- Amazon confirmed it is developing a new HIPAA-eligible machine learning service that enables developers to analyze patient EHRs to identify information including patient diagnoses, treatments, dosages, symptoms, and signs in a Tuesday blog post.
The tool allows users to process unstructured medical text and is designed to improve clinical decision support for healthcare providers. The service can also help providers, insurers, researchers, clinical trial investigators, and biotech and pharmaceutical companies streamline revenue cycle management and clinical trials management.
Developers can use the tool to identify key common types of medical data including medical conditions, anatomic terms, medications, details of medical tests, treatments, and procedures.
Amazon aims to ultimately leverage the tool to allow patients to manage their own health, proactively schedule visits, and make informed decisions about their own care.
In addition to patient EHRs, the tool can also analyze unstructured text in clinical trial reports and doctors’ notes.
In the blog post, Amazon confirmed it is already working closely with Seattle’s Fred Hutchinson Cancer Research Center to apply the service to cancer care.
Comprehend Medical is helping providers identify patients for clinical trials who may benefit from specific cancer therapies by reading information in patient EHRs.
“Curing cancer is, inherently, an issue of time,” said Fred Hutchinson Cancer Research Center CIO Matthew Trunnell. “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,” Trunnell continued.
So far, the cancer treatment center has evaluated millions of clinical notes to extract and index medical conditions, medications, and choice of cancer therapeutic options to significantly reduce the time associated with processing each patient health record.
“Amazon Comprehend Medical will reduce this time burden from hours per record to seconds,” Trunnell said. “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.”
Amazon has also been previewing the service with Roche Diagnostics.
“Roche’s NAVIFY decision support portfolio provides solutions that accelerate research and enable personalized healthcare. With petabytes of unstructured data being generated in hospital systems every day, our goal is to take this information and convert it into useful insights that can be efficiently accessed and understood,” said Roche Diagnostics Information Solutions Director of Software Engineering Anish Kejariwal.
“Amazon Comprehend Medical provides the functionality to help us with quickly extracting and structuring information from medical documents, so that we can build a comprehensive, longitudinal view of patients, and enable both decision support and population analytics,” Kejariwal added.
This announcement follows a 2017 report from CNBC that revealed a major Cerner and Amazon partnership was potentially in the works.
Rumors of the potential partnership signaled that Amazon planned to enter the healthcare sector.
In August, Amazon joined Google, Microsoft, IBM, Salesforce, and Oracle to state their commitment to advancing healthcare interoperability and health data exchange through artificial intelligence (AI) and the cloud.
The joint statement served as a more concrete indicator of Amazon’s intention to expand into healthcare.
“We are jointly committed to removing barriers for the adoption of technologies for healthcare interoperability, particularly those that are enabled through the cloud and AI,” wrote the tech giants in the letter. “We share the common quest to unlock the potential in healthcare data, to deliver better outcomes at lower costs.”
Researchers at Google are also already working to leverage data within patient EHRs to improve care.
In January 2018, researchers at Google teamed up with researchers at the University of California San Francisco, Stanford University, and University of Chicago Medicine to use the entire patient EHR for more accurate predictive analytics.
The tech giant’s study demonstrated that deep learning can produce valid predictions across a variety of clinical problems and health outcomes.