Epistemologies of evidence-based medicine: a plea for corpus-based conceptual research in the medical humanities

Abstract

Evidence-based medicine has been the subject of much controversy within and outside the field of medicine, with its detractors characterizing it as reductionist and authoritarian, and its proponents rejecting such characterization as a caricature of the actual practice. At the heart of this controversy is a complex linguistic and social process that cannot be illuminated by appealing to the semantics of the modifier evidence-based. The complexity lies in the nature of evidence as a basic concept that circulates in both expert and non-expert spheres of communication, supports different interpretations in different contexts, and is inherently open to contestation. We outline a new methodology that combines a social epistemological perspective with advanced methods of corpus linguistics and elements of conceptual history to investigate this and other basic concepts that underpin the practice and ethos of modern medicine. The potential of this methodology to offer new insights into controversies such as those surrounding EBM is demonstrated through a case study of the various meanings supported by evidence and based, as attested in a large electronic corpus of online material written by non-experts as well as a variety of experts in different fields, including medicine.

Keywords: Basic concept; Corpora; Evidence; Evidence-based medicine; Social epistemology.

Fig. 1

Example screenshot of a KWIC concordance of evidence from the GoK interface, ordered by the lexical item in position 1 to the left of the keyword

Fig. 2

Mosaic of evidence collocates in the GoK Internet Corpus (cropped). The size of the tiles is relative to the words’ collocation strength, calculated using the MI3 measure (a variant of Mutual Information less biased towards rare words), omitting log transformation. Local view is selected within the interface, meaning that significance is represented within each position to the left or right of the keyword, rather than across all positions (global view). See Luz and Sheehan (, pp. 11–12) for a broader discussion of the visualization tool

Fig. 3

Concordance tree showing patterns preceding much evidence in the GoK Internet Corpus (cropped). Left co-text is shown. More common patterns are displayed in larger font. They include direct negation of sufficient quantity via the adverb not; more extended examples include ‘don’t provide’ and ‘neither side has managed to produce’. See Luz and Sheehan (, pp. 11, 13) for more information on the visualization tool