Search PubMed⌕ Search

Biomedical subjects

Stephen J Roberts

Publications and source records attributed to Stephen J Roberts.

6 recordsLinked to original sources
PubMed2005

Data-adaptive test statistics for microarray data.

MOTIVATION: An important task in microarray data analysis is the selection of genes that are differentially expressed between different tissue samples, such as healthy and diseased. However, microarray data contain an enormous number of dimensions (genes) and very few samples (arrays), a mismatch which poses fundamental statistical problems for the selection process that have defied easy resolution. RESULTS: In this paper, we present a novel approach to the selection of differentially expressed genes in which test statistics are learned from data using a simple notion of reproducibility in selection results as the learning criterion. Reproducibility, as we define it, can be computed without any knowledge of the 'ground-truth', but takes advantage of certain properties of microarray data to provide an asymptotically valid guide to expected loss under the true data-generating distribution. We are therefore able to indirectly minimize expected loss, and obtain results substantially more robust than conventional methods. We apply our method to simulated and oligonucleotide array data. AVAILABILITY: By request to the corresponding author.

Algorithms↗
PubMed2005

A theoretical analysis of the selection of differentially expressed genes.

A great deal of recent research has focused on the challenging task of selecting differentially expressed genes from microarray data ("gene selection"). Numerous gene selection algorithms have been proposed in the literature, but it is often unclear exactly how these algorithms respond to conditions like small sample sizes or differing variances. Choosing an appropriate algorithm can therefore be difficult in many cases. In this paper we propose a theoretical analysis of gene selection, in which the probability of successfully selecting differentially expressed genes, using a given ranking function, is explicitly calculated in terms of population parameters. The theory developed is applicable to any ranking function which has a known sampling distribution, or one which can be approximated analytically. In contrast to methods based on simulation, the approach presented here is computationally efficient and can be used to examine the behavior of gene selection algorithms under a wide variety of conditions, even when the number of genes involved runs into the tens of thousands. The utility of our approach is illustrated by comparing three widely-used gene selection methods.

Algorithms↗
PubMed2004

Adaptive BCI based on variational Bayesian Kalman filtering: an empirical evaluation.

This paper proposes the use of variational Kalman filtering as an inference technique for adaptive classification in a brain computer interface (BCI). The proposed algorithm translates electroencephalogram segments adaptively into probabilities of cognitive states. It, thus, allows for nonstationarities in the joint process over cognitive state and generated EEG which may occur during a consecutive number of trials. Nonstationarities may have technical reasons (e.g., changes in impedance between scalp and electrodes) or be caused by learning effects in subjects. We compare the performance of the proposed method against an equivalent static classifier by estimating the generalization accuracy and the bit rate of the BCI. Using data from two studies with healthy subjects, we conclude that adaptive classification significantly improves BCI performance. Averaging over all subjects that participated in the respective study, we obtain, depending on the cognitive task pairing, an increase both in generalization accuracy and bit rate of up to 8%. We may, thus, conclude that adaptive inference can play a significant contribution in the quest of increasing bit rates and robustness of current BCI technology. This is especially true since the proposed algorithm can be applied in real time.

Algorithms↗
PubMed2004

Cognitive tasks for driving a brain-computer interfacing system: a pilot study.

Different cognitive tasks were investigated for use with a brain-computer interface (BCI). The main aim was to evaluate which two of several candidate tasks lead to patterns of electroencephalographic (EEG) activity that could be differentiated most reliably and, therefore, produce the highest communication rate. An optimal signal processing method was also sought to enhance differentiation of EEG profiles across tasks. In ten normal subjects (five male), aged 29-54 years, EEG activity was recorded from four channels during cognitive tasks grouped in pairs, and performed alternately. Four imagery tasks were: spatial navigation around a familiar environment; auditory imagery of a familiar tune; and right and left motor imagery of opening and closing the hand. Signal processing methodology included autoregressive (AR) modeling and classification based on logistic regression and a nonlinear generative classifier. The highest communication rate was found using the navigation and auditory imagery tasks. In terms of classification performance and, hence, possible communication rate, these results were significantly better (p < 0.05) than those obtained with the classical pairing of motor tasks involving imaginary movements of the left and right hands. In terms of EEG data analysis, a nonlinear classification model provided more robust results than a linear model (p << 0.01), and a lower AR model order than those used in previous work was found to be effective. These findings have implications for establishing appropriate methods to operate BCI systems, particularly for disabled people who may experience difficulty with motor tasks, even motor imagery.

Adult↗
PubMed2004

A theoretical analysis of gene selection.

A great deal of recent research has focused on the challenging task of selecting differentially expressed genes from microarray data ('gene selection'). Numerous gene selection algorithms have been proposed in the literature, but it is often unclear exactly how these algorithms respond to conditions like small sample-sizes or differing variances. Choosing an appropriate algorithm can therefore be difficult in many cases. In this paper we propose a theoretical analysis of gene selection, in which the probability of successfully selecting relevant genes, using a given gene ranking function, is explicitly calculated in terms of population parameters. The theory developed is applicable to any ranking function which has a known sampling distribution, or one which can be approximated analytically. In contrast to empirical methods, the analysis can easily be used to examine the behaviour of gene selection algorithms under a wide variety of conditions, even when the numbers of genes involved runs into the tens of thousands. The utility of our approach is illustrated by comparing three well-known gene ranking functions.

Algorithms↗