Saykara, a Seattle-based health technology start-up company, recently launched its first mobile app for iOS, an AI-fueled voice scribe that aims to be the Amazon Alexa for providers and hospitals.

#PNN_phone_stethoscope_miscmedicalitems

The goal is to accurately transcribe audio to text, parse the information to make it structured, and insert it cleanly into an electronic health record, according to CNBC. SayKara was developed by a group of former employees from companies like speech recognition giant Nuance and Amazon.

The app has been used at a number of private practices over the past few months, but with the rollout of the app on iOS, it will begin trials at larger hospitals, as reported by GeekWire.

"We're taking the state of the art in speech recognition and machine learning and we're applying it," Saykara CEO Harjunder Sandhu explained. "The key is to couple it with deep knowledge of how physicians work and the information that is relevant to them."

Unlike Amazon’s Alexa, Saykara is focusing solely on healthcare by simplifying data captured with a new artificial intelligence-based virtual scribe solution that eliminates the hassle and cost of working with EHRs. It also aims to cut months of training for human transcribers, saving time and money.

There are still concerns in the medical field, however. When dealing with patient information, security is a huge factor. Like EHRs, having all that information stored in a cloud-based format is a risk. And while certain measures are currently being taken across the country to help keep patient information safe, voice-enabled equipment is still relatively new, especially in medicine, and could bring up problems not yet experienced.

One major issue is identifying and understanding different medical terms. A simple misinterpretation between “hyper” and “hypo” can ultimately lead to extreme complications. Speech patterns and certain accents can attribute to this issue and inaccuracy.  

“Saykara is built on a combination of speech recognition, natural language processing and machine learning. Most importantly, it is highly customized to a physician's workflow, by speciality,” Sandhu said in an email to Geekwire.

(0) comments

Welcome to the discussion.

Keep it Clean. Please avoid obscene, vulgar, lewd, racist or sexually-oriented language.
PLEASE TURN OFF YOUR CAPS LOCK.
Don't Threaten. Threats of harming another person will not be tolerated.
Be Truthful. Don't knowingly lie about anyone or anything.
Be Nice. No racism, sexism or any sort of -ism that is degrading to another person.
Be Proactive. Use the 'Report' link on each comment to let us know of abusive posts.
Share with Us. We'd love to hear eyewitness accounts, the history behind an article.