Big data need big theory too

Abstract

The current interest in big data, machine learning and data analytics has generated the widespread impression that such methods are capable of solving most problems without the need for conventional scientific methods of inquiry. Interest in these methods is intensifying, accelerated by the ease with which digitized data can be acquired in virtually all fields of endeavour, from science, healthcare and cybersecurity to economics, social sciences and the humanities. In multiscale modelling, machine learning appears to provide a shortcut to reveal correlations of arbitrary complexity between processes at the atomic, molecular, meso- and macroscales. Here, we point out the weaknesses of pure big data approaches with particular focus on biology and medicine, which fail to provide conceptual accounts for the processes to which they are applied. No matter their ‘depth’ and the sophistication of data-driven methods, such as artificial neural nets, in the end they merely fit curves to existing data. Not only do these methods invariably require far larger quantities of data than anticipated by big data aficionados in order to produce statistically reliable results, but they can also fail in circumstances beyond the range of the data used to train them because they are not designed to model the structural characteristics of the underlying system. We argue that it is vital to use theory as a guide to experimental design for maximal efficiency of data collection and to produce reliable predictive models and conceptual knowledge. Rather than continuing to fund, pursue and promote ‘blind’ big data projects with massive budgets, we call for more funding to be allocated to the elucidation of the multiscale and stochastic processes controlling the behaviour of complex systems, including those of life, medicine and healthcare.This article is part of the themed issue ‘Multiscale modelling at the physics–chemistry–biology interface’.

Genetic studies of alcohol dependence in the context of the addiction cycle

“…Big data generating efforts, especially in genomics and the NIH Big Data to Knowledge (BD2K) program, have become an attractive approach for advancing biological discoveries. However, pure big data approaches have been criticized for failing to provide conceptual insights into biological processes (Coveney et al, 2016). It is therefore suggested that big data approaches should rely on theoretical frameworks to avoid circumventing the proven modern scientific method of inquiry and digressing to pre-Baconism methods of radical empiricism (i.e., data generation without reason).…”

Gene expression profiling in the human alcoholic brain

“…This allows the study of alcohol-induced alterations in gene expression in the human brain at an unprecedented level, and the advancement of potentially relevant treatment strategies for normalizing addiction-related changes in gene expression. With these rapid advances also come challenges that are further amplified when considering the broad range of ‘omic’ approaches and modeling requirements for understanding complex disease (Coveney et al, 2016). …”

Hope, hype and harms of Big Data

“…While increasing the availability, scope and amount of interrogable data, this Big Data flood will be of limited use if there is no conceptual framework that grounds the questions to be asked and guides data collection, curation and interpretation, and specifies key variables that need to be measured – and measured accurately . The impact of Big Data on minimising clinical uncertainty may be much more modest than proponents claim.…”