The Heritage Provider Network has created a $3 million prize for the development of a healthcare predictive model that could save medical costs and improve healthcare.
The goal of the Heritage Health Prize is to develop a predictive algorithm that can identify patients who will be admitted to the hospital within the next year, using historical claims data.
The data mining and analytics contest was announced by Richard Merkin, CEO of the Heritage Provider Network, at last week's Data 2.0 Conference in San Francisco.
Contestants in the challenge will be provided with a data set consisting of medical records of patients covering a specific time period, and will be required to predict who from that patient population went to the hospital during the following year and how long they spent in the hospital. Heritage Provider Network (HPN) will award the $3 million prize to the team with the highest level of predictive accuracy after the two-year competition phase concludes. There will also be six Milestone Prizes totaling $230,000, which are awarded in varying amounts at three intervals during the competition.
More than 71 million individuals in the United States are admitted to hospitals each year, according to the latest survey from the American Hospital Association. Studies have concluded that in 2006 well over $30 billion was spent on unnecessary hospital admissions. HPN hopes the healthcare analytics competition will change that.
The winning team will create an algorithm that predicts how many days a patient will spend in the hospital in the next year. Armed with that information, healthcare providers will be able to develop new care plans and strategies to reach patients before emergencies occur, reducing the number of unnecessary hospitalizations. The result will be to increase the health of patients while decreasing the cost of care. "In short, a winning solution will change health care delivery as we know it from an emphasis on caring for the individual after they get sick to a true health care system," HPN said.
The predictive modeling contest has received interest from a diverse group of participants, including individuals at Google, Accenture, Bank of America, the U.S. Food and Drug Administration and Department of Energy, Britain's National Health Service, Harvard, MIT, Stanford, Oxford, Ben Gurian University, and the Cleveland and Mayo Clinics. Entries have come from as far away as the Ukraine, Poland and Portugal.