ijsmr
Abstract : Model Based Sparse Feature Extraction for Biomedical Signal Classification
|
|
Abstract: This article focuses on model based sparse feature extraction of biomedical signals for classification problems, which stems from sparse representation in modern signal processing. In the presented work, a novel approach based on sparse principal component analysis (SPCA) is proposed to extract signal features. This method involves partitioning signals and utilizing SPCA to select only a limited number of signal segments in order to construct signal principal components during the training stage. For signal classification purposes, a set of regression models based on sparse principal components of the selected training signal segments is constructed. Within this approach, model residuals are estimated and used as signal features for classification. The applications of the proposed approach are demonstrated by using both the synthetic data and real EEG signals. The high classification accuracy results suggest that the proposed methods may be useful for automatic event detection using long-term observational signals. keywords: Sparse Principal Component Analysis, Sparse Feature Extraction, Signal Classification, Long-term Signals. Keywords: Sparse Principal Component Analysis, Sparse Representation, Signal Classification, Long-term Signals. |
Abstract : Bayesian Modelling of Tuberculosis Risk Factors in South Africa 2014
|
|
Abstract: Background: Although the number of deaths has declined since 2007, Tuberculosis (TB) continues to be the number one cause of death in South Africa. To create a country free of TB, there is need for continued research to explore models that will provide the Department of Health with new interventions. Aim: This study was aimed at identifying the risk factors of active self-reported TB prevalence for South Africa in 2014. Methods: The Frequentist Logistic Regression (FLR) approach was applied on a sample of 19213 individuals taken from the National Income Dynamics Survey (NIDS) wave data. Bayesian analysis with non-informative priors were used to model Wave 1 to 3 data and elicitation of the obtained posterior density parameters by averaging done to obtain the informative priors used to model wave 4. The wave 4 results obtained under the two estimation approaches were compared as well as the results for non-informative and informative priors. Results: The findings show that self-reported TB prevalence is higher than the reported 1%, Human Immuno Deficiency Virus (HIV) remains a major threat to TB and Eastern Cape is the province mostly affected by TB with Limpopo recording the least prevalence. Poor living conditions and lower socio-economic conditions continue to be drivers of TB whilst English illiteracy, lack of Secondary/Tertiary education, alcohol consumption, marital status, gender and age groups also influence TB progression to disease. FLR yielded similar results to Bayesian with non-informative priors whilst the results are more precise for informative priors. Conclusion: This study identified individuals and communities at risk of developing active TB disease in South Africa. Keywords: Tuberculosis, HIV, South Africa, National Income Dynamics Survey, Bayesian analysis, Frequentist Logistic Regression. |
Abstract : ROC Analysis for Phase II Group Sequential Basket Clinical Trial
|
|
Abstract: The basket trial is a recent development in the clinical trial practice. It conducts the test of the same treatment on several different related diseases in a single trial, and has the advantage of reduced cost and enhanced efficiency. A natural question is how to assess the performance of the group sequential basket trial against the classical group sequential trial? To our knowledge, a formal assessment hasn’t been seen in the literature, and is the goal of this study. Specifically, we use the receiver operating characteristic curve to assess the performance of the mentioned two trials. We considered two cases, parametric and nonparametric settings. The former is efficient when the parametric model is correctly specified, but can bemis-leading if the model is incorrect; the latter is less efficient but is robust in that it cannot be wrong no matter what the true data generating model is. Simulation studies are conducted to evaluate the experiments, and it suggests that the group sequential basket trial generally outperforms the group sequential trial in either the parametric and nonparametric cases, and that the nonparametric method gives more accurate evaluation than the parametric one for moderate to large sample sizes. Keywords: Basket trial, group sequential clinical trial, nonparametric ROC curve, parametric ROC curve, phase II clinical trial. |
Abstract : Evaluation of Methods for Gene Selection in Melanoma Cell Lines
|
|
Abstract: A major objective in microarray experiments is to identify a panel of genes that are associated with a disease outcome or trait. Many statistical methods have been proposed for gene selection within the last fifteen years. While the comparison of some of these methods has been done, most of them concentrated on finding gene signatures based on two groups. This study evaluates four gene selection methods when the outcome of interested is continuous in nature. We provide a comparative review of four methods: the Statistical Analysis of Microarrays (SAM), the Linear Models for Microarray Analysis (LIMMA), the Lassoed Principal Components (LPC), and the Quantitative Trait Analysis (QTA). Comparison is based on the power to identify differentially expressed genes, the predictive ability of the genelists for a continuous outcome (G2 checkpoint function), and the prognostic properties of the genelists for distant metastasis-free survival. A simulated dataset and a publicly available melanoma cell lines dataset are used for simulations and validation, respectively. A primary melanoma dataset is used for assessment of prognosis. No common genes were found among the genelists from the four methods. While the SAM was generally the best in terms of power, the QTA genelist performed the best in the prediction of the G2 checkpoint function. Identification of genelists depends on the choice of the gene selection method. The QTA method would be preferred over the other approaches in predicting a quantitative outcome in melanoma research. We recommend the development of more robust statistical methods for differential gene expression analysis. Keywords: Differential gene expression, Melanoma cell lines, Prediction, Power, Quantitative trait. |
