CMS Contest Gets Real About Artificial Intelligence
By Mandy Roth
How can AI tools—such as deep learning and neural networks—be used to predict unplanned hospital and skilled nursing facility admissions and adverse events? In the Artificial Intelligence (AI) Health Outcomes Challenge, the Centers for Medicare & Medicaid Services (CMS) is dangling up to $1.65 million in prize money to the innovators who can figure it out.
Six hospitals and health systems are among the 25 participants who were selected from a field of more than 300 submissions. The ultimate goal is to harness AI solutions to predict health outcomes for healthcare providers and clinicians, as well as potential use in CMS Innovation Center innovative payment and service delivery models.
“Artificial Intelligence is a vehicle that can help drive our system to value—proven to reduce out-of-pocket costs and improve quality,” said CMS Administrator Seema Verma in a news release. “It holds the potential to revolutionize healthcare: imagine a doctor being able to predict health outcomes— such as a hospital admission—and to intervene before an illness strikes,” said. “The participants in our AI Challenge demonstrate that such possibilities will soon be within reach.”
The selection committee prioritized applications that offered “explainable artificial intelligence solutions to help front-line clinicians understand and trust AI-driven data feedback to target scarce resources and improve the quality of care,” according to the release.
The six hospitals and health systems selected to participate, along with the names of their submissions, include:
- Geisinger in Danville, Pennsylvania: Reducing Adverse Events and Avoidable Hospital Readmissions by Empowering Clinicians and Patients
- Hospital of the University of Pennsylvania, Philadelphia: The Intelligent Risk Project
- Jefferson Health, Philadelphia: Using AI to Improve Medicare Population Health, Optimize Ambulatory Scheduling, and Reduce Adverse Events at Hospitals
- Mayo Clinic, Rochester, Minnesota: Claims-Based Learning Framework
- Northwestern Medicine, Chicago: A Human-Machine Solution to Enhance Delivery of Relationship-Oriented Care
- University of Virginia Health, Charlottesville, Virginia: Actionable AI
The challenge was designed to engage innovators from all sectors‒not just healthcare. A complete list of participants is posted on the CMS website.
The CMS AI Health Outcomes Challenge was launched in March 2019 by the CMS Innovation Center in collaboration with the American Academy of Family Physicians and Arnold Ventures. The 25 participants were announced yesterday.
During this next stage, the 25 participating teams will design and test their proposed solution using certain Medicare claims data sets. Up to seven finalists will be announced next spring and advance to the second stage of the contest, along with an award of up to $60,000. These finalists will be able to request additional Medicare claims data to refine their solutions.
The grand prize winner will be announced next year and receive up to a million dollars. The runner up will receive up to $230,000.
Mandy Roth is the innovations editor at HealthLeaders.