Posted On: May 14, 2021

Amazon Transcribe Medical is a HIPAA-eligible automatic speech recognition (ASR) service that makes it easy for developers to add speech-to-text capabilities to healthcare and life science applications. We are pleased to launch support for the automatic identification of protected health information (PHI) in your medical transcriptions feature for batch processing. With automatic PHI identification, customers can now reduce the cost, time, and effort spend on identifying PHI content from both live audio streams and static recordings. PHI entities are labeled clearly with each output transcript, making it convenient to build additional downstream processing for a variety of purposes, such as redaction prior to text analytics.

Common use cases for Amazon Transcribe Medical include helping clinicians transcribe their patient notes to enhance overall clinical documentation efficiency, converting recorded calls into text for drug-safety monitoring (pharmacovigilance), or subtitling for telehealth sessions. Starting today, Amazon Transcribe Medical can identify PHI that was disclosed during live or pre-recorded conversations within the transcription outputs.

Transcribe Medical is covered under AWS’s HIPAA eligibility and BAA which requires BAA customers to encrypt all PHI at rest and in transit when in use. Automatic PHI identification is now available for both streaming and batch processing at no additional charge and in all regions where Amazon Transcribe Medical operates. Try it out in our service console or learn more by visiting Amazon Transcribe Medical’s technical documentation.