Gene expression profiles have become an important and promising way for cancer prognosis and treatment. In addition to their application in cancer class prediction and discovery, gene expression data can be used for the prediction of patient survival. Here, we use particle swarm optimization (PSO) to address one of the major challenges in gene expression data analysis, the curse of dimensionality, in order to discriminate high risk patients from low risk patients. A discrete binary version of PSO is used for gene selection and dimensionality reduction, and a probabilistic neural network (PNN) is implemented as the classifier. The experimental results on the diffuse large B-cell lymphoma data set demonstrate the effectiveness of PSO/PNN system in survival prediction.

Meeting Name

IEEE Engineering in Medicine and Biology 27th Annual Conference, 2005


Electrical and Computer Engineering

Second Department

Computer Science


Mary K. Finley Missouri Endowment
National Science Foundation (U.S.)

Keywords and Phrases

Cancer; Cellular Biophysics; Genetics; Learning (Artificial Intelligence); Medical Computing; Molecular Biophysics; Neural Nets; Particle Swarm Optimisation

Document Type

Article - Conference proceedings

Document Version

Final Version

File Type





© 2006 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Full Text Link