Speech Understanding will Bring More Information to the Doctor

Came across an interesting post by Steven F. Palter, MD from the docinthemachine blog. Specifically the blog he wrote on EMR=Clonewars

He notes that there is a hidden danger in EMRs of the inadvertant cloning of patients.

I don't think it is so much hidden or inadvertent - it's human nature and doctors are like everyone else - we always look for the path of least resistance. Copying from a previous note especially one using templates with a series of choices can be helpful.

But what he gets in his practice

..... is EMR records from other practices .... and the patients look identical.....Instead of all the details of a past treatment cycle it will list drug dose and failure with no detail of WHY it did not work. The diseases all look the same. There is never any detail on the nuances and subtle aspects of that individual’s condition. So when a group uses these records and they review a treatment every single person with the same disease (the “patient clones”) end up looking identical and treated identically. Cookie cutter assembly line medicine.

There's hope - Speech Understanding and in particular the use of CDA4CDT documents which make narrative notes interoperable with electronic medical records - bridging the divide between where we are today:

• More than 60% of clinical content produced, stored and locked in narrative documents

and where we want to get to

• Structured encoded information that is semantically interoperable and can be automatically processed and used by computer systems to help apply the best knowledge of healthcare diagnosis and treatments available today
  

What this means is a at the most basic level virtually any clinician can produce a minimal CDA document utilizing the simplest form of the structure which includes all important uniform metadata for all documents that allows them to be indexed, searched and the content integrated in a meaningful way into the EMR.

And at the high end, lab systems, pharmacy systems and EMR's can produce richly-structured, fully machine-processable CDA documents that remain human-readable as well as machine readable which will satisfy Steven's needs of :

the nuances and subtle aspects of that individual’s condition

So as Steve rightly points out quoting from AHIMA 2006 study:

....65 percent of chief information officers planned to get it (Speech Recognition) by 2008. It’s being touted as a natural add-on to the electronic medical record, since doctors are used to recording their notes, says Harry Rhodes, director of practice leadership for the American Health Information Management Association.

Voice can help solve the cloning of patients and the technology and the standard is available today.