Amazon looking to mine patient records to more accurately diagnose diseases

Amazon building

As part of its efforts to push deeper into the healthcare market, Amazon has launched a project to mine data from electronic medical records.

The company’s latest offering, called Amazon Comprehend Medical, allows developers to “process unstructured medical text and identify information such as patient diagnosis, treatments, dosages, symptoms and signs, and more,” according to a blog post.

The company’s senior leader in healthcare and AI, Taha Kass-Hout, told the Wall Street Journal that internal tests showed that the software performed as good or better than other published efforts to extract data on patients’ medical conditions, lab orders and procedures.

Amazon said the reason it got into this space is to help speed up the process of making sense of health data, which isn’t usually stored in ways that computers can understand and analyze.

“The majority of health and patient data is stored today as unstructured medical text, such as medical notes, prescriptions, audio interview transcripts, and pathology and radiology reports,” the blog post reads. “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.”

Amazon is also teaming up with Fred Hutchinson Cancer Research Center in Seattle to apply machine learning to its data sets in a bid to prevent and cure cancers. The company aims to use its technology to evaluate “millions of clinical notes to extract and index medical conditions,” and — together with its partners such as Roche — turn them into actionable insights.

For what it’s worth, Amazon is not the only one looking to leverage modern technologies in healthcare. UnitedHealth Group’s Optum is already in this space, and so are other major tech companies like Apple and Alphabet (Google).