Amazon launches NLP service to process unstructured text

Register now

A new machine learning service from Amazon Web Services is being offered to process unstructured medical text and identify information such as patient diagnosis, treatments, dosages, and symptoms.

Amazon Comprehend Medical is being touted as a natural language processing service that makes it easy to use machine learning to accurately and quickly extract relevant information from unstructured text, such as medical notes, prescriptions, audio interview transcripts, as well as pathology and radiology reports.

“There are no servers to provision or manage—developers only need to provide unstructured medical text to Comprehend Medical,” wrote Amazon’s Taha Kass-Hout, MD, former FDA chief health informatics officer, and Matt Wood, general manager for deep learning and AI, in a blog post on Tuesday.

“The service will ‘read’ the text and then identify and return the medical information contained within it,” added Kass-Hout and Wood, who noted that the majority of health and patient data is stored today as unstructured medical text. “Comprehend Medical will also highlight protected health information (PHI). There are no models to train and no ML experience is required. And, no data processed by the service is stored or used for training. Through the Comprehend Medical API, these new capabilities can be integrated with existing services and health systems easily. The service is also covered under AWS’s HIPAA eligibility and BAA.

Also See: How Amazon’s digital health moves could affect providers

Amazon also announced that Fred Hutchinson Cancer Research Center in Seattle is using Amazon Comprehend Medical to identify patients for clinical trials who may benefit from specific therapies.

Specifically, the vendor said the center was able to utilize Amazon Comprehend Medical to evaluate millions of clinical notes to extract and index medical conditions, medications, and choice of cancer therapeutic options, while significantly reducing the time required to process each document.

“Curing cancer is, inherently, an issue of time,” said Matthew Trunnell, chief information officer at Fred Hutchinson Cancer Research Center. “The process of developing clinical trials and connecting them with the right patients requires research teams to sift through and label mountains of unstructured medical record data. 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 when they need it so they can find actionable insights to advance lifesaving therapies for patients.”

For reprint and licensing requests for this article, click here.