Amazon’s Amazon Web Services (AWS) division launched Amazon Transcribe Medical, a HIPAA-eligible, machine learning-powered medical transcription service that uses automatic speech recognition applications designed to convert clinician and patient speech to text.
It can automatically and accurately transcribe physicians’ dictations, as well as their conversations with patients. Moreover, the service enables automatic punctuation and capitalization, allowing physicians to speak naturally when transcribing voice notes.
According to an Amazon press release, voice solutions built on top of Amazon Transcribe Medical will be able to produce accurate medical transcripts of dictation and conversational speech in the medical domain.
In clinical documentation workflow, physicians can more efficiently capture medical notes without distraction during patient engagements. In addition, physicians can leverage the transcribed notes after patient encounters to more quickly enter medical data into electronic health record (EHR) systems.
“Anything that can make it easier for clinicians to do their documentation in real time, at the point of care, is a welcome advance. If Amazon, and others, can use their vast potential for machine learning to improve the accuracy and precision of turning sound into text, it will make it much easier to use additional processing to convert that text to clinical data. The next challenge will be to extract computable clinical data from that text to support clinical decisions, quality improvement, reporting and the management of chronic diseases—especially as the population ages,” says David Lareau, CEO of Medicomp Systems, located in Washington, D.C., which provides physician-driven, point-of-care solutions that fix EHRs.