The new app scans and analyzes "prescriptions, notes, audio interviews and test reports," and collates them in a centralized database. It uses this information to identify and prescribe medication for potential symptoms. The service will be used in many contexts, including clinical trials. The goal of the app is to accelerate recovery processes by eliminating the scrutiny of unnecessary information. The app is completely compliant with the Health Insurance Portability and Accountability Act (HIPAA); all the data is encrypted and Amazon has ensured that it cannot be used without consent by implementing a "key" feature.
"We're able to completely, automatically look inside medical language and identify patient details with incredibly high accuracy," says Matt Wood, GM of artificial intelligence at Amazon Web Services.
The Fred Hutchinson Cancer Research Center in Seattle helped Amazon test the new software. Rival programs didn't measure up, so the software will be officially adopted by the Center. They'll use it primarily to identify patients eligible to participate in drug and research studies.
Matthew Trunnell, the CIO of Fred Hutchinson Cancer Research Center said: "For cancer patients and the researchers dedicated to curing them, time is the limiting resource. 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."
Currently, 60 people at the Center sift through around 500,000 patients' records manually. By adopting this platform, this menial task will largely be automated and streamlined.
Amazon said that "identifying this information today is a manual and time-consuming process, which either requires data entry by high skilled medical experts, or teams of developers writing custom code and rules to try and extract the information automatically."