Managing Big Data
Personalized medical treatment is growing in popularity with many healthcare organizations - including Mayo Clinic. As reported in the June issue of CAP TODAY, personalized medicine compiles and analyzes patients’ genetic code, utilizing big data to better diagnose, predict, and treat disease.
"We generated 90 trillion base pairs of sequence last year," says Eric Wieben, Ph.D., director of Mayo’s Medical Genome Facility in Rochester, Minn. "Gathering big piles of data is the easy part. It’s trying to transform the data into knowledge that’s the hard part."
According to Dr. Wieben, "Right now, the different research groups [within Mayo] all have their own solutions, ranging from fairly sophisticated database applications to Excel spreadsheets and things that are even less capable than that. It’s more in silos than what we’d like from an institutional perspective."
To consolidate these solutions, Mayo's health system is implementing Oracle’s Oracle Health Sciences Translational Research Center platform. The Oracle solution encompasses a growing list of more than 1,200 entities and 11,000 attributes that cover clinical, operational, research, and omics domains. With the Oracle solution, the institution’s information technology experts must run tests to ensure the information is loaded correctly and that the platform can be searched and the information retrieved without error.
"Since these [data sets] ultimately will be used for lots of different purposes, our IT folks want to go through lots of error-checking routines and do this in a way that preserves the integrity of the data,” said Dr. Wieben.
He also added that the goal is to have the solution available for general use by the end of the year—two years after the project began.
Read the full article for more information on Mayo's use with the Oracle solution.