House calls may have gone the way of the country doctor, but physicians continue to be pioneers in the field of mobile technology. Physicians, for example, were one of the first groups to test out mobile pagers in the 1950s—the precursor to the mobile phone. Today, it’s hard to imagine a doctor without a smartphone or tablet on hand to aid in diagnosis and, of course, keep ahead of the next emergency.

And yet the role of the doctor has changed little over the years. On-site diagnosis and evaluation of patients is still a critical part of their jobs, and one that requires mobile technology in order to make those assessments in a timely manner while information and recall are still fresh. Physicians often record this information through a web-based portal or via an automated interactive voice response (IVR) system. But what happens when these resources aren’t available or convenient? Web sites, after all, can sometimes be slow; IVR systems even slower.

Dialogic partner Interactive Media arrived at an interesting solution to the problem: an automated agent that functions like a traveling medical secretary for physicians. To record their diagnoses and notes, physicians simply launch an app from their mobile device, provide their ID code and PIN, and begin speaking. The app uses advanced speech recognition software developed by Interactive Media to translate the voice into text, send it to the physician as an email and submit it as part of the patient’s medical records in the hospital database.

Building a human speech recognition engine isn’t, well, as easy as it sounds. There are accents and ambient effects that can make accurate speech detection challenging. Add the highly complex lexicon of medicine to the equation, and Interactive Media had their work cut out for them. To solve this problem, the company has developed a sophisticated natural language understanding solution and combined it with a database of known medical terms to provide error-free transcriptions of physicians’ notations and diagnoses. Of course, clear delivery of the voice media itself is critical to the solution’s effectiveness, and a major reason why Interactive Media uses Dialogic media processors to provide a clear connection between the physician and the application server where the speech-to-text translation occurs.

Since developing the application, Interactive Media has been working to roll out the solution for multiple languages in the hopes of helping more doctors record critical information at the point of treatment. In a field where minutes can make a world of difference, Interactive Media’s medical application ensures that physicians can easily record the right diagnosis, right away.