National CRE News In Your Inbox.
Sign up for Connect emails to stay informed with CRE stories that are 150 words or less.
Amazon Launches Venture to Mine Electronic Medical Records
Amazon has launched a project to mine data from electronic medical records, according to a blog post. Introduced as Amazon Comprehend Medical, it “allows developers to process unstructured medical text, and identify information such as patient diagnosis, treatments, dosages, symptoms and signs, and more.”
Amazon’s 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, according to Taha Kass-Hout, the Seattle-based company’s senior leader in healthcare and artificial intelligence.
Amazon also confirmed that it’s partnering with Fred Hutchinson Cancer Research Center in Seattle to apply machine-learning to its data sets in an effort to prevent and cure cancers. The tech firm is working with the health provider to evaluate “millions of clinical notes to extract and index medical conditions.”
While industry experts predicted that Amazon would eventually compete directly with EMR companies, including Cerner and AllScripts, it seems more likely it’ll work hand-in-hand with them to provide population health services and clinical trial support.
With Amazon Comprehend Medical, the company will compete directly with UnitedHealth Group’s Optum, which already operates in the healthcare data analytics space, as well as tech rivals Apple and Google-parent company Alphabet.
In the blog post, Amazon said it hopes to 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 company said. “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.”
For questions, comments or concerns, please contact Jennifer Duell Popovec
