Medical diagnosis as a linguistic game

Peter Fritz,Andreas Kleinhans,Christine Fritz-Kuisle,Mark Dominik Alscher,Florian Kuisle,Patricius Albu

doi:10.1186/s12911-017-0488-3

Peter Fritz, Andreas Kleinhans + Show 4 more

Open Access

https://doi.org/10.1186/s12911-017-0488-3

Copy DOI

Abstract

BackgroundWe present a formalized medical knowledge system using a linguistic approach combined with a semantic net.MethodDiseases are defined and coded by natural linguistic terms and linked via a complex network of attributes, categories, classes, lists and other semantic conditions.ResultsWe 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.ConclusionsMemem7 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.

Highlights

We present a formalized medical knowledge system using a linguistic approach combined with a semantic net
Our approach has as starting point the fact that the collection of patient data can be considered as a patient data vector
Many thesauri could be obtained from Internet or official institutions as the DIMDI (Deutsches Institut für medizinische Dokumentation) [22]

Summary

Introduction

We present a formalized medical knowledge system using a linguistic approach combined with a semantic net. It is known that diagnostic errors occur, with a frequency (depending on how terms are defined) ranging between 2.5% and 20% [1, 2]. Most errors have only moderate negative consequences, but some do not. Our approach has as starting point the fact that the collection of patient data can be considered as a patient data vector. Assignment of the symptoms or signs of a patient to a certain diagnosis is possible by a bundle of different not exclusive methods: (1) by the knowledge of the physician, (2) by comparison of the patient data with clinical pathways and guidelines, (3) by boards of specialized physicians, (4) a second opinion by an experienced medical doctor, and (5) by computer-assisted comparison with a data base of medical knowledge.

Methods

Results

Discussion

Conclusion