The part-whole relation has significant effect on classification in the medical domain, since diagnoses, medical procedures and findings commonly relate to anatomical objects and their parts. The paper analyses conventional medical terminology and classification systems with respect to part-whole relations, it investigates how languages of the KL-ONE-family approach the complexity of part-whole relation and subsumption, and it outlines recent developments in medical concept representation. Conventional systems used tor medical documentation, indexing of clinical data or bibliographical retrieval are weak for several reasons. Partitive and generic relations are often incompletely represented and both relations are often mixed. This is due to the common combination of a concept system with a coding schema, which often constrains the hierarchical organization of concepts. Terminological languages in the tradition of KL-ONE approach the part-whole relation by different ways: Partly, they use the transitivity of subsumption for representing the transitivity of part-whole. On the other hand, there are arguments for keeping the part-whole relation outside the classifier and for modelling the effect of part-whole on subsumption in the axiomatic component of a terminological reasoning system. GRAIL and BERNWARD are approaches which focus on formal concept representation in the medical domain. GRAIL considers part-whole relations by the classifier and allows for the specification of roles to be refinable along partitive criteria. BERNWARD is based on conceptual graphs and follows a different approach. The transitivity of part-whole is represented by explicit ordering of concepts through a partonomy and by transitive chaining of part-of roles in composite concept descriptions. Both approaches allow for partitive nesting in concept representation and consider the effect of partitive attributes on subsumption by the classifier, but lack a deeper theory of the part-whole relation.