Document Detail


Individualization of pharmacological anemia management using reinforcement learning.
MedLine Citation:
PMID:  16109475     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
Effective management of anemia due to renal failure poses many challenges to physicians. Individual response to treatment varies across patient populations and, due to the prolonged character of the therapy, changes over time. In this work, a Reinforcement Learning-based approach is proposed as an alternative method for individualization of drug administration in the treatment of renal anemia. Q-learning, an off-policy approximate dynamic programming method, is applied to determine the proper dosing strategy in real time. Simulations compare the proposed methodology with the currently used dosing protocol. Presented results illustrate the ability of the proposed method to achieve the therapeutic goal for individuals with different response characteristics and its potential to become an alternative to currently used techniques.
Authors:
Adam E Gaweda; Mehmet K Muezzinoglu; George R Aronoff; Alfred A Jacobs; Jacek M Zurada; Michael E Brier
Related Documents :
6239005 - Evaluation of exemplar-based generalization and the abstraction of categorical informat...
16213695 - An incremental em-based learning approach for on-line prediction of hospital resource u...
17298235 - Neighborhood property-based pattern selection for support vector machines.
8891955 - A learning method of hidden markov models for sequence discrimination.
23696455 - Isentropic compressibilities-experimental origin and the quest for their rigorous estim...
15026975 - Begging and sibling competition: how should offspring respond to their rivals?
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't; Research Support, U.S. Gov't, Non-P.H.S.    
Journal Detail:
Title:  Neural networks : the official journal of the International Neural Network Society     Volume:  18     ISSN:  0893-6080     ISO Abbreviation:  Neural Netw     Publication Date:    2005 Jun-Jul
Date Detail:
Created Date:  2005-09-05     Completed Date:  2005-11-09     Revised Date:  2006-11-15    
Medline Journal Info:
Nlm Unique ID:  8805018     Medline TA:  Neural Netw     Country:  United States    
Other Details:
Languages:  eng     Pagination:  826-34     Citation Subset:  IM    
Affiliation:
Department of Medicine, University of Louisville, Louisville, KY 40292, USA. adam.gaweda@kdp.louisville.edu
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms
Anemia / drug therapy*
Artificial Intelligence*
Classification
Erythropoietin, Recombinant / administration & dosage*,  therapeutic use*
Hemoglobins / metabolism
Humans
Markov Chains
Models, Neurological
Neural Networks (Computer)
Reinforcement (Psychology)*
Chemical
Reg. No./Substance:
0/Erythropoietin, Recombinant; 0/Hemoglobins

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Identification of motifs with insertions and deletions in protein sequences using self-organizing ne...
Next Document:  FGFR4 GLY388 isotype suppresses motility of MDA-MB-231 breast cancer cells by EDG-2 gene repression.