Background: Historical accounts of psychiatric classifications have hitherto been written in terms of a ‘received view’. This contains two assumptions, that: (i) the activity of classifying is inherent to the human mind; and (ii) psychiatric ‘phenomena’ are stable natural objects.
Objectives: The aim of this article is to provide an outline of the evolution of psychiatric classifications from the perspective of conceptual history. This is defined as a theoretical and empirical inquiry into the principles, sortal techniques and contexts in which alienists carried out their task. It assumes that all psychiatric classifications are cultural products, and endeavours to answer the question of whether classificatory models imported from the natural sciences can be applied to man-made constructs (such as mental illness) definitionally based on ‘personalised semantics’.
Methods: Exemplars of classificatory activity are first mapped and contextualised. Then, it is suggested that in each historical period crafting classifications has been like playing a game of chess with each move being governed by rules. This is illustrated by offering an analysis of the 1860–1861 French debate on classification.
Results and Conclusions: (1) Medicine is not a contemplative but a modificatory activity and hence classifications are only valuable if they can release new information about the object classified. (2) It should not be inferred from the fact that psychiatric classifications are not working well (i.e. that they only behave as actuarial devices) that they must be given up. Conceptual work needs to continue to identify ‘invariants’ (i.e. stable elements that anchor classifications to ‘nature’. (3) Because mental disorders are more than unstable behavioural epiphenomena wrapped around stable molecular changes, ‘neurobiological’ invariants may not do. Stability depends upon time frames. Furthermore, it is unlikely that gene-based classifications will ever be considered as classifications of mental disorders. For once, they would have low predictive power because of their lack of information about the defining codes of mental illness. ‘Social’ and ‘psychological’ invariants have problems of their own.