Application of gene expression programming and neural networks to predict adverse events of radical hysterectomy in cervical cancer patients

Created by W.Langdon from gp-bibliography.bib Revision:1.7778

@Article{Kusy:2013:MBEC,

• author = "Maciej Kusy and Bogdan Obrzut and Jacek Kluska",
• title = "Application of gene expression programming and neural networks to predict adverse events of radical hysterectomy in cervical cancer patients",
• journal = "Medical \& Biological Engineering \& Computing",
• year = "2013",
• volume = "51",
• number = "12",
• pages = "1357--1365",
• publisher = "Springer",
• month = "1 " # dec,
• keywords = "genetic algorithms, genetic programming, gene expression programming, GEP, cervical cancer, radical hysterectomy, perioperative complications, neural networks",
• ISSN = "0140-0118",
• bibsource = "OAI-PMH server at www.ncbi.nlm.nih.gov",
• language = "English",
• oai = "oai:pubmedcentral.nih.gov:3825140",
• oai = "oai:CiteSeerX.psu:10.1.1.1029.4333",
• URL = "http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3825140",
• URL = "http://www.ncbi.nlm.nih.gov/pubmed/24136688",
• URL = "http://dx.doi.org/10.1007/s11517-013-1108-8",
• URL = "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1029.4333",
• DOI = "doi:10.1007/s11517-013-1108-8",
• size = "9 pages",
• abstract = "The aim of this article was to compare gene expression programming (GEP) method with three types of neural networks in the prediction of adverse events of radical hysterectomy in cervical cancer patients. One-hundred and seven patients treated by radical hysterectomy were analysed. Each record representing a single patient consisted of 10 parameters. The occurrence and lack of perioperative complications imposed a two-class classification problem. In the simulations, GEP algorithm was compared to a multilayer perceptron (MLP), a radial basis function network neural, and a probabilistic neural network. The generalisation ability of the models was assessed on the basis of their accuracy, the sensitivity, the specificity, and the area under the receiver operating characteristic curve (AUROC). The GEP classifier provided best results in the prediction of the adverse events with the accuracy of 71.96percent. Comparable but slightly worse outcomes were obtained using MLP, i.e., 71.87percent. For each of measured index: accuracy, sensitivity, specificity, and the AUROC, the standard deviation was the smallest for the models generated by GEP classifier.",

}

Genetic Programming entries for Maciej Kusy Bogdan Obrzut Jacek Kluska

Citations