AHRQ Announces New Challenge Competition To Develop Predictive Analytics on Hospital Inpatient Data
The Agency for Healthcare Research and Quality (AHRQ) today announced a challenge competition to explore how predictive analytics may be applied to existing databases to forecast future trends in healthcare utilization and spending.
Predictive analytics are complex statistical techniques that analyze and learn from current and historical facts to make educated predictions about future events. While the technique has been used extensively in fields ranging from business to manufacturing, AHRQ has identified predictive analytics’ potential to help policymakers, researchers and others anticipate and plan for emerging needs in healthcare.
“Healthcare decision makers need better access to estimates that define current and future healthcare issues,” said Gopal Khanna, M.B.A., 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.”
The agency’s new challenge competition – “Bringing Predictive Analytics to Healthcare Challenge” – is the third in an AHRQ series to encourage the development of innovative tools to tackle healthcare problems. To date, AHRQ has announced the winner of the first challenge, the “AHRQ Step Up App Challenge,” and is currently receiving applications for the second challenge, the “AHRQ Visualization Resources of Community-Level Social Determinants of Health Challenge.”
In the newest challenge, applicants will be asked to use predictive analytics and related methods to estimate hospital inpatient utilization for selected counties in the U.S. for 2017. They 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.
Ultimately, challenge judges will require a brief report describing the model, methods, analytic approach and rationale for the estimates so that they may try to replicate the results. Programming code, Excel spreadsheets, analytic files and other supporting documentation should be submitted. The winners will be awarded a total prize pool of $225,000.
Building on AHRQ’s current data infrastructure, applicants will receive access to customized analytic files that includes information on hospital inpatient discharges for years 2011 to 2016. Participants may supplement their access to AHRQ data, at their option, by using any free, publicly available data sources, such as the Area Health Resources File or data provided by the U.S. Census Bureau.
Applications will be evaluated based on two areas: reliability and validity. Judges will determine if the submitted model or method predicts the actual utilization rates for 2017 and how well the model performs in an earlier year of data.
Participants may apply independently or collaborate with others, including health information technology developers, healthcare providers, artificial or machine intelligence scientists or others with appropriate expertise.
“We are very excited to reach new audiences with this challenge such as the social science and technical innovator communities,” Khanna said. “These are audiences not traditionally associated with AHRQ, and I encourage all teams to expand their research horizons and find unique ways to use social determinants of health data in their submissions.”
The deadline to apply is June 28, and the winner will be selected by July 31. The first place winner will receive $100,000, second place will be awarded $75,000 and $50,000 for third place. Visit the “Bringing Predictive Analytics to Healthcare” website for more information.
Page originally created March 2019