Textract, a tool from Amazon's cloud computing arm that uses machine learning to extract text and data from scanned documents, can now be deployed for HIPAA-compliant tasks, Amazon Web Services announced Oct. 10.
The service, released to all AWS customers beginning in May, uses artificial intelligence to "read" documents to compile the most relevant information into lists and databases. Textract can extract data from a variety of complex, typically non-machine readable document types, including hospital claims, patient forms and medical charts.
The new security and privacy updates mean AWS healthcare clients can use Textract across all operations, including those requiring HIPAA-compliant processing and storage of protected health information.
"Healthcare organizations can now use Amazon Textract service to extract medical data from files that previously have been non-machine readable. This brings an opportunity to integrate this data with their electronic health records or other cloud technologies," said Matt Ferrari, CTO of AWS data security provider ClearDATA. "This is just another step forward in increasing the opportunity to use these emerging technologies to improve access to data, get better insights, lower costs and improve patient and member experiences."
Other HIPAA-eligible AWS artificial intelligence services include Amazon Polly, Amazon SageMaker, Amazon Rekognition, Amazon Translate, Amazon Transcribe and Amazon Comprehend.
More articles on AI:
UCSF to launch AI center for radiology technology
VUMC researchers use AI to detect heart disease phenotypes
Healthcare execs are investing in, optimistic about future of AI: Optum report