Gender-specific genomic profiling in metastatic colorectal cancer patients treated with 5-fluorouracil and oxaliplatin

AIMS: Survival and response rates in metastatic colorectal cancer remain poor, despite advances in drug development. There is increasing evidence to suggest that gender-specific differences may contribute to poor clinical outcome. We tested the hypothesis that genomic profiling of metastatic colorectal cancer is dependent on gender.

MATERIALS & METHODS: A total of 152 patients with metastatic colorectal cancer who were treated with oxaliplatin and continuous infusion 5-fluorouracil were genotyped for 21 polymorphisms in 13 cancer-related genes by PCR. Classification and regression tree analysis tested for gender-related association of polymorphisms with overall survival, progression-free survival and tumor response.

RESULTS: Classification and regression tree analysis of all polymorphisms, age and race resulted in gender-specific predictors of overall survival, progression-free survival and tumor response. Polymorphisms in the following genes were associated with gender-specific clinical outcome: estrogen receptor β, EGF receptor, xeroderma pigmentosum group D, voltage-gated sodium channel and phospholipase A2.

CONCLUSION: Genetic profiling to predict the clinical outcome of patients with metastatic colorectal cancer may depend on gender.

Predicting forest attributes In southeast Alaska using artificial neural networks

Artificial neural network (ANN) methods are used to predict forest characteristics. The data source is the Southeast Alaska (SEAK) Grid Inventory, a ground survey compiled by the USDA Forest Service at several thousand sites. The main objective of this article is to predict characteristics at unsurveyed locations between grid sites. A secondary objective is to evaluate the relative performance of different ANNs. Data from the grid sites are used to train six ANNs: multilayer perceptron, fuzzy ARTMAP, probabilistic, generalized regression, radial basis function, and learning vector quantization. A classification and regression tree method is used for comparison. Topographic variables are used to construct models: latitude and longitude coordinates, elevation, slope, and aspect. The models classify three forest characteristics: crown closure, species land cover, and tree size/structure. Models are constructed using n-fold cross-validation. Predictive accuracy is calculated using a method that accounts for the influence of misclassification as well as measuring correct classifications. The probabilistic and generalized regression networks are found to be the most accurate. The predictions of the ANN models are compared with a classification of the Tongass national forest in southeast Alaska based on the interpretation of satellite imagery and are found to be of similar accuracy.

Root Cause Analysis by a Combined Sparse Classification and Monte Carlo Approach

Classification methods with embedded feature selection capability are very appealing for the analysis of complex processes since they allow the analysis of root causes even when the number of input variables is high. In this work, we investigate the performance of three techniques for classification within a Monte Carlo strategy with the aim of root cause analysis. We consider the naive bayes classifier and the logistic regression model with two different implementations for controlling model complexity, namely, a LASSO-like implementation with a L1 norm regularization and a fully Bayesian implementation of the logistic model, the so called relevance vector machine. Several challenges can arise when estimating such models mainly linked to the characteristics of the data: a large number of input variables, high correlation among subsets of variables, the situation where the number of variables is higher than the number of available data points and the case of unbalanced datasets. Using an ecological and a semiconductor manufacturing dataset, we show advantages and drawbacks of each method, highlighting the superior performance in term of classification accuracy for the relevance vector machine with respect to the other classifiers. Moreover, we show how the combination of the proposed techniques and the Monte Carlo approach can be used to get more robust insights into the problem under analysis when faced with challenging modelling conditions.

The classification and diagnosis of erythrocytosis

An absolute erythrocytosis is present when the red cell mass is raised and the haematocrit is elevated above prescribed limits. Causes of an absolute erythrocytosis can be primary where there is an intrinsic problem in the bone marrow and secondary where there an event outside the bone marrow driving erythropoiesis. This can further be divided into congenital and acquired causes. There remain an unexplained group idiopathic erythrocytosis. Investigation commencing with thorough history taking and examination and then investigation depending on initial features is required. Clear simple criteria for polycythaemia vera are now defined. Those who do not fulfil these criteria require further investigation depending on the clinical scenario and initial results. The erythropoietin level provides some guidance as to the direction in which to proceed and the order and extent of investigation necessary in an individual patient. It should thus be possible to make an accurate diagnosis in the majority of patients.