Artificial Intelligence (AI) Health Outcomes Challenge

AI Health Outcomes Challenge logo

The CMS Artificial Intelligence (AI) Health Outcomes Challenge is an opportunity for innovators to demonstrate how AI tools – such as deep learning and neural networks – can be used to predict unplanned hospital and skilled nursing facility admissions and adverse events.

Partnering with the American Academy of Family Physicians and Arnold Ventures, the CMS AI Health Outcomes Challenge will engage with innovators from all sectors – not just from healthcare – to harness AI solutions to predict health outcomes for potential use in CMS Innovation Center innovative payment and service delivery models.

Challenge Objectives

  1. Use AI/deep learning methodologies to predict unplanned hospital and SNF admissions and adverse events within 30 days for Medicare beneficiaries, based on a data set of Medicare administrative claims data, including Medicare Part A (hospital) and Medicare Part B (professional services).
  2. Develop innovative strategies and methodologies to: explain the AI-derived predictions to front-line clinicians and patients to aid in providing appropriate clinical resources to model participants; and increase use of AI-enhanced data feedback for quality improvement activities among model participants.

Stages

Launch Stage:

  • Opened on March 27, 2019, to the general public. Entrants each completed an online application and submitted a brief slide deck providing information about the submitting entity and their proposed solution.
  • The Launch Stage application period closed June 19, 2019.

Stage 1

CMS announced 25 Participants to advance to Stage 1 on October 30, 2019. The 25 Participants, titles of proposed solutions and geographic locations are listed below:

Participant: Accenture Federal Services
Proposed Solution: Accenture Federal Services AI Challenge
Geographic Location: Arlington, Virginia

 

Participant: Ann Arbor Algorithms Inc.
Proposed Solution: Generalizing Time-to-event Algorithms to Deep Learning-based Prediction for CMS Data
Geographic Location: Sterling Heights, Michigan

 

Participant: Booz Allen Hamilton
Proposed Solution: Booz Allen Launch Stage Submission
Geographic Location: McLean, Virginia

 

Participant: ClosedLoop.ai
Proposed Solution: Healthcare's Data Science Platform
Geographic Location: Austin, Texas

 

Participant: Columbia University Department of Biomedical Informatics
Proposed Solution: The CLinically Explainable Actionable Risk (CLEAR) Model from Columbia University Department of Biomedical Informatics
Geographic Location: New York, New York

 

Participant: CORMAC
Proposed Solution: CORMAC Response to Challenge Questions
Geographic Location: Columbia, Maryland

 

Participant: Deloitte Consulting LLP
Proposed Solution: Further, Faster: The Deloitte Team’s Approach to Harnessing the Power of AI to Improve Health Outcomes
Geographic Location: Arlington, Virginia

 

Participant: Geisinger
Proposed Solution: Reducing Adverse Events and Avoidable Hospital Readmissions by Empowering Clinicians and Patients
Geographic Location: Danville, Pennsylvania

 

Participant: Health Data Analytics Institute
Proposed Solution: HDAI’s Analytic Platform Technology for Healthcare Improvement
Geographic Location: Dedham, Massachusetts

 

Participant: HealthEC, LLC
Proposed Solution: Leveraging Artificial Intelligence to Predict and Improve Health Outcomes, Maximize Quality Improvement, and Reduce Costs
Geographic Location: Edison, New Jersey

 

Participant: Hospital of the University of Pennsylvania
Proposed Solution: The Intelligent Risk Project
Geographic Location: Philadelphia, Pennsylvania

 

Participant: IBM Corporation
Proposed Solution: AI for Explainable Adverse Event Prediction: Empowering Beneficiaries and Providers to Improve Health Outcomes
Geographic Location: Yorktown, New York

 

Participant: Innovative Decisions Inc. (IDI)
Proposed Solution: Multi-Modeling with Augmented Datasets for Positive Health Outcomes (MADPHO)
Geographic Location: Vienna, Virginia

