Capturing the Nuance with Medical Speech Recognition

When documenting a patient encounter, it is essential to record the “nuance” of that particular patient’s history, your findings, and the care that you provided. Every patient is unique, and the “click notes” functionality in today’s EHRs is simply not capable of recording that kind of detail. You don’t want the last 10 headache patients to all sound the same, right?

Creating "generic" notes can compromize patient care provided by us and others. The only way to capture the subtleties for each patient is to add specific text in addition to clicking. This can be done via keyboard or speech recognition software. Typing (no matter how fast you are) is a terrible waste of your time, talents, and efficiency. With the increasing pressures to do more in less time, we also tend to cut corners, decreasing the quality of our documentation.

When using speech recognition software, there are a number of ways to be most efficient:

  1. Make corrections by voice, instead of using your keyboard. This is faster, and also helps the software to become more accurate over time.
  2. Use Custom Commands (macros) to insert chunks of repetitive text into your notes instead of dictating the same things repeatedly for each patient. This functionality works best for standard physical exams, review of systems, procedures, and patient education sections of the notes which can tend to be repetitive. The inserted text can then be easily modified by voice for any variations related to a specific patient.
  3. Schedule an “experienced user class” so you can learn (and re-learn) techniques for using the software most efficiently. These are done remotely, one-on-one, and customized to your current skills and future goals, lasting 1-1.5 hours per session. Our clients almost always experience an ”Ah-Ha Moment” in the first few minutes of these sessions. Just as you attend regular CME sessions to keep your medical skills up to date, you should consider sharpening your medical speech recognition skills at least once a year. See: Dragon Training
  4. Upgrade to the most recent version of the speech recognition software; this will give you noticeably increased speed and accuracy. For Dragon Medical, you can purchase an upgrade to Dragon Medical Practice Edition-4 (version 15) for about 1/3 the cost of a new license. With SayIt, your monthly subscription includes automatic updates on a quarterly basis.

By |January 25th, 2019|Providers|0 Comments

Dragon Medical – Selecting & Correcting by Voice

This article is intended to refresh some key concepts since you completed your Dragon Medical Training.

SELECT is Dragon’s MOST important command.  We are all in the habit of reaching for our mouse to delete an incorrect word, then typing the correction.  Two problems with this:

  • It wastes time
  • Dragon doesn’t “learn” from these corrections

If you gradually switch to correcting by voice, you will become more efficient and Dragon will become more accurate!

Using the “Select” command:

  • Select/highlight the incorrect word (or phrase) to be edited by saying “Select” followed by the incorrect word (or phrase) e.g. “Select disgust”; Don't pause or hesitate between the command and the word
  • Nice feature: If there are multiple occurrences of the word (e.g. “disgust”), then Dragon will number all of them for you.  Simply say “Choose 3” (for example) to highlight the one that you want.

The Correction Menu appears with a number of options:

  1. You can immediately say another word or phrase (e.g. “discussed”)

OR

  1. If one of the menu options is what you want, say “Choose” followed by the number of that option, e.g. “Choose 2”.

OR

  1. If none of the listed options are correct say “Spell That” to spell the correct word or words into the Spell Dialog Box. Unfortunately, since many letters sound the same (e.g. “s” vs. “f”), it is easier to just type the correct spelling using your keyboard, rather than trying to spell by voice.

Then say “Go Back”, and your cursor will return to where you left off so that you can resume dictating.

Variation:  The “Select [first word] Thru [last word]” command:

What if you need to select a phrase, sentence, or whole paragraph?

Example:  Assume that you have a command for a normal Review of Systems for a level 3 visit:  “ROS 6”, and the CV history is NOT normal:

--------------------

Constitutional:  No chronic fatigue, unexpected weight gain or weight loss.

Eyes:  No visual impairment, no pain, watering, discharge or itching.

ENT:  No ear or sinus infections.  No recurring nosebleeds, no chronic nasal congestion.  No  mouth lesions or dental pain.  No throat pain or dysphagia.

Respiratory:  No wheezing, dyspnea on exertion, or chronic cough.

CV:  No chest pain, cyanosis, palpitations, dizziness, or fainting.

