Google Wants To Bring Voice Tech To Doctors

Google

Google is hiring staff to work on an early-stage research project called Medical Digital Assist, which will use voice recognition to help physicians take notes.

According to CNBC, four recently posted internal job listings describe building the “next-gen clinical visit experience,” as well as utilizing audio and touch technologies to improve the accuracy and availability of care.

The project is aiming to launch testing with an external healthcare partner by the end of the year.

This is the latest project for Google Brain, which focuses on healthcare. Late last year, the Brain team launched a “digital scribe” study with Stanford Medicine, using speech recognition and machine learning tools so that doctors could automatically fill out electronic health records (EHR) from patient visits.

Dr. Steven Lin, the Stanford physician leading the research with Google, explained how an AI-powered speech recognition system needs to accurately “listen in” to a patient visit and simultaneously use the relevant information to form a useful narrative.

“This is even more of a complicated, hard problem than we originally thought,” he said. “But if solved, it can potentially unshackle physicians from EHRs and bring providers back to the joys of medicine: actually interacting with patients.”

The first phase of this study will end in August, with both parties planning to renew the second-phase collaboration for at least another year. While there are no set plans to commercialize the tool, Lin believes that “if something like this actually existed, I think you’d have practices and hospitals tripping over themselves to get it at whatever cost.”

Google is certainly not the only company working on this kind of technology. Microsoft is working with the University of Pittsburgh Medical Center on its own Intelligent Scribe system, while Amazon is designing technology to take unstructured data from electronic medical records and then identify an incorrect code or the misdiagnosis of a patient.