Healthcare Technology News

August 03, 2023

Say Hello to Effortless Clinical Documentation with AWS HealthScribe

A pressing issue for healthcare professionals is the compilation of clinical documentation after patient-clinician discussions. This critical process ensures compliance, quality measures and reimbursement, but its complexity and multi-step nature often collectively consume valuable time that could be spent attending to additional patients.

While some healthcare software providers currently employ text-to-speech and natural language processing (NLP) to streamline documentation, they have long sought a more transformative solution.

Generative AI fills the gap, seamlessly transforming recorded discussions into concise clinical documentation suitable for Electronic Health Records (EHR). However, integrating multiple AI systems into a unified solution requires substantial engineering resources, making it a complex undertaking. Building these generative AI capabilities demands training or fine-tuning Language Models (LLM), necessitating access to sought-after AI experts, extensive annotated healthcare data, and considerable computational power.

Amazon Web Services has a solution for that.

AWS unveiled AWS HealthScribe, a new HIPAA-eligible service catering to healthcare software providers. This service empowers them to develop clinical applications that use speech recognition and generative AI, effectively saving clinicians time by automating the generation of clinical documentation.

With AWS HealthScribe, healthcare software providers gain access to a single API that automatically generates comprehensive transcripts, extracts vital details like medical terms and medications, and creates summaries from doctor-patient discussions. These clinical notes can then be seamlessly entered into an electronic health record system.

The service leverages Amazon Bedrock to simplify integration and enables healthcare software providers to quickly incorporate generative AI capabilities into their applications, specifically in general medicine and orthopedics specialties, without needing to manage the underlying machine learning infrastructure or train their own healthcare-specific LLMs.

Notably, AWS HealthScribe ensures responsible deployment of AI systems by providing references to the original conversation transcript for each line of generated text, aiding physicians in reviewing clinical notes before entering them into the EHR. The service prioritizes security and privacy, allowing customers to retain control over data storage, encrypting data in transit and at rest, and ensuring that inputs and outputs from the service are not used for model training.

“Our healthcare customers and partners tell us they want to spend more time creating innovative clinical care and research solutions for their patients while spending less time building, maintaining, and operating foundational health data capabilities,” said Bratin Saha, Vice President of Machine Learning and AI services at AWS. “That is why AWS has invested in building a portfolio of AI-powered, high-performance, and population-scale health applications so that clinicians can spend more time with the patients during the face-to-face or telehealth visits.”

Among the customers and partners is 3M Health Information Systems, whose various M*Modal speech understanding, conversational and ambient AI solutions are currently used by more than 300,000 clinicians. Here is what 3M HIS President Garri Garrison said about HealthScribe.

“3M HIS is collaborating with AWS to bring conversational and generative AI directly into clinical documentation workflows,” said Garrison. “AWS HealthScribe will be a core component of our clinician applications to help expedite, refine and scale the delivery of 3M's ambient clinical documentation and virtual assistant solutions.”

AWS HealthScribe joins an array of purpose-built health services, further contributing to the transformation of healthcare and life sciences industries by facilitating data-driven clinical decisions, advancing precision medicine, and reducing the cost of care.

Edited by Alex Passett
Get stories like this delivered straight to your inbox. [Free eNews Subscription]

FREE eNewsletter

Click here to receive your targeted Healthcare Technology Community eNewsletter.
[Subscribe Now]