Medical diagnosis as a linguistic game

BACKGROUND: We present a formalized medical knowledge system using a linguistic approach combined with a semantic net. METHOD: Diseases are defined and coded by natural linguistic terms and linked via a complex network of attributes, categories, classes, lists and other semantic conditions. RESULTS: We have isolated more than 4600 disease entities (termed pathosoms using a made-up word) with more than 100.000 attributes sets (termed pathophemes using a made-up word) and a semantic net with more than 140.000 links. All major-medical thesauri like ICD, ICD-O and OPS are included. CONCLUSIONS: Memem7 is a linguistic approach to medical knowledge approach. With the system, we performed a proof of concept and we conclude from our data that our or similar approaches provides reliable and feasible tools for physicians given a formalized history taking is available. Our approach can be considered as both a linguistic game and a third opinion to a set of patient’s data. ELECTRONIC SUPPLEMENTARY MATERIAL: The online version of this article (doi:10.1186/s12911-017-0488-3) contains supplementary material, which is available to authorized users.