So many data points will need to be analyzed in the ME/CFS Severely Ill-BIG DATA Study—literally millions and millions—that we are creating a unique computer program to analyze it all. This new program will be able to process and compare the huge amount of data to find the biological abnormalities that the 20 severely ill patient subjects have in common and compare them with control subjects. It truly is a “BIG DATA” study. This system will be developed by Wenzhong Xiao and his teams at Harvard University and Stanford University.
We hope to then test for the same abnormalities in patients with other diseases and ME/CFS patients who have moderate or even mild cases of ME/CFS. Our systematic, step-by-step process is with the goal of identifying diagnostic biomarkers and targets for treatments.
With an expanded data platform, we will be able to ask and answer the following questions (and many others):
- How do ME/CFS patients’ particular biological test results compare with or differ from healthy people and with people with other diseases?
- Is there a biological footprint for ME/CFS patients, are there defined subsets, and how do they compare to healthy people or people with other diseases?
- Will some treatments for other diseases of similar symptoms also work on ME/CFS?
An added benefit of this computer program is that the patients’ de-identified data will be stored as quickly as possible in a format that can be openly shared with other researchers to test their hypotheses, which will expand the scope and impact of the original study. Our aim is to make this useful to as many scientists as possible.
Check out these presentation slides about the data mining process we’ll be doing.