Amazon Introduces Medical Language Processing Capability

Device allows users to process unstructured text, identify information

At the end of 2018, Amazon excitedly announced Amazon Comprehend Medical, a HIPAA-compliant device that allows developers to process unstructured medical text and identify information such as patient diagnosis, treatments, dosages, symptoms and signs, and more.

Between medical notes, prescriptions, audio interview transcripts, and pathology and radiology reports, the majority of today’s medical information is stored as unstructured text, and requires a time-consuming manual processing. It can require either data entry by skilled medical experts, or teams of developers writing custom code and rules to try and extract the information automatically.

Amazon Comprehend Medical allows developers to identify the key common types of medical information automatically without the need for large numbers of custom rules. Comprehend Medical can identify medical conditions, anatomical terminology, medications, details of medical tests, treatments, and procedures. Ultimately, this richness of information may be able to one day help consumers with managing their own health, including medication management, proactively scheduling care visits, or empowering them to make informed decisions about their health and eligibility.

“Curing cancer is, inherently, an issue of time,” said Matthew Trunnell, Chief Information Officer, Fred Hutchinson Cancer Research Center. “For cancer patients and the researchers dedicated to curing them, time is the limiting resource. Amazon Comprehend Medical will reduce this time burden from hours per record to seconds. This is a vital step toward getting researchers rapid access to the information they need.”