Dataset Information

Evaluation of gene expression classification studies: factors associated with classification performance.

ABSTRACT: Classification methods used in microarray studies for gene expression are diverse in the way they deal with the underlying complexity of the data, as well as in the technique used to build the classification model. The MAQC II study on cancer classification problems has found that performance was affected by factors such as the classification algorithm, cross validation method, number of genes, and gene selection method. In this paper, we study the hypothesis that the disease under study significantly determines which method is optimal, and that additionally sample size, class imbalance, type of medical question (diagnostic, prognostic or treatment response), and microarray platform are potentially influential. A systematic literature review was used to extract the information from 48 published articles on non-cancer microarray classification studies. The impact of the various factors on the reported classification accuracy was analyzed through random-intercept logistic regression. The type of medical question and method of cross validation dominated the explained variation in accuracy among studies, followed by disease category and microarray platform. In total, 42% of the between study variation was explained by all the study specific and problem specific factors that we studied together.

SUBMITTER: Novianti PW

PROVIDER: S-EPMC4000205 | biostudies-literature | 2014

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Evaluation of gene expression classification studies: factors associated with classification performance.

Novianti Putri W PW Roes Kit C B KC Eijkemans Marinus J C MJ

PloS one 20140425 4

Classification methods used in microarray studies for gene expression are diverse in the way they deal with the underlying complexity of the data, as well as in the technique used to build the classification model. The MAQC II study on cancer classification problems has found that performance was affected by factors such as the classification algorithm, cross validation method, number of genes, and gene selection method. In this paper, we study the hypothesis that the disease under study signifi ...[more]

PMID: 24770439

Similar Datasets

Project description:BackgroundThe increasing number of gene expression microarray studies represents an important resource in biomedical research. As a result, gene expression based diagnosis has entered clinical practice for patient stratification in breast cancer. However, the integration and combined analysis of microarray studies remains still a challenge. We assessed the potential benefit of data integration on the classification accuracy and systematically evaluated the generalization performance of selected methods on four breast cancer studies comprising almost 1000 independent samples. To this end, we introduced an evaluation framework which aims to establish good statistical practice and a graphical way to monitor differences. The classification goal was to correctly predict estrogen receptor status (negative/positive) and histological grade (low/high) of each tumor sample in an independent study which was not used for the training. For the classification we chose support vector machines (SVM), predictive analysis of microarrays (PAM), random forest (RF) and k-top scoring pairs (kTSP). Guided by considerations relevant for classification across studies we developed a generalization of kTSP which we evaluated in addition. Our derived version (DV) aims to improve the robustness of the intrinsic invariance of kTSP with respect to technologies and preprocessing.ResultsFor each individual study the generalization error was benchmarked via complete cross-validation and was found to be similar for all classification methods. The misclassification rates were substantially higher in classification across studies, when each single study was used as an independent test set while all remaining studies were combined for the training of the classifier. However, with increasing number of independent microarray studies used in the training, the overall classification performance improved. DV performed better than the average and showed slightly less variance. In particular, the better predictive results of DV in across platform classification indicate higher robustness of the classifier when trained on single channel data and applied to gene expression ratios.ConclusionsWe present a systematic evaluation of strategies for the integration of independent microarray studies in a classification task. Our findings in across studies classification may guide further research aiming on the construction of more robust and reliable methods for stratification and diagnosis in clinical practice.

Project description:BackgroundDengue fever (DF) is the most prevalent arthropod-borne viral disease affecting humans. The World Health Organization (WHO) proposed a revised classification in 2009 to enable the more effective identification of cases of severe dengue (SD). This was designed primarily as a clinical tool, but it also enables cases of SD to be differentiated into three specific subcategories (severe vascular leakage, severe bleeding, and severe organ dysfunction). However, no study has addressed whether this classification has advantage in estimating factors associated with the progression of disease severity or dengue pathogenesis. We evaluate in a dengue outbreak associated risk factors that could contribute to the development of SD according to the 2009 WHO classification.MethodsA prospective cross-sectional study was performed during an epidemic of dengue in 2009 in Chiapas, Mexico. Data were analyzed for host and viral factors associated with dengue cases, using the 1997 and 2009 WHO classifications. The cost-benefit ratio (CBR) was also estimated.ResultsThe sensitivity in the 1997 WHO classification for determining SD was 75%, and the specificity was 97.7%. For the 2009 scheme, these were 100% and 81.1%, respectively. The 2009 classification showed a higher benefit (537%) with a lower cost (10.2%) than the 1997 WHO scheme. A secondary antibody response was strongly associated with SD. Early viral load was higher in cases of SD than in those with DF. Logistic regression analysis identified predictive SD factors (secondary infection, disease phase, viral load) within the 2009 classification. However, within the 1997 scheme it was not possible to differentiate risk factors between DF and dengue hemorrhagic fever or dengue shock syndrome. The critical clinical stage for determining SD progression was the transition from fever to defervescence in which plasma leakage can occur.ConclusionsThe clinical phenotype of SD is influenced by the host (secondary response) and viral factors (viral load). The 2009 WHO classification showed greater sensitivity to identify SD in real time. Timely identification of SD enables accurate early decisions, allowing proper management of health resources for the benefit of patients at risk for SD. This is possible based on the 2009 WHO classification.

Dataset Information

Evaluation of gene expression classification studies: factors associated with classification performance.

Publications

Evaluation of gene expression classification studies: factors associated with classification performance.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets