are much more complicated and must compare the additional labor of the physician corrections against the time saved going to medical records, editing transcriptions, and searching for charts.
The true value of speech recognition lies in the quality improvement of the practice that generates high-quality consults and reports that are immediately available electronically. Any tertiary care physician will impress the referring physician by returning a written report quickly, and conversely, slow reporting is the death of the consultant. Many reports have demonstrated that quick actions, such as administration of antibiotics for pneumonia in the ER within 4 hours, shorten the admission and lower costs with improved outcomes. "
Ophthalmology Times
Speech Recognition Benefits Healthcare Providers
“Speech recognition solutions can effectively replace traditional transcription, reducing cost and speeding response to referring physicians,” said Dr. Robert Tash. “Document creation in realtime can be achieved without significantly altering the radiologists daily workflow. In addition, speech recognition software is always available, and the rapid turnaround of reports is a major benefit for us. We are very pleased with our results with speech recognition technology and consider it a vital tool.” SpeechTech Magazine (View Entire Article)
"Now, a physician assistant (PA) working in Cardiology, for example, carries a laptop during rounds. After meeting with a patient, the PA will go to a nursing station or other suitable area, put on a headset, and using Dragon’s NaturallySpeaking with a layer of WhyType?, begin dictating their notes from that visit at the point of care. The laptop is already connected to the hospital’s information system, so once dictation is complete, the physician simply copies the text and drops it into the existing network."
“The real benefit here is accuracy,” said Burke, a 20-year veteran of the technology sector. “As a clinician does their rounds, they may see a large number of patients. At the end of the day when they dictate reports, it is very difficult to recall every intricate detail on every patient. So, what we’re seeing is that the information captured at the point of care is much more detailed, which translates into better billing. There are people who code billing from what doctors dictate for billing purposes. If the doctor’s notes are more precise, then so will be the coding. Therefore, the billing will be more accurate. This is an enormous benefit.” SpeechTech Magazine (View Entire Article)
"Computer voice recognition transcription using real-time voice recognition software is an economical and accurate way to generate ED records. The software is nearly as accurate as traditional transcription, it has a much shorter turnaround time and it is less expensive. We recommend it’s use as a tool for physician charting in the ED." Robert G. Zick, MD and Jon Olsen, MD (Read Entire Case Study)
How Speech Recognition is utilized by Healthcare Providers:
Each practice uses speech recognition for different purposes, depending on their responsibilities, workflow, preferences, and other applications used. Speech recognition users include doctors, medical students, nurses, physician assistants, dentists, chiropractors, physical/occupational therapists, administrators, people with disabilities, transcriptionists, assistants, and other support staff.
The primary use of speech recognition software by medical professional is to dictate medical records, patient notes into their word processor. Other uses include emailing referral notes and/or letters to physicians. With the enhancements in EMR\EHR Software, many physicians are combing the two technologies to manage their patient records.
Doctors who wish to maintain their traditional workflow can dictate into a handheld recorder or save their recorded dictation with their documents for someone else to transcribe or correct. This substantially reduces the turnaround time compared to traditional transcription. If transcription is produced in-house, using speech recognition software frees up support staff for more productive tasks and can significantly reduce cost of outsourcing transcription.