--------------------

Just Say:  Select No Thru fainting”  (Use THRU not TO)

The whole CV review will be selected.  Then dictate the abnormal history, such as:

“3 month history of substernal pressure during exertion”…then say:

Go Back

It’s as easy as that!

Twin Cities EMR Consulting, Minneapolis, MN
 Medical Speech Recognition Products – EHR Consulting Services – Training – Support
By |April 27th, 2017|Providers|0 Comments

Dragon Medical – How To Improve Accuracy

Wayne Kaniewski, MD

This article is intended to refresh some key concepts since you completed your Dragon Medical Training.

For clinicians who were accustomed to dictating to a human transcriptionist in the past, you discovered quickly that you cannot dictate at “warp speed” when using medical speech recognition technologies (MSRT).

Q:  Must I dictate very slowly when using Dragon voice recognition software?

A:  No.  But you must e-nun-see-ate more than you may be used to.  Dragon™ Medical “listens” for patterns of sound (phonemes).  So, you must pronounce some words more distinctly that you may be used to.  When you speak to another person, they can usually “fill in the blanks” if you are not speaking clearly; with Dragon, enunciation is more important.  Examples:

  • Sound-alike words
    • he vs. she
    • an vs. and
    • is vs. it
  • Terminal syllables
    • discuss vs. discussed
    • depress vs. depressed
    • patient vs patients

Generally, you are able to dictate as fast as you are able to enunciate clearly.  When you start “tripping over your tongue”, Dragon Medical will start making misrecognitions.

The more “sound data” that you provide, the more that Dragon will be able to decide, using complicated mathematical algorithms, between several words that sound alike.  These algorithms also look for word pairs that commonly occur together, and these pairs may vary greatly depending on the vocabulary (e.g. casual speech vs. medical terms) and the user.

For instance, if you dictate “an EKG” and the software repeatedly transcribes “in EKG”, it won’t accomplish much to correct or train “an" vs. "in” since these words each consist of very little sound data to allow distinguishing between them.  You will be more successful by training the phrase “an EKG”.

Just as Dragon will have difficulty distinguishing between monosyllabic words, it also has no way of knowing what homonym forms you intend if those words are used in isolation.  For instance, how can you distinguish between these words, when they are all pronounced the same?

  • their, there, they’re
  • two, too, to, 2
  • past, passed

The solution is to dictate in complete sentences, with the period (or ! or ?)  The software engine “looks” at the context of a sentence, and is thus able to be more accurate in determining the correct word form to use.  The speech engine for medical specialties actually looks at the medical context of a sentence, and that is one reason why the medical versions of speech recognition software are going to work better for medical documentation than available non-medical products.  It’s not just the difference in the software vocabularies!

We’re not used to dictating in complete sentences.  It’s a bit easier if you first think about what you are going to say in the next sentence, then dictate it.

When a misrecognition occurs, try to avoid the habit of correcting it using the mouse & keyboard.  Instead, follow these steps:

  • Use the “Select” voice command to highlight the misrecognized word(s)
  • Speak the correct word(s), or "Choose" from the Corrections Dialog Menu
  • Use the"Train That" command

The software will “learn” and be less likely to make that misrecognition in the future.  It’s a difficult habit to break, but it will pay off in the long run!  This process, once mastered, will be faster than always reaching for your mouse & keyboard, and will also decrease the chances of repetitive stress injuries.   Also, selecting then correcting 2-3 words together may be more effective than just one word, particularly if that one word is a monosyllable.

Despite your best efforts, you will sometimes have unexpected, nonsensical, and even hilarious things transcribed into your notes.  So, the final and most important point is to always read your notes before you sign them.  Putting a disclaimer in your electronic notes that “Speech recognition software was used to create this note.” will not protect you in a court of law.  Not reading your notes can also, more importantly, potentially impact patient care.  How about this one?

Dictated:  “Questions were invited and addressed.”

Transcribed as:  “Russians were invited and undressed.”

In summary:

  • Enunciate
  • Dictate smoothly at an even, moderate pace
  • Speak in complete sentences with punctuation
  • Make corrections by voice, not keyboard
By |January 20th, 2017|Providers|0 Comments