Visualising and mapping the intellectual structure of medical big data

Abstract

In this study, we sought to apply recent advances in informetrics to the analysis of literature related to big data in the field of medicine. Our aim was to elucidate research trends, identify knowledge clusters and decipher the links between them. We also sought to ascertain the theories most commonly applied in the processing of medical data and identify potential research gaps. The most important keywords over the last 10 years have been ‘big data’, ‘data mining’, ‘healthcare’, ‘cloud computing’, ‘machine learning’ and ‘electronic health record system’. These could be viewed as the core issues of research associated with big data in the field of medicine. We also identified a number of keywords that are expected to play a pivotal role in this field in the near future. These terms include the ‘internet of things’, ‘e-health’, ‘sensors’, ‘predictive modeling’, ‘quantified self’, ‘smart city’, ‘wearable device’ and ‘m-health’. Finally, we compiled co-word networks indicating the degree of connectivity between keywords, for use in locating knowledge gaps by revealing the overall context of issues commonly encountered when investigating big data. Our findings form a solid academic foundation on which to develop medical technologies, managerial strategies and theory related to big data.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 16 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.