Algorithm Contest Aims To Predict Health Problems

databuff writes "The April 4 launch of the $3 million Heritage Health Prize has been announced by the Heritage Provider Network, a network of doctors. The competition challenges data hackers to build algorithms that predict who will go to the hospital in the next year, so that preventative action can be taken. An algorithm might find that somebody with diabetes, hypertension and high cholesterol is a 90 per cent risk for hospitalization. Knowing this, it might be cheaper for an HMO to enroll them in an exercise program now rather than pay the likely hospital bill. The competition takes the same approach as the $1 million Netflix Prize, but solves a far more significant problem."

Comments

Re:Good idea, hard to implement

[damn_registrars]

the data is not centralized

Actually a solid argument could be made that the data is centralized, you just don't have access to it because your insurance company makes more money by not allowing you to access it. Insurance companies have plenty of centralized data on plenty of people in this country; enough to make very solid models - particularly models for the types of people that the insurance companies are most concerned about.

If you could get the data from just one big insurance company or HMO - like perhaps the one that is advertising on this story - you could get plenty of data to build your algorithm. You just have to convince them that you are worthy of access to it (even if it has the personal identifiers removed).