This paper presents a concept for a Decision Support System for Therapy Planning based on the Q-Learning method. It focuses the consideration on a multilevel approach for constructing a data driven evidence based system for classification of different drug dosages and their effectiveness for clinical trials. We consider time - ordered sequences of patient data called patient trials consisting of state, time and medication ordered by clinicians. A patient state generalization function to provide generalized patient states as categories of patient data is presented. For classification of medications we introduce a medication generalization function based on similarity classes of medications and a similarity function between two drug dosages. Both generalization functions are used for generalizing patient trials and for the synthesis of the Q-Learning agent for the Decision Support System.
|Title of host publication||Proceedings of 21st European Modeling and Simulation Symposium EMSS 2009|
|Publisher||DIPTEM University of Genova|
|Publication status||Published - 2009|
|Event||21st European Modeling and Simulation Symposium 2009 EMSS09 - Tenerife, Spain|
Duration: 23 Sep 2009 → 25 Sep 2009
|Conference||21st European Modeling and Simulation Symposium 2009 EMSS09|
|Period||23.09.2009 → 25.09.2009|