As a resident in obstetrics and gynecology I am exposed to a number of different clinical situations. We take care of patients in the outpatient setting, in the emergency room, on the labor floor and in the operating room. Regardless of where we are caring for our patients, documentation is a large part of daily clinical responsibilities. On a daily basis we are documenting our patients' clinical statuses, their progressions in labor, their operative reports and discharge summaries.

With a hectic clinical schedule and ever-important administrative demands, sometimes it feels that there is just not enough time to sit down and write/type all that has to be captured. And truth be told, some days there isn't. It is because of these great demands that I am extremely excited about the power and application of speech recognition.

Instead of spending time interpreting and then typing, speech recognition software allows me to "interpret out loud" and document at the same time. For example, when reviewing an electronic fetal heart monitor tracing or reading an EKG, it is much easier to say what I see, as I read it, than see, type, read, see, type, etc. As we all know, this is not a new concept since our radiology colleagues have been doing this for years. However, as opposed to being limited to radiology suites with super computers, the new medical dictation software packages are perfectly suited for your favorite desktop or laptop.

With just a simple microphone and a few hours of patience, you'll be dictating in no time.

I've found that setup is incredibly easy and that the integration between common word-processing software and electronic medical records is essentially seamless.

Furthermore, since some of the powerhouse software packages (Levine uses Dragon Medical by Nuance), come with pre-loaded medical specialty-specific libraries, the learning curve is nearly abolished since it knows complex words/phrases. For example, Pfannenstiel incision, leiomyomata, and morcellation were all recognized on my first dictation!

What is important to note is that it’s not just “convenient” that Dragon Medical can capture /recognize such key words; it is that the functionality allows me to create de novo patient-specific documentation.

As opposed to using pre-formatted templates to increase my efficiency and daily workflow, I can now just say what I did, how I did it, why I did it, etc. No longer do I need to scroll-up/down and continuously edit a pre-formatted note to make it fit my patient. Instead, I dictate notes that are specific and genuine to each patient. In my opinion, this is the critical backbone to using dictation for documentation. With speech recognition, the physician has the ability to generate highly accurate patient-specific documents that correctly convey the clinical scenario.

As someone who loves to integrate technology into his daily clinical practice, I am finding new and innovative uses for speech recognition in my clinical documentation process every day. I'm sure it's only a matter of time until we all have workstations that have microphones, because speech recognition truly is the way of the future, and the backbone in increasing the efficiency and quality of our clinical documentation.

Brian A. Levine, MD, MS is a resident-physician in New York City. He has a penchant for healthcare technology and is constantly experimenting with new and innovative ways to improve clinical efficiency.