AWS announces generative A.I. tool to save doctors time on paperwork

Share

Amazon Web Services (AWS) has introduced a new service called AWS HealthScribe, specifically designed for health-care software providers. This innovative service utilizes generative artificial intelligence and speech recognition to automatically generate clinical documentation.

The primary goal of AWS HealthScribe is to save valuable time for health-care workers by providing AI-generated transcripts and summaries of patient visits. These generated records can then be seamlessly integrated into the electronic health record system. Notably, the service can also identify important medical terms, medications, and other key details from the transcripts. Physicians have the option to review and cross-check each line of the AI-generated text with the original transcript.

Clinical documentation has long been a significant challenge for doctors and nurses, with studies revealing that they spend excessive hours on administrative tasks. For instance, a study funded by the American Medical Association highlighted that physicians typically spent two additional hours on administrative work for every hour spent with a patient. Moreover, they often devoted an extra one to two hours of “pajama time,” referring to clerical work outside of regular working hours.

In response to this issue, various companies, including Microsoft’s Nuance Communications and now AWS, have been actively working on developing solutions to alleviate this administrative burden. AWS HealthScribe aims to provide an efficient and AI-driven approach to streamline clinical documentation and ease the workload for health-care professionals.

“It is clear that generative AI has the power to transform the health-care and life sciences industry in many ways”

Swami Sivasubramanian, AWS’s vice president of database, analytics and machine-learning services said at during a keynote speech at AWS Summit New York Wednesday.

Image Source – AWD

In March, Microsoft’s Nuance unveiled DAX Express, a generative clinical notes application that shares similarities with AWS HealthScribe. Like HealthScribe, DAX Express uses AI to automatically generate clinical notes shortly after a patient visit. The application can record real-time conversations between doctors and patients and then swiftly create a draft of the clinical note by leveraging a combination of existing AI technology and OpenAI’s latest model, GPT-4.

Both AWS HealthScribe and DAX Express provide physicians with the option to review the AI-generated notes before entering them into the electronic health record system, ensuring accuracy and control over the documentation.

AWS HealthScribe is built on Amazon Bedrock, Amazon’s service designed for creating generative AI applications. The service is compliant with the Health Insurance Portability and Accountability Act (HIPAA) and does not retain any customer information. Moreover, customers have the flexibility to choose where they want to store their clinical documentation.

Regarding pricing, AWS HealthScribe operates on a pay-as-you-go model, with customers being charged based on the number of seconds of audio processed per month.

AWS has reported that several organizations are already using HealthScribe, including 3M Health Information Systems, a software company. Detlef Koll, 3M’s vice president of global R&D, expressed satisfaction with the technology, emphasizing that it does not act as decision support or alter the care provided to patients. 3M and AWS have been collaborating since the previous fall to responsibly introduce the technology without compromising documentation quality.

“Technology is an enabler for a solution, it’s not the solution,” Koll told in an interview Wednesday.

The initial focus of AWS HealthScribe was on serving the needs of general medicine and orthopedics specialties. The service was made available in a limited private preview capacity starting from a certain date. Tehsin Syed, who holds the position of General Manager of Health AI at AWS, mentioned that the company intends to closely collaborate with its customers to gather feedback and insights. This feedback will be instrumental in refining and updating the underlying technology.

Syed emphasized the importance of being cautious and thorough in the expansion of the service’s access. While there is significant interest from potential users, AWS wants to ensure that the technology works seamlessly at scale and meets the requirements of the users in the most effective manner possible. As a result, AWS will take measured steps to ensure a successful and smooth adoption of AWS Health.

Read more

Recommended For You