The aim of the ANTHEM (Advanced Natural Language Interface for Multilingual Text Generation) project was to have ready in September 1996 an API for medical systems able to generate out of medical diagnosis sublanguage statements in French or Dutch, language independent representations of the utterances that will generate translations of the original input in Dutch, French or German, and to perform automatic encoding following the ICD-10 classification rules. A second aim of ANTHEM was to use the same sublanguage approach for the analysis of standardised medical diagnosis expressions such as those used in international classification systems in order to facilitate cross-mapping to other systems and a smooth transition from older to new versions.

ANTHEM undertook testing of the final prototypes in a real world environment. Validation of the prototypes were carried out from a threefold perspective: linguistically (by testing the performance of the various subsystems with respect to automatic encoding and translation), technically (by assessing the flexibility with which the APIs can be integrated in existing healthcare applications) and operationally (by allowing end-users to comment on the overall user-friendliness and practical performance of the system).