%0 Journal Article %1 gray:1998:GPcfs:aNMRshbtb %A Gray, Helen F. %A Maxwell, Ross J. %A Martinez-Perez, Irene %A Arus, Carles %A Cerdan, Sebastian %D 1998 %J NMR Biomedicine %K algorithms, artificial brain classification, feature genetic intelligence, programming, selection tumour, %N 4-5 %P 217--224 %R doi:10.1002/(SICI)1099-1492(199806/08)11:4/5<217::AID-NBM512>3.0.CO;2-4 %T Genetic programming for classification and feature selection: analysis of 1H nuclear magnetic resonance spectra from human brain tumour biopsies %V 11 %X Genetic programming (GP) is used to classify tumours based on 1H nuclear magnetic resonance (NMR) spectra of biopsy extracts. Analysis of such data would ideally give not only a classification result but also indicate which parts of the spectra are driving the classification (i.e. feature selection). Experiments on a database of variables derived from 1H NMR spectra from human brain tumour extracts (n = 75) are reported, showing GP's classification abilities and comparing them with that of a neural network. GP successfully classified the data into meningioma and non-meningioma classes. The advantage over the neural network method was that it made use of simple combinations of a small group of metabolites, in particular glutamine, glutamate and alanine. This may help in the choice of the most informative NMR spectroscopy methods for future non-invasive studies in patients.

@article{gray:1998:GPcfs:aNMRshbtb, abstract = {Genetic programming (GP) is used to classify tumours based on 1H nuclear magnetic resonance (NMR) spectra of biopsy extracts. Analysis of such data would ideally give not only a classification result but also indicate which parts of the spectra are driving the classification (i.e. feature selection). Experiments on a database of variables derived from 1H NMR spectra from human brain tumour extracts (n = 75) are reported, showing GP's classification abilities and comparing them with that of a neural network. GP successfully classified the data into meningioma and non-meningioma classes. The advantage over the neural network method was that it made use of simple combinations of a small group of metabolites, in particular glutamine, glutamate and alanine. This may help in the choice of the most informative NMR spectroscopy methods for future non-invasive studies in patients.}, added-at = {2008-06-19T17:35:00.000+0200}, author = {Gray, Helen F. and Maxwell, Ross J. and Martinez-Perez, Irene and Arus, Carles and Cerdan, Sebastian}, biburl = {https://www.bibsonomy.org/bibtex/2cd78e63237011653cfee4bca103d12dd/brazovayeye}, doi = {doi:10.1002/(SICI)1099-1492(199806/08)11:4/5<217::AID-NBM512>3.0.CO;2-4}, interhash = {25998ff4a6a1f456a7b70c50c311e8de}, intrahash = {cd78e63237011653cfee4bca103d12dd}, journal = {NMR Biomedicine}, keywords = {algorithms, artificial brain classification, feature genetic intelligence, programming, selection tumour,}, month = {June-August}, notes = {PMID: 9719576, UI: 98384081 Computer Science Department, Arhus University, Denmark.}, number = {4-5}, pages = {217--224}, timestamp = {2008-06-19T17:40:36.000+0200}, title = {Genetic programming for classification and feature selection: analysis of {1H} nuclear magnetic resonance spectra from human brain tumour biopsies}, volume = 11, year = 1998 }