Q-Learning Based Therapy Modeling

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.