MIT researchers aim to take the human element out of big-data analysis, with a new system that not only searches for patterns but designs the feature set, too. To test the first prototype of their system, they enrolled it in three data science competitions, in which it competed against human teams to find predictive patterns in unfamiliar data sets.
This article is pretty geeky but the implications are interesting.
We are gathering hordes of data as a byproduct of doing business with computers. It is sometimes called digital exhaust. All this data has the potential to reveal hidden truths about almost everything we do including medicine and dentistry. In theory analyzing this big data could allow us to vastly improve the human condition.
This new approach from MIT automates big data analysis to an even greater extent which should improve the speed and quality of future analysis.
The end result could be a cloud based artificial intelligence application that takes in diagnostic data from an individual and formulates a personalized diagnosis and treatment plan. Personalized down to the exact chemical composition of a medicine based on the genome of the individual, the genome of the pathogens and the results of millions of similar cases.