Big Data in Diagnostics (Dx)
With great knowledge comes great responsibility.
Big Data leads us to the former, as long as we can master the quantity of continuous data streams and know how to extract the right one from them. In this respect, the concept of generating large databases in which various trends can be identified and associated with individual patient cases is being pursued in the LifeScience sector. The knowledge in genomics and epigenomics, for example, opens up new possibilities in health management – diagnostics, therapy and prevention can all benefit from this. In addition to the massive volume of data, aspects such as growth rate, value, heterogeneity, veracity and variability also complicate the efficient and sustainable handling of highly sensitive and complex data sets.
The big data discourse in fields such as health and bioinformatics also revolves, against the background of (external) economic preferences, around topics such as privacy, data responsibility and security, with reference to collection, storage and further processing as well as transfer, and corresponding ownership relationships, but also the handling of data during storage with regard to data sorting, organization and interpretation, in order to ensure personal protection in the long term (which would also be in line with the DSGVO). With the ubiquity of Big Data in mind, IT governance also plays an important role, as increasingly modern information and communication technologies (ICT), e.g. cloud services, social technologies or mobile computing and their software solutions, are encountering an ever-growing global society that is, so to speak, becoming older and older, first and foremost in the Western nations – a massive burden on the LifeScience sector, which must adequately absorb the aging generations against the backdrop of technical challenges. The volume of data is therefore growing due to the increasing needs of society and the rapidly evolving technologies and their sprawling into permanent health monitoring, which now allow the collection not only of more, but also of very specific health data, be it physical or psychological, so to speak personal or emotional. Both causes have so far prevented rapid conclusion, decision-making and action as desirable in health care, but the latter is also an innovative approach.
In order to transform the resulting isles of data into effective and active resources, these must be sorted via data integration into existing data stores and interconnected with each other. Completely new data clusters can also be created. Automated tools (see Watson from IBM) can support this preparation process, as can AI (Artificial Intelligence)-based machine learning processes, e.g. cognitive computing. An improvement of the control and quality measurement procedures during the treatment or e.g. also material supply chains, as well as reduction of previous infrastructural costs can offer for instance the Blockchain (to some degree right now). On the way to real-time transmission, early diagnosis and subsequent prognosis, as well as necessary material supply, research and industry make an important contribution – Big Data represents an interdisciplinary undertaking, the method behind it corresponds to a user-centered process. Based on the need of cooperation, which they impose on us in order to master their handling, large amounts of data form the starting point for connection technologies that could deprive humans of the necessity of their own functionality in the long term. In the LifeScience sector this would mean time, no longer primarily for data, its research, collection and processing, whose results sometimes only scratch the tip of the iceberg, but for people within the care chain and new (individual) error-resistant methods of diagnosis, therapy and prevention geared to them.