Big Data & Medicine

Big data analysis can deliver incredible results, but the possibility of misuse must be considered. This is especially true in the field of medical data analysis. Big Data works with anonymous data only, i.e., the data cannot be traced back to people.

Interpolation of laboratory results of cancer patients

At the Institute of Medical Statistics (CeMSIIS) we deal with nearly 6 million lab results of over 2,000 cancer patients. Despite the large scope of this data, they are incomplete and consist of measurements that are either inaccurate or temporally inhomogeneous, i.e. the measurements are carried out at different points of times.

Big data analysis provides strategies on how to proceed with missing and incorrect data. This method is called "interpolation of data". In such cases, it is essential to ensure that the results are used for medical purposes only and do not have any potential disadvantage for patients.