Precision oncology: The promise of big data and the legacy of small data

Abstract

Big data are expected to exert profound impacts on medicine. High-throughput technologies, electronic medical records, high-resolution imaging, multiplexed omics, these are examples of fields that are progressing at a fast pace. Because they all yield complex heterogeneous data types, managing such variety and volumes is a challenge. While the computation power required to analyze them is available, the main difficulty consists in interpreting the results. In light of the emerging precision medicine paradigm, oncology is influenced by digital phenotypes characterizing disease expression, In particular, digital biomarkers could become critical for the evaluation of clinical endpoints. Currently, integrative approaches are conceived for the analysis of multi-evidenced data, i.e., data generated from multiple sources, such as cells, organs, individual lifestyle and social habits, environment, population dynamics, etc. The granularity, the scales of measurement, the model prediction accuracy, these are factors justifying an ongoing progressive differentiation from evidence-based medicine, typically based on a relatively small and unique scale of the experiments, thus well assimilated by a mathematical or statistical model. A premise of precision medicine is the N-of-1 paradigm, inspired by a focus on individualization. However, diversity, amount, and complexity of input data points that are needed for individual assessments, suggest centrality of systems inference principles. In turn, a revised paradigm is acquiring relevance, say (N-of-1) c , where the exponent c indicates connectivity. What makes connectivity such a key factor? For instance, the synergy embedded but often latent in the data layers, namely signatures, profiles, etc., which can lead to many stratified directions. Reference then goes to the biological and medical insights due to data integration, here discussed in view of the current oncological trends.