…from the ConText blender. SpeechMagic is now served in the following flavours:
- Consultations – US English
- Emergency Medicine – US English
News from a technology that is transforming healthcare practice
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:
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.
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!
HIMSS goes South again this year: after New Orleans 2007, welcome to Orlando 2008, live from the Convention Center. Booth #6843 is where you can find me and/or hot speech recognition breakthroughs: interactive SR for clinical notes, integrated PACS SR…not to mention the opportunity to meet with Stephen E. Rosenthal, M.D., the first healthcare Executive in North America to implement a wireless SR system in an ER setting. Other option: Mickey Mouse & co., just a few miles away. I always wondered how a speech engine would react to Donald Duck ‘s mumbling anyway.
The word is clearly spreading. A recent CRM Buyer Magazine article reports positive results for two US hospitals that have adopted speech recognition technology for their respective ER Departments. The news echoes the 2006 HIMSS survey, in which 65% of chief information officers had announced plans to equip their staff with speech recognition technology by 2008.
Abbott Northwestern Hospital, Minneapolis
Speech Recognition has been around for the past two years in the hospital’s ER department.
I’m able to complete my charts and consult other physicians about patients in real time. In the past, you might not see dictated notes for six to 12 hours, but now it’s instantly accessible by the entire team,” comments Christopher Obetz, M.D., emergency medicine physician.
The technology is not without its problems though. As you’re dictating, you have to keep one eye on the computer and make sure its transcribing correctly. Compared to the traditional method, a lot of the burden falls on the user for accurate transcription.
Ironically, while the software does very well with complicated medical language, it often struggles with shorter words or phrases such as “I am” or “she is.”
Massachusetts General Hospital, Boston
After a successful trial in the ER and a larger pilot in 2005-2006, speech recognition is now used by approximately 175 providers in 30 departments throughout the hospital.
For the most part, the software is easy to integrate with relatively short set-up and training times,” says Deborah Adair, director of health information services.
Harry Rhodes, director of practice leadership for AHIMA, commented the above news:
It’s being touted as a natural add-on to the electronic medical record, since doctors are used to recording their notes. The software can also prompt users to include information they may have forgotten, creating a more complete record. Resistance to change is also a hurdle. It’s a big transition, but not an insurmountable one, given that the technology can improve quality of care.
Visitors to the HIMSS Annual Conference & Exhibition will have the opportunity to meet Dr. Stephen Rosenthal, the first in North America to implement a wireless speech recognition and patient administration solution in an ER setting.
We introduced PDA devices that interface with the emergency and patient index system, as well as the speech recognition server. Physicians can now access up-to-date patient data and record their findings all from one single device,” explains Dr. Rosenthal.
Having turned his vision of a 100% future-proof system into reality, physicians now have access to a 24-seven solution. Document turnaround time has been accelerated significantly and the ER now has documents that are readable, searchable and that deliver suitable information for the electronic chart, making it much easier for physicians to make split-second decisions.
The ER is a fast-paced environment, says Rosenthal. We need to be with patients, we need to be mobile; we can’t be tied to a desk.
Dr. Rosenthal is credited with the initiation, development and implementation of medical informatics projects and has implemented electronic records, mobile speech recognition and digital dictation at his hospital. A member of the standards committee for interoperable Electronic Health Records (EHR) at Canada Health Infoway, Dr. Rosenthal has a vision that reaches far beyond the Montreal hospital’s walls.
“Standardizing information with the help of speech recognition can provide physicians with better decision support across provinces, even countries”, he noted.
Visitors to the conference will be able to share Dr. Rosenthal’s vision and experiences on the Crescendo booth (#6843) on February 26-27, 2008 (between 10.00 am and 4.00 pm). Meetings can be booked directly from the Crescendo web site.
The latest KLAS study on Medical Transcription Services Organizations (MTSOs) sheds more light on the role of speech recognition in the onshore/offshore dilemna. Michael K. Smith and Stacilee Whiting analyze the latest trends in the ever-changing world of transcription outsourcing in this month’s Advance Magazine:
Providers have begun to evaluate if editing services should be engaged domestically or offshore. KLAS has observed the beginning of acceptance of offshore transcription but preference for domestic, onshore editing. Providers who accept offshore transcription expect the editorial staff to be onshore to enhance the language proficiency, but there is not sufficient experience to determine the extent at which this is occurring. Some providers indicate they are willing to redirect some of the speech recognition operational cost savings to shifting offshore MTSO work back onshore.
The need for transcription is increasing due to :
1) electronic medical records and the need to populate them quickly and
2) speech recognition services needing editing on the back end. For these reasons, many MTSOs are increasing their capacity.