 

Participant: Jefferson Health
Proposed Solution: Using AI to Improve Medicare Population Health, Optimize Ambulatory Scheduling, and Reduce Adverse Events at Hospitals
Geographic Location: Philadelphia, Pennsylvania

 

Participant: KenSci Inc.
Proposed Solution: Assistive Intelligence for Unplanned Admissions and Adverse Events Prediction
Geographic Location: Seattle, Washington

 

Participant: Lightbeam Health Solutions, LLC
Proposed Solution: AI Risk Predictions- preventing hospital, ER and SNF admissions
Geographic Location: Irving, Texas

 

Participant: Mathematica Policy Research, Inc.
Proposed Solution: The CPC+ AI Model by Mathematica
Geographic Location: Princeton, New Jersey

 

Participant: Mayo Clinic
Proposed Solution: Claims-based Learning Framework (CBLF)
Geographic Location: Rochester, Minnesota

 

Participant: Mederrata
Proposed Solution: Boosting medical error and readmission prediction by leveraging Deep Learning, Topological Data Analysis, and Bayesian modeling
Geographic Location: Columbus, Ohio

 

Participant: Merck & Co., Inc.
Proposed Solution: Actionable AI to Prevent Unplanned Admissions and Adverse Events
Geographic Location: Kenilworth, New Jersey

 

Participant: North Carolina State University (NCSU)
Proposed Solution: Multi-Layered Feature Selection and Dynamic Personalized Scoring
Geographic Location: Raleigh, North Carolina

 

Participant: Northrop Grumman Systems Corporation (NGSC)
Proposed Solution: Reducing Patient Risk through Actionable Artificial Intelligence: AI Risk Avoidance System (ARAS)
Geographic Location: Herndon, Virginia

 

Participant: Northwestern Medicine
Proposed Solution: A human-machine solution to enhance delivery of relationship-oriented care
Geographic Location: Chicago, Illinois

 

Participant: Observational Health Data Sciences and Informatics (OHDSI)
Proposed Solution: OHDSI Submission
Geographic Location: New York, New York

 

Participant: University of Virginia Health System
Proposed Solution: Actionable AI
Geographic Location: Charlottesville, Virginia

COVID-19 3-Month Pause

The Centers for Medicare & Medicaid Services (CMS) is seeking to support providers responding to the public health emergency (PHE) 2019 Novel Coronavirus (COVID-19) by temporarily relaxing the requirements for health care providers participating in innovative payment and service delivery models and other initiatives. It is our hope that by relaxing certain initiative requirements, in combination with the other efforts already underway by other federal agencies, we will better support health care providers in directing their resources towards caring for patients, ensuring the safety of staff, and reducing the spread of transmission.

In order to accommodate these current priorities, CMS will temporarily pause the Artificial Intelligence Health Outcomes Challenge (the Challenge), and restart the Challenge on Monday, June 29, 2020. If you’ve already submitted your pretest data results, you will not need to resubmit but you may resubmit if you choose to do so. Please note that in the meantime, the Limited Data Set (LDS) files you received (and all derivative data) are for use in the context of the Challenge only, and such use is subject to the terms of the Data Use Agreement (DUA) that you signed.

In the coming weeks, CMS will distribute a more detailed timeline for the remaining stages of the Challenge. We appreciate your continued participation in the Challenge, and thank you for your patience and dedication as we all work to navigate this unprecedented time. Please let us know if you have any questions or concerns.

Stage 2

CMS will announce more information about Stage 2 at a later date.

 

Learn More

Please visit ai.cms.gov to learn more about the AI Health Outcomes Challenge!

Prizes (subject to change)

Total prizes up to $1.65 million

  • 7 finalists progress to Stage 2 and receive awards of up to $60,000
  • 1 grand prize winner will receive up to $1 million and the runner-up will receive up to $230,000

Additional Information

 

Last updated on:
08/13/2020