To expand its reach overseas and add new features to its population-health management platform, HealtheIntent, Cerner is using cloud-based services from Amazon Web Services.
As providers increasingly assume financial risk for patient populations, Cerner’s goal is to develop analytical tools and databases that will help its customers, primarily providers, succeed with reimbursement arrangements in which they assume financial risk for patient populations. In addition to sharing data for care coordination among providers, this also includes strategies to help consumers adopt healthy lifestyles.
That is why Cerner began moving some of HealtheIntent’s footprint to AWS two years ago. “We were looking for not only faster ways to speed innovation but also ways to connect across industries, connect with consumers and connect in different ways,” Ryan Hamilton, senior vice president of population health at Cerner, says.
Cerner is not alone. AWS has been actively courting healthcare customers, which now include providers, insurers, researchers, and the Centers for Disease Control and Prevention in addition to technology companies. Some examples include Medsphere Systems, which is migrating its cloud-based EHR and population health software to AWS, and providers such as the Cleveland Clinic and MedStar Health.
Hamilton spoke about the relationship between Cerner and AWS at a summit open to all industry sectors in San Francisco on April 4. The one-day meeting was one of numerous educational events AWS plans to host this year to promote its cloud-based services, including its products in artificial intelligence, such as SageMaker, a machine learning toolset that AWS says helps “everyday developers” build and train predictive models.
“Healthcare is going to be an industry that is elevated and made better by machine learning and artificial intelligence,” says Mark Johnston, director of global business development for healthcare and life sciences at AWS. Using AWS, providers and other healthcare entities can dive into the entire advanced analytics process—from ingesting and managing data to applying AI-based model-building and training techniques, he adds.
Johnston sees a role for AWS in healthcare not only as a purveyor of AI toolsets but also as an integrator of patient data. “Looking ahead, AWS is interested in how we can work with longitudinal health records to leverage them for population health and analysis efforts. It’s possible for the cloud to act as a permanent home for all patient records and enable the shift away from event-based records to a more holistic view of patient health, supporting value-based care initiatives.”
For example, care coordination among providers, such as through health information exchanges, would be easier to do if lab results and other types of clinical information are stored in a cloud environment, he says.
As far as Cerner’s relationship with AWS, the first step was moving disaster recovery for HealtheIntent to AWS. Cerner also launched HealtheIntent in Canada and Australia using cloud-based services from AWS, Hamilton says. Going forward, the company plans to evaluate whether to use AWS hosting services whenever it launches HealtheIntent in a new global region, he added.
Beyond those cases, Cerner is interested in deploying AWS’ products and services in two ways:
- To help its customers develop new predictive algorithms using AI tools, such as SageMaker.
- To integrate data from Cerner’s customers with data from AWS customers in other industries, such as consumer devices or retail, to facilitate population health management.
For example, Cerner and AWS created HealtheDataLab, which is a product for clinical researchers and data scientists. “We wanted to give them a way in one click to say, ‘I want to create a new model,’” Hamilton says.
This is how it works: Using Amazon’s cloud infrastructure, Cerner creates a dataset of de-identified and encrypted data for each customer’s specific project, managing what data the researchers have permission to see. Cerner’s customers then use SageMaker to build their predictive models and test them. The setup also enables researchers from multiple organizations to collaborate easily, he said.
Cerner also provides a way to integrate the new models into Cerner’s electronic health record, Millennium, and HealtheIntent.
What AWS has done is make machine learning accessible to software engineers by automating the “really, hard complex stuff,” he says. “You don’t have to understand the math behind the training models.”
Cerner also wants to combine patient data from its customers with data from entities outside the provider realm to help consumers lead healthy lives. With permission of individual consumers, the goal is to link data together “to make their lives easier,” he says.
Hamilton says Cerner is exploring such cross-sector collaboration, but it is not yet ready to disclose the details of specific endeavors. In explaining the general concept, however, Hamilton said, “You have to think about what role does retail play in helping people live better lives and manage their conditions? What role does transportation play in doing that? Consumer products—things like Alexa (Amazon’s intelligent digital assistant)?”
Register or login for access to this item and much more
All Health Data Management content is archived after seven days.
Community members receive:
- All recent and archived articles
- Conference offers and updates
- A full menu of enewsletter options
- Web seminars, white papers, ebooks
Already have an account? Log In
Don't have an account? Register for Free Unlimited Access