Speech Recognition With General and Medical Vocabularies Revisited II

A Google search on “mba md programs” brings back over 12 million results, many of which are the particulars of the hundreds of MD/MBA programs now offered by leading universities.

This means that medical practices are now incorporating modern business models and that, in turn, means that practice managers and their accountants are not only looking for ways to cut costs as they have in the past but are now also looking for ways to establish new profit centers. Many times, speech-to-text tools like Dragon Medical Practice Edition provide the solution to one or both.

Nuance will this month release Dragon Medical Practice Edition, an upgrade to its medical speech recognition tool for small offices that should even further reduce transcription costs by making it easierier to enter data into an EHR.

Dragon Medical Practice Edition is similar to Nuance's existing Dragon speech recognition options for health care in that it allows health care workers to create medical notes directly in an EHR system in real time.

The new version has a number of time-saving features: for example, it alerts the user and offers advice when a poor audio input caused by incorrect microphone connection or background noise is detected. And that’s just the beginning.

Existing and new users can click here for the results of a YouTube search on “Dragon Medical Practice Edition”

These voice-translation videos fall roughly into the following three categories:

• Technical topics such as profile optimization

• Nuance and other tutorials

• Case studies narrated by practicing physicians

These YouTube videos and my prior posts on speech-to-text translation offer a pretty comprehensive introduction to speech recognition software in general and Dragon Medical software in particular. Check them out.

Speech Recognition With General and Medical Vocabularies Revisited

A while ago, back on May 10, 2009, I posted an article that discussed speech recognition software in general and Dragon Medical 10 in particular. Click here to navigate to that post. In the two years plus since then, the field of speech-to-text translation (and the hardware available for speech-to-text translation software to execute on) has advance. This can be seen in the research reports published at the Special Interest Sites that you can navigate to from the links at the top of the right-hand column of this blog.



Reflecting these advances, Vendors, Nuance Communications Inc., the maker of Dragon NaturallySpeaking and Dragon Medical Practice Edition, in particular, have been able to release improved versions of their products: The next version of Dragon Medical will be called “Dragon Medical Practice Edition” and will feature the Dragon NaturallySpeaking 11.5 Speech Engine. I have found it to be faster and more accurate than any previous version of Dragon. (The most recent versions utilize new hardware features such as multithreading and multicore CPUs, and they double the sampling rate and more).

That said, it's still important that you use any speech-to-text translation product with a good sound card and a good microphone.

Click here for a downloadable Product Sheet

Click here for a Feature and Specs Sheet

As is my wont, I recently installed a pre-release copy of Dragon Medical Practice Edition hurriedly: that is, I wasn’t very careful when I built a profile (trained Dragon) and then gave Dragon an initial test run by speaking into a 10-year-old, $5.95 microphone that happened to be connected to my sound card at the time. The idea was simply to familiarize myself with this new edition a little before using it seriously later. To my astonishment, even with this primitive set up, Dragon Medical Practice Edition converted my speech to text without a single error throughout a 5-minute run (using the General vocabulary).

There's an awful lot of information about this new version to sift through. Nuance's site (click here) is a good place to start.



{ Click on the image above for a larger view }



As a footnote, I want to add that systems that convert spoken words to text are not just of value to professional practices. I have an acquaintance who has used this software for over a year as he has had a stroke and finds it difficult to type. He speaks well of it.

IBM's Watson and Nuance's Dragon Medical

Earlier this week, after the Watson computer defeated human champions in a three-day match on the popular TV show Jeopardy, its creators and a Massachusetts software company prepared to sell a medical version of the smart machine.

IBM has an agreement with Nuance Communications Inc. of Burlington to sell Watson-based products to health care providers. Nuance already offers voice-recognition software for a variety of applications. The companies are pitching forthcoming technology that will, among other things, allow medical providers to describe symptoms orally and get diagnostic information in return.

Watson technology will enable Nuance to add artificial intelligence to its offerings. And that's where this blog comes in. I've been talking about these two topics, albeit separately, for some time now.

Watson's ability to analyze the meaning and context of human language, and quickly process information to find precise answers can assist decision makers, such as physicians and nurses, unlock important knowledge and facts buried within huge volumes of information, and offer answers they may not have considered to help validate their own ideas or hypotheses.

For example, a doctor considering a patient’s diagnosis could use Watson’s analytics technology, in conjunction with Nuance’s voice and clinical language understanding solutions, to rapidly consider all the related texts, reference materials, prior cases, and latest knowledge in journals and medical literature to gain evidence from many more potential sources than previously possible, thereby helping the medical professional to confidently determine the most likely diagnosis and treatment options.

For more information about the Watson computing system and the Jeopardy! challenge, click here.

On earlier posts to this blog, I discussed the semantic Web, ontologies, and speech recognition software from Nuance (and Adobe):

See, for example, my November 7, 2009 post "Vagueness, Logic and Ontology: Fuzzy Ontologies"

In traditional ontology theory, concepts and roles are crisp sets. However, there is a great deal of fuzziness in the real world.

For example, one may be interested in finding “a very strong flavored red wine” or in reasoning with concepts such as “a cold place”, “an expensive item”, “a fast motorcycle”, etc.

A possible solution to handling uncertain data is to incorporate fuzzy logic into ontologies. Unfortunately, these fuzzy ontologies have shortcomings – reasoners for fuzzy ontologies are not yet so polished as those for crisp (aka traditional) ontologies.

See, for example, my May 30, 2009 post on "Speech Recognition Software"

The trivial example of one-to-one translation given there can be extended to one-to-many translation: That is, in a matter of seconds, you could “program” Dragon Medical to type out a whole sentence in response to your speaking just a single word or code into the microphone. And, vice versa: you could “program” Dragon Medical to type out just a single word or code in response to your speaking a whole sentence into the microphone.