The Centers for Medicare and Medicaid Services announced this past Friday that ClosedLoop.ai is the winner of its multistage Artificial Intelligence Health Outcomes Challenge.

WHY IT MATTERS
The challenge developed by the CMS Innovation Center to find new AI-powered approaches to predicting health outcomes for Medicare beneficiaries initially drew more than 300 entries from across all industries, including Accenture, Deloitte, Geisinger, IBM, Mayo Clinic and Merck. These were first winnowed to a top 25 and then to seven finalists.

As the grand prize winner, Austin, Texas-based ClosedLoop.ai will receive up to $1 million in prize money. 

Danville, Pennsylvania-based Geisinger was the runner-up and will receive up to $230,000.

Both organizations were recognized by CMS for their AI and machine learning tools to predict unplanned hospitalizations, skilled nursing facility admissions and adverse events. They each created predictive algorithms as well to identify Medicare beneficiaries at risk of mortality in 12 months.

Special attention was devoted to rooting our sources of algorithmic bias that might affect health disparities, according to CMS. Transparency was prioritized too, with finalists demonstrating how the AI tools could be easily explained to physicians and nurses.

With help from a team of outside AI scientists, CMS subjected the finalists to a rigorous assessment of the accuracy of the algorithms' predictions. Clinicians from the American Academy of Family Physicians reviewed and scored their explainability. Winners were selected by a panel of CMS senior leadership.

"Clinicians are eager to use the latest innovations to better help identify patients at risk, provide higher quality care, and improve health outcomes," said CMS Acting Administrator Liz Richter in a statement. "The use of artificial intelligence has the potential to achieve these aims by providing important information to clinicians that may be helpful in providing higher quality care."

"Our Patient Health Forecasts were key to winning the Challenge. We reimagined the entire concept into a comprehensive and personalized risk forecast that could be delivered directly into a clinical workflow," said ClosedLoop CTO and cofounder Dave DeCaprio in a statement. "Each forecast surfaces key variables and explains precisely how they contribute to a patient’s specific risk."

THE LARGER TREND
The competition, in collaboration with the AAFP and Arnold Ventures, was launched in 2019 with the aim of accelerating development of AI solutions for predicting patient health outcomes for Medicare beneficiaries for potential use by the Innovation Center.

Of $1.65 million in total prizes to participants, Arnold Ventures will contribute up to $300,000 and the AAFP is contributing up to $340,000.

ON THE RECORD
"We are excited about the early successes and great potential of Artificial Intelligence to dramatically improve health outcomes, reduce administrative burden, and create smarter health IT," said American Academy of Family Physicians CEO Shawn Martin in a statement. "We look forward to seeing the winning, and all of the great, solutions in the market."

"Avoidable hospitalizations and skilled nursing facility stays are bad for patients and make our healthcare system costlier and less sustainable for everyone," said Mark Miller, executive vice president of health care at Arnold Ventures. "We are eager to see how the winners of the competition use new data approaches to identify solutions to improve care in Medicare."

"Finding effective ways to improve outcomes and reduce the cost of care is a national imperative," said ClosedLoop CEO Andrew Eye. "The Challenge drove us to improve our capabilities across the board – scalability, accuracy, deep explainability, and ways to address algorithmic bias and fairness."

Twitter: @MikeMiliardHITN
Email the writer: mike.miliard@himssmedia.com
Healthcare IT News is a HIMSS publication.