AWS Launches Amazon Transcribe Medical

The giant of cloud has released a new machine learning service to quickly create accurate transcriptions from medical consultations between patients and physicians.

Amazon Transcribe Medical enables highly accurate automatic speech recognition (ASR) for the medical industry. The service is trained to understand the terminology and style of clinical language, including drugs.

Transcribe Medical, which is currently available only in English, complies with HIPAA requirements, easily integrates with clinical documentation applications and with any device equipped with a microphone.

Transcribe Medical transcriptions can be automatically sent to a natural language processing service such as Amazon Comprehend Medical. This uses automatic learning to extract relevant medical information from transcriptions, such as medical conditions, drugs, dosage and frequency.

Amazon Transcribe Medical can be used for dictation of notes by physicians, to transcribe the patient’s conversation with the physician (e.g. in the history or recognition of therapy), or to drive a clinical application with the voice.

Transcribe Medical uses state-of-the-art automatic learning models and is able to recognize speech with great accuracy. The service supports conversations between several people or dictation from a single source.

It also provides self-punctuation so that doctors can speak naturally instead of explicitly pronouncing punctuation marks. The transcription will also automatically include normalized numbers (e.g. 50 beats per minute instead of “fifty”) and will automatically insert uppercase letters.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s