Donate to Science & Enterprise

S&E on Mastodon

S&E on LinkedIn

S&E on Flipboard

Please share Science & Enterprise

Federal Agency Holds A.I.-Health Outcomes Challenge

Artificial intelligence graphic

(Gerd Altmann, Pixabay)

29 Mar. 2019. The U.S. agency directing Medicare and Medicaid is sponsoring a challenge competition to spur development of artificial intelligence to predict health care outcomes. Centers for Medicare and Medicaid Services, or CMS, an agency of the U.S. Department of Health and Human Services, says the competition has a total prize purse of $1.65 million, with support from American Academy of Family Physicians and Arnold Ventures LLC, formerly the Laura and John Arnold Foundation.

The CMS Artificial Intelligence Health Outcomes Challenge aims to provide better tools for health care providers for predicting the results of their work in hospitals and nursing facilities. Among those outcomes are adverse consequences to patients and unplanned readmissions that drive up costs for patients and facilities. Participants in the competition will be given access to large data sets, including hospital and professional services claims as raw material.

CMS is seeking solutions that improve delivery of care in health facilities and home visits to Medicare beneficiaries. The models developed by challenge participants are also expected to inspire further innovations in health care delivery that offer better measures and improve health care quality. Results from the challenge should provide algorithms for predicting outcomes from Medicare fee-for-service data, as well as explain predictions from machine learning and neural networks to clinicians delivering health care services to patients.

“For artificial intelligence to be successful in health care,” says CMS Administrator Seema Verma in an agency statement, “it must not only enhance the predictive ability of illnesses and diseases, but also enable providers to focus more time with patients. The power of artificial intelligence will truly be unleashed when providers understand and trust the data and predictions.”

The competition is structured into 3 rounds:

A launch stage, or stage 0, where all applicants submit their proposals at the challenge web site: ai.cms.gov. From that initial stage, judges will select 20 semi-finalists advancing to…

Stage 1, where participants will design and demonstrate their solutions using Medicare claims data. From this round, 5 finalists will be selected, each receiving an $80,000 prize and eligible to take part in …

Stage 2, where finalists can request further data from CMS to refine their solutions, and compete for a $1 million grand prize and $250,000 second prize.

The entire competition is expected to take about 1 year. The launch stage deadline for submissions is 18 June 2019, while stage 1 will take place during the summer and fall, and stage 2 will occur in the winter of 2019 and spring of 2020. CMS says the dates are subject to change.

More from Science & Enterprise:

*     *     *

1 comment to Federal Agency Holds A.I.-Health Outcomes Challenge