AWS announces AI service for physicians at Re: Invent

  • December 17, 2019
  • imc

At this month’s AWS Re:Invent conference in Las Vegas, Amazon Web Services (AWS) announced an artificial intelligence (AI) service that offers healthcare providers accurate, real-time speech-to-text transcription so they can focus on patient care.
 
Today, physicians are required to conduct detailed data entry into electronic health record (EHR) systems as part of their everyday duties. However, AWS says products that help them accurately record and document patient encounters are sub-optimal.
 
At many hospitals, physicians must dictate medical notes into recorders and then submit those voice files to third-party manual transcription services, which is expensive and can take as many as three business days, delaying documentation workflows overall. Another option is to leverage existing front-end dictation software, but existing tools are limited and physicians still end up spending several hours on clinical documentation every day. A third option is for healthcare providers to hire human scribes to assist physicians with note taking during patient encounters, but human scribes can be unsettling to patients, physicians often mention that their output is imperfect, and medical organisations struggle to schedule and coordinate scribes at scale.
 
Amazon Transcribe Medical solves these problems by using machine learning technology to transcribe natural medical speech automatically. Clinical documentation applications built on top of Transcribe Medical’s speech-to-text capabilities produce accurate and affordable transcripts.
 
Transcribe Medical consists of multiple machine learning models that have been trained on tens of thousands of hours of medical speech to deliver accurate, machine learning-powered medical transcription. Transcripts are generated in real time, eliminating the multi-day turnarounds.
 
It can help physicians automatically transcribe conversations during the patient encounter without the distraction of manual note taking, allowing health care providers to focus on patient care. Physicians can speak naturally, and Transcribe Medical uses built-in automatic punctuation to overcome the limitations of existing transcription software.
 
For healthcare providers, voice products built on the service are scalable to thousands of potential medical centres, removing the operational pain of managing and coordinating temporary scribes.
 
The service is HIPAA eligible, and offers an easy-to-use API that can integrate with voice-enabled applications and any device with a microphone. Text output from Transcribe Medical can also be used by other AWS services, such as Amazon Comprehend Medical, a natural language processing service, for downstream data analysis before final entry into EHR systems.
 
This was one of five machine-learning services launched at Re:Invent for application developers and end users with no machine learning experience required. The other four services are:

  • Kendra reinvents enterprise search by using natural language processing and other machine learning techniques to unite multiple data silos inside an enterprise and consistently provide high-quality results to common queries instead of a random list of links in response to keyword queries.
  • CodeGuru helps software developers automate code reviews and identify an application’s most expensive lines of code.
  • Fraud Detector helps businesses identify online identity and payment fraud in real time, based on the same technology developed for Amazon.com.
  • Augmented Artificial Intelligence helps machine learning developers validate machine learning predictions through human confirmation.

The services use AI to allow more developers to apply machine learning to create better end user experiences, including machine learning-powered enterprise search, code reviews and profiling, fraud detection, medical transcription, and human review of AI predictions.

• AWS and the US National Football League (NFL) announced a partnership at the show with the goal of advancing player health and safety using AWS’s portfolio of services and expertise. Building on the existing Next Gen Stats partnership, AWS and the NFL plan to innovate together to shape the future of gridiron football.

The partnership aims to leverage AWS’s artificial intelligence and machine learning services to provide a deeper understanding of the game. The NFL and AWS say they will develop tools and generate deeper and better-informed insights into player injuries, specifically the impact of a variety of factors such as game rules, equipment, and rehabilitation and recovery strategies. Over time, the collaboration aims to also build the capability to predict the risk of player injuries before they happen.