The HealthScribe API enables the summary of doctor-patient discussions, using speech recognition and generative AI

2 Min Read
A doctor holding a tablet showing something on the screen to a patient
Getty Images

AWS is throwing its weight behind generative AI solutions for the health care sector.

At the AWS Summit New York, the cloud giant unveiled HealthScribe, a new API to help health care software providers build applications that transcribe and summarize doctor-patient discussions, using speech recognition and generative AI.

AWS said HealthScribe is a single API that lets applications “automatically create robust transcripts, extract key details (such as) medical terms and medications, and create summaries from doctor-patient discussions” that can then be entered into an electronic health record system.

By automating medical note-taking, it lets physicians focus on their discussions with patients.

HealthScribe can create clinical notes on more than one medical specialty, starting with general medicine and orthopedics.

The cloud giant also emphasized that every line of generated text has its source cited within the original conversation transcript, which makes it “easier for physicians to review clinical notes” before entering them into an electronic health record system.

There has been some concern among medical professionals about blindly trusting an AI-powered system when it relates to patient health.

AWS also stressed that all data coming through HealthScribe is secured and encrypted. No data is used by AWS to train its models. HealthScribe is HPAA-eligible as well, meaning its API adheres to provisions of the Health Insurance Portability and Accountability Act to ensure health information is kept secure and private.

According to AWS, developers do not have to manage the underlying machine learning infrastructure or train their own large language models specific to health care.

AWS Ramps Up Generative AI Efforts

AWS’ health care API comes as the company ramps up its generative AI efforts.

Its flagship offering, Bedrock, offers users a host of AI models including Claude from Anthropic and Jurassic-2 makers AI21 Labs. The new HealthScribe platform is also powered by Bedrock.

In June, AWS announced that it is spending $100 million on a Generative AI Innovation Center to connect clients with AWS machine learning experts to help work on projects.

And AWS’ parent company Amazon has been exploring ways to use AI to improve its e-commerce search offerings. Amazon sought to hire several AI engineers to work on AI-powered improvements to its shopping site.

Amid its accelerating efforts, AWS was among the companies to have agreed to rules from the White House to allow independent experts to vet AI products before they are released to the public. Rivals Microsoft and Google also agreed to the rules, as did OpenAI, Anthropic, Inflection AI and Meta.

This article first appeared on IoT World Today's sister site, AI Business.

About the Author(s)

Ben Wodecki

Junior Editor - AI Business

Ben Wodecki is the junior editor of AI Business, covering a wide range of AI content. Ben joined the team in March 2021 as assistant editor and was promoted to junior editor. He has written for The New Statesman, Intellectual Property Magazine, and The Telegraph India, among others.

Deborah Yao

Editor, AI Business

Deborah Yao is an award-winning journalist who has worked at The Associated Press, Amazon and the Wharton School. A graduate of Stanford University, she is a business and tech news veteran with particular expertise in finance. She loves writing stories at the intersection of AI and business.

Sign Up for the Newsletter
The most up-to-date news and insights into the latest emerging technologies ... delivered right to your inbox!

You May Also Like