Identification of signatures in biomedical spectra using domain knowledge

Institute for Biodiagnostics, National Research Council, 435 Ellice Avenue, Winnipeg, Manitoba, Canada R3B 1Y6.
Artificial Intelligence in Medicine (Impact Factor: 2.02). 12/2005; 35(3):215-26. DOI: 10.1016/j.artmed.2004.12.002
Source: PubMed


Demonstrate that incorporating domain knowledge into feature selection methods helps identify interpretable features with predictive capability comparable to a state-of-the-art classifier.
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.
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.

Download full-text


Available from: Erinija Pranckeviciene, Aug 14, 2014
  • Source
    • "Recently, the support vector machine (SVM) proposed by Vapnik [29] [30] is a new classification technique. SVM has been used as a classification tool with a great deal of success in various application areas [31] [32] [33] [34] [35] [36] [37] [38] [39] [40] [41]. Therefore, in this study, a new trial for estimation of cardiac sound murmurs by two morphological characteristics in frequency domain with aid of a multi-supported vector machine technique is proposed. "
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, a novel cardiac sound spectral analysis method using the normalized autoregressive power spectral density (NAR-PSD) curve with the support vector machine (SVM) technique is proposed for classifying the cardiac sound murmurs. The 489 cardiac sound signals with 196 normal and 293 abnormal sound cases acquired from six healthy volunteers and 34 patients were tested. Normal sound signals were recorded by our self-produced wireless electric stethoscope system where the subjects are selected who have no the history of other heart complications. Abnormal sound signals were grouped into six heart valvular disorders such as the atrial fibrillation, aortic insufficiency, aortic stenosis, mitral regurgitation, mitral stenosis and split sounds. These abnormal subjects were also not included other coexistent heart valvular disorder. Considering the morphological characteristics of the power spectral density of the heart sounds in frequency domain, we propose two important diagnostic features Fmax and Fwidth, which describe the maximum peak of NAR-PSD curve and the frequency width between the crossed points of NAR-PSD curve on a selected threshold value (THV), respectively. Furthermore, a two-dimensional representation on (Fmax, Fwidth) is introduced. The proposed cardiac sound spectral envelope curve method is validated by some case studies. Then, the SVM technique is employed as a classification tool to identify the cardiac sounds by the extracted diagnostic features. To detect abnormality of heart sound and to discriminate the heart murmurs, the multi-SVM classifiers composed of six SVM modules are considered and designed. A data set was used to validate the classification performances of each multi-SVM module. As a result, the accuracies of six SVM modules used for detection of abnormality and classification of six heart disorders showed 71-98.9% for THVs=10-90% and 81.2-99.6% for THVs=10-50% with respect to each of SVM modules. With the proposed cardiac sound spectral analysis method, the high classification performances were achieved by 99.9% specificity and 99.5% sensitivity in classifying normal and abnormal sounds (heart disorders). Consequently, the proposed method showed relatively very high classification efficiency if the SVM module is designed with considering THV values. And the proposed cardiac sound murmurs classification method with autoregressive spectral analysis and multi-SVM classifiers is validated for the classification of heart valvular disorders.
    Full-text · Article · Nov 2009 · Computers in Biology and Medicine
  • Source
    • "The model selection procedure based on Linear Programming Support Vector Machine (LPSVM), also known as liknon [3] is claimed to exhibit robustness to the sample bias. The method was initially proposed by [6], and has been used for practical classification tasks by [7],[18],[17] and several other researchers. However, its robustness for feature selection does not appear to have been thoroughly investigated. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Many real-world classification problems are represented by very sparse and high-dimensional data. The recent successes of a linear programming support vector machine (LPSVM) for feature selection motivated a deeper analysis of the method when applied to sparse, multivariate data. Due to the sparseness, the selection of a classification model is greatly influenced by the characteristics of that particular dataset. In this study, we investigate a feature selection strategy based on LPSVM as the initial feature filter, combined with state-of-art classification rules, and apply to five real-life datasets of the agnostic learning vs. prior knowledge challenge of IJCNN2007. Our goal is to better understand the robustness of LPSVM as a feature filter. Our analysis suggests that LPSVM can be a useful black box method for identification of the profile of the informative features in the data. If the data are complex and better separable by nonlinear methods, then feature pre-filtering by LPSVM enhances the data representation for other classifiers.
    Full-text · Conference Paper · Sep 2007
  • Source
    • "Using this method, we investigate two popular feature selection procedures: Forward Feature Selection (FFS) and Linear Programming Support Vector Machine (LPSVM) [2], named LIKNON by [1]. LPSVM has yielded promising classifiers in microarray analysis [1], face recognition [3], and classification of biomedical spectra [7]. We will describe these procedures briefly and then present details and results of our proposed evaluation methodology. "
    [Show abstract] [Hide abstract]
    ABSTRACT: We investigated the geometrical complexity of several high-dimensional, small sample classication problems and its changes due to two popular feature selection procedures, forward feature selection (FFS) and Linear Programming Support Vector Machine (LPSVM). We found that both pro- cedures are able to transform the problems to spaces of very low dimensionality where class separability is improved over that in the original space. The study shows that geo- metrical complexities have good potentials for comparing different feature selection methods in aspects relevant to classication accuracy, yet independent of particular clas- sier choices.
    Full-text · Conference Paper · Jan 2006
Show more