Explorys was founded in 2009 as an innovation spinoff from Cleveland Clinic. Explorys addresses the national imperative to leverage BIG DATA in healthcare for the improvement of medicine and delivery of care.
BIG DATA ANALYSIS: KILLER APP!!
HOW THE MEDICAL DATABASE IS ACCUMULATED FOR ANALYSIS
DEFINITION (on above diagram)
Now, you have this huge accumlation of medical data. It is worth NOTHING, until it is intelligently analyzed. That where the new medial specialty of MEDICAL INFOMATICS comes into play, converting these medical databases to useful medical uses.
In information technology, big data is a loosely-defined term used to describe data sets so large and complex that they become awkward to work with using on-hand database management tools. Difficulties include capture, storage, search, sharing, analysis, and visualization.
Presently, in the digitalization of medicine, big data and cloud databases are formed, perhaps in a “Google Cloud“, or a “Microsoft Cloud“, and supercomputers are analyziing the data in the cloud.
One of the converging factors, spoken about in the Convergence page, is “Big Data”. We could not even think about Big Data if we did not have the huge asset of “Big Computers”.That is because it takes many computers to analyze the enormous amounts of date collected from all the collection systems which we now possess. Information, now, is digitalized, and easily collected, and analyzed with the aid of computers. iIn seconds.Formerly, with written records, this could not be done very easily, and would take years.
There is a new Subspecialty of Medical Informatics just born in late 2011. The approved Subspecialty of “Medical Informatics”, which, undoubtedly, will become adept at interpreting the huge data clouds.
Now, that we have this data in the cloud, what do we do with it? The approach to this huge amount of date is best performed with the “Science of Informatics”, the increasingly prominent study of this new Subspecialty:
“The science of informatics drives innovation that is defining future approaches to information and knowledge management in biomedical research, clinical care, and public health. Informatics researchers develop, introduce, and evaluate new biomedically motivated methods in areas as diverse as data mining (deriving new knowledge from large databases), natural language or text processing, cognitive science, human interface design, decision support, databases, and algorithms for analyzing large amounts of data generated in public health, clinical research, or genomics/proteomics. The science of informatics is inherently interdisciplinary, drawing on (and contributing to) a large number of other component fields, including computer science, decision science, information science, management science, cognitive science, and organizational theory.”
Now, bascially, when one comes down to it, a doctor is a decision maker. And what does he based his decision on? Data, and experience, and intuition. On this page, we will deal with the data variable.
Now, we will have increasing huge, insatiable data assembling devices, including
1) wireless biosensors
2) genome sequencing
On a small scale, the doctor can gather this information, and with the aid of experience and intuition, make a decision. But now, there is an ability to collect HUGE sets of data, based on large number of databases, and doctor decisions, and construct alogrithms on how to treat a certain disease or situation.
Datastores such as Data.gov provide immensely rich sets of data on topics like patient outcomes, clinical trials, and population epidemiology, empowering developers and engineers to create tools that can derive insight and reveal trends in the data.
A Medical Infomatic Subspecialist will take on a increasingly important role as a consultant in certain clinical situations, a role which will undoubtedly increase in time.
Currently, there are massive amounts of healthcare information in cyberspace, ranging from government and business maintained resources to Web 2.0 user-generated content, e.g. wikis, blogs, online healthcare discussion groups, etc. However, all this information is not being effectively leveraged because 1) the sources are diverse in syntax, semantics and structural representation; and 2) they are fragmented across an enormously distributed network.