Identification of signatures in biomedical spectra using domain knowledge

Authors:
Erinija Pranckeviciene;Ray Somorjai;Richard Baumgartner;Moon-Gu Jeon
Affiliations:
Institute for Biodiagnostics, National Research Council, 435 Ellice Avenue, Winnipeg, Man., Canada R3B 1Y6 and Kaunas University of Technology, Studentu 50, Kaunas, LT 3031, Lithuania;Institute for Biodiagnostics, National Research Council, 435 Ellice Avenue, Winnipeg, Man., Canada R3B 1Y6;Institute for Biodiagnostics, National Research Council, 435 Ellice Avenue, Winnipeg, Man., Canada R3B 1Y6;Institute for Biodiagnostics, National Research Council, 435 Ellice Avenue, Winnipeg, Man., Canada R3B 1Y6
Venue:
Artificial Intelligence in Medicine
Year:
2005

Citing 15
Cited 2

Introduction to statistical pattern recognition (2nd ed.)

Introduction to statistical pattern recognition (2nd ed.)
The Random Subspace Method for Constructing Decision Forests

IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models

Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models
Support vector machines with different norms: motivation, formulations and results

Pattern Recognition Letters
Gene Selection for Cancer Classification using Support Vector Machines

Machine Learning
On the Relationship Between the Support Vector Machine for Classification and Sparsified Fisher‘s Linear Discriminant

Neural Processing Letters
Comparison of Two Classification Methodologies on a Real-World Biomedical Problem

Proceedings of the Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition
Feature Selection Via Mathematical Programming

INFORMS Journal on Computing
Simultaneous classification and relevant feature identification in high-dimensional spaces: application to molecular profiling data

Signal Processing - Special issue: Genomic signal processing
Constructing Descriptive and Discriminative Nonlinear Features: Rayleigh Coefficients in Kernel Feature Spaces

IEEE Transactions on Pattern Analysis and Machine Intelligence
Structure Preserving Dimension Reduction for Clustered Text Data Based on the Generalized Singular Value Decomposition

SIAM Journal on Matrix Analysis and Applications
Support Vectors Selection by Linear Programming

IJCNN '00 Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 5 - Volume 5
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Reducing the overconfidence of base classifiers when combining their decisions

MCS'03 Proceedings of the 4th international conference on Multiple classifier systems
Simultaneous feature selection and classifier training via linear programming: a case study for face expression recognition

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition

Liknon Feature Selection for Microarrays

WILF '07 Proceedings of the 7th international workshop on Fuzzy Logic and Applications: Applications of Fuzzy Sets Theory
Computer-aided diagnosis of pulmonary nodules using a two-step approach for feature selection and classifier ensemble construction

Artificial Intelligence in Medicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

Objective: Demonstrate that incorporating domain knowledge into feature selection methods helps identify interpretable features with predictive capability comparable to a state-of-the-art classifier. Methods: Two feature selection methods, one using a genetic algorithm (GA) the other a L"1-norm support vector machine (SVM), were investigated on three real-world biomedical magnetic resonance (MR) spectral datasets of increasing difficulty. Consensus sets of the feature sets obtained by the two methods were also assessed. Results and conclusions: Features identified independently by the two methods and by their consensus, determine class-discriminatory groups or individual features, whose predictive power compares favorably with that of a state-of-the-art classifier. Furthermore, the identified feature signatures form stable groupings at definite spectral positions, hence are readily interpretable. This is a useful and important practical result for generating hypothesis for the domain expert. t.