Common component classification: what can we learn from machine learning?

Machine learning methods have been applied to classifying fMRI scans by studying locations in the brain that exhibit temporal intensity variation between groups, frequently reporting classification accuracy of 90% or better. Although empirical results are quite favorable, one might doubt the ability of classification methods to withstand changes in task ordering and the reproducibility of activation patterns over runs, and question how much of the classification machines' power is due to artifactual noise versus genuine neurological signal. To examine the true strength and power of machine learning classifiers we create and then deconstruct a classifier to examine its sensitivity to physiological noise, task reordering, and across-scan classification ability. The models are trained and tested both within and across runs to assess stability and reproducibility across conditions. We demonstrate the use of independent components analysis for both feature extraction and artifact removal and show that removal of such artifacts can reduce predictive accuracy even when data has been cleaned in the preprocessing stages. We demonstrate how mistakes in the feature selection process can cause the cross-validation error seen in publication to be a biased estimate of the testing error seen in practice and measure this bias by purposefully making flawed models. We discuss other ways to introduce bias and the statistical assumptions lying behind the data and model themselves. Finally we discuss the complications in drawing inference from the smaller sample sizes typically seen in fMRI studies, the effects of small or unbalanced samples on the Type 1 and Type 2 error rates, and how publication bias can give a false confidence of the power of such methods. Collectively this work identifies challenges specific to fMRI classification and methods affecting the stability of models.

Brain networks underlying perceptual habituation to repeated aversive visceral stimuli in patients with irritable bowel syndrome.

Patients with irritable bowel syndrome (IBS) show decreased discomfort and pain thresholds to visceral stimuli, as well hypervigilance to gastrointestinal sensations, symptoms, and the context in which these visceral sensations and symptoms occur. Previous research demonstrated normalization of visceral hypersensitivity following repeated exposure to experimental rectal stimuli over a 12-month period that was associated with reduction in cortical regions functionally associated with attention and arousal. Building upon these functional analyses, multivariate functional and effective connectivity analyses were applied to [(15)O] water positron emission tomography (PET) data from 12 IBS patients (male=4) participating in a PET study before and after 4 visceral sensory testing sessions involving rectal balloon distensions over a 1-year period. First, behavioral partial least squares was applied to test for networks related to reduced subjective ratings observed following repeated application of an aversive rectal stimulus. Next, path analysis within a structural equation modeling framework tested the hypothesis that perceptual habituation to the repeated visceral stimuli resulted in part from the reduced connectivity within a selective attention to threat network over time. Two independent, perception-related networks comprised of interoceptive, attentional and arousal regions were engaged differentially during expectation and distension. In addition, changes in the effective connectivity of an attentional network as well as modulatory amygdala influence suggested that perceptual habituation associated with repeated stimulus delivery results both in an increase in top-down modulation of attentional circuits, as well as in a reduction of amygdala-related interference with attentional mechanisms.

Does the Clock Drawing Test have focal neuroanatomical correlates?

The Clock Drawing Test (CDT) is widely used in clinical neuropsychological practice. The CDT has been used traditionally as a "parietal lobe" test (e.g., Kaplan, 1988), but most empirical work has focused on its sensitivity and specificity for detecting and differentiating subtypes of dementia. There are surprisingly few studies of its neuroanatomical correlates. The authors investigated the neuroanatomical correlates of the CDT, using 133 patients whose lesions provided effective coverage of most of both hemispheric convexities and underlying white matter. On the CDT, 30 subjects were impaired and 87 were unimpaired (16 were "borderline"). Impairments on the CDT were associated with damage to right parietal cortices (supramarginal gyrus) and left inferior frontal-parietal opercular cortices. Visuospatial errors were predominant in patients with right hemisphere damage, whereas time setting errors were predominant in patients with left hemisphere lesions. These findings provide new empirical evidence regarding the neuroanatomical correlates of the CDT, and together with previous work, support the use of this quick and easily administered test not only as a screening measure but also as a good index of focal brain dysfunction.

Increased feelings with increased body signals.

Since the beginning of psychology as a scientific endeavour, the question of whether the body plays a role in how a person experiences emotion has been the centre of emotion research. Patients with structural gastrointestinal disorders, such as Crohn's disease, provide an intriguing opportunity to study the influence of body signals on emotions and feelings. In the present study, emotionally salient films were presented to participants with Crohn's disease in either the active state (Crohn's-active, CA) or silent state (Crohn's-silent, CS), and to normal comparison (NC) participants. We hypothesized that CA participants would have increased feelings, compared with CS and NC participants, when viewing emotional films designed to elicit happiness, disgust, sadness and fear. Gastric myoelectrical activity (electrogastrogram, or EGG) was measured during the films, and after each film was presented, participants rated emotion intensity (arousal) and pleasantness (valence). All groups labelled the emotions similarly. In support of the hypothesis, CA participants showed an increase in subjective arousal for negative emotions compared with CS and NC participants. The CA participants also showed increased EGG during emotional film viewing, as well as a strong positive correlation of EGG with arousal ratings. Together, these findings can be taken as evidence that aberrant feedback from the gastrointestinal system up-regulates the intensity of feelings of negative emotions.