Big Data

Big data means radically changing the way of thinking, both in scientific research and in other applications. It is not about using large archives, with thousands or millions of people involved, data on variables identified “a priori” and sorted into epidemiological databases. Those already exist and medicine has been using them for long time. Big data, on the other hand, means gathering information about everything, even on aspects that do not seem important at the moment. Apart from clinical records, administrative data on hospital admissions, or structured questionnaires on eating habits, we also take under consideration the environment in which the patient lives, the infrastructure of the territory and various data from the apps currently available on smartphones. On top of that, data from the “-omic” tests will provide information on all variations, genetic or epigenetic, all metabolites and all the bacteria present in our body.

A cultural and methodological revolution. No more limits on information, but a wide data gathering, even if some of them seem irrelevant for the time being. Normal medical and biological data can be added to the geographical location where a person lives, the economy of his city, the weather, his cultural interests, his leisure time and millions of other information. Messy archives perhaps collected in completely different manner, on different occasions. In classical thinking, they would be useless. Instead, “grinding” them according to Big Data procedures, could bring forward completely new ideas.

Following that pathway, we will form a well-defined great picture, crucial for a “tailor-made” medical approach. From an epidemiological point of view, it is no longer important analysing huge populations, having few variables for each subject, but processing millions of information even for a single study subject (the so-called “N-of-1 study”).