AHRQ launches Bringing Predictive Analytics to Healthcare Challenge

The Agency for Healthcare Research and Quality has issued a $225,000 challenge to industry to develop predictive analytics to estimate important hospital utilization metrics.

The prime task for participants in AHRQ’s Bringing Predictive Analytics to Healthcare Challenge will be to use analytics to show hospital inpatient utilization for selected counties in the U.S. for 2017.

Participants also “must also provide the predicted values of the number of hospital inpatient discharges and the average length of stay for selected U.S. counties in 2016 by applying the model, methods and analytic approach used to obtain the 2017 estimates.”

Participants in the competition will have access to customized analytic files that include information on hospital inpatient discharges for years 2011 to 2016. They may also supplement the AHRQ provided data by using free, publicly available data sources including the Area Health Resources File or data provided by the U.S. Census Bureau.

“Healthcare decision makers need better access to estimates that define current and future healthcare issues,” says Gopal Khanna, director of AHRQ. “AHRQ’s challenge competition will help demonstrate how predictive analytics can use existing data to provide those kinds of estimates and make new resources available for real-time decisions about policies and use of healthcare resources.”

AHRQ-headquarters-CROP (2).jpg
AHRQ headquarters

Also See: AHRQ issues app challenge for patient-reported outcomes data

The challenge is open to health information technology developers, healthcare providers, artificial intelligence scientists and others with appropriate expertise, who may apply independently or in teaming arrangements.

“Applications will be evaluated based on two broad areas: reliability and validity,” according to AHRQ. “In general, reliability is assessed by how closely the model or method deployed predicts the actual utilization rates for 2017. Validity is assessed by how well the model performs on earlier years of data.”

The first place prize is $100,000, second place will be awarded $75,000 and third place will receive $50,000. The submission deadline is June 28, 2019, with the winners to be announced by July 31, 2019.

Additional information about the challenge is available here.

For reprint and licensing requests for this article, click here.