Medical knowledge representation by means of multipopulation genetic programming: an application to burn diagnosing

Decision support systems have proved to be useful in medical decision making. Here, the authors present a methodology that allow them to capture medical knowledge and develop a decision system for burn diagnosing by means of Genetic Programming. Diagnosing the evolution of a burn is a very difficult task. The authors present a learning classifier system based on multipopulations genetic programming. It uses a set of parameters, obtained by specialist doctors, to predict the evolution of a burn according to its initial stages. The system is first trained with a set of parameters and results of evolution have been recorded over a set of clinic cases. Once the system is trained, it is useful for deciding how new cases will probably evolve. Thanks to the use of Genetic Programming an explicit expression of the input parameter is provided. This explicit expression takes the form of a Decision Tree, which will be incorporated into software tools that help physicians in their everyday work