Narrow Results

Random forest is an ensemble classification algorithm. It performs well when most predictive variables are noisy and can be used when the number of variables is much larger than the number of observations. The use of bootstrap samples and restricted subsets of attributes makes it more powerful than simple ensembles of trees. The main advantage of a random forest classifier is its explanatory power: it measures variable importance or impact of each factor on a predicted class label. These characteristics make the algorithm ideal for microarray data. It was shown to build models with high accuracy when tested on high-dimensional microarray datasets. Current implementations of random forest in the machine learning and statistics community, however, limit its usability for mining over large datasets, as they require that the entire dataset remains permanently in memory. We propose a new framework, an optimized implementation of a random forest classifier, which addresses specific properties of microarray data, takes computational complexity of a decision tree algorithm into consideration, and shows excellent computing performance while preserving predictive accuracy. The implementation is based on reducing overlapping computations and eliminating dependency on the size of main memory. The implementation's excellent computational performance makes the algorithm useful for interactive data analyses and data mining.

There is little consensus about which objective markers should be used to assess major psychiatric disorders, and predict/evaluate treatment response for these disorders. Clinical practice relies instead on subjective signs and symptoms, such that there is a "translational gap" between research findings and clinical practice. This gap arises from: a) a lack of integrative theoretical models which provide a basis for understanding links between gene-brain-behavior mechanisms and clinical entities; b) the reliance on studying one measure at a time so that linkages between markers are their specificity are not established; and c) the lack of a definitive understanding of what constitutes normative function. Here, we draw on a standardized methodology for acquiring multiple sources of genomic, brain and behavioral data in the same subjects, to propose candidate markers of selected psychiatric disorders: depression, post-traumatic stress disorder, schizophrenia, attention-deficit/hyperactivity disorder and dementia disorders. This methodology has been used to establish a standardized international database which provides a comprehensive framework and the basis for testing hypotheses derived from an integrative theoretical model of the brain. Using this normative base, we present preliminary findings for a number of disorders in relation to the proposed markers. Establishing these objective markers will be the first step towards determining their sensitivity, specificity and treatment prediction in individual patients.