Application and comparison of classification algorithms for recognition of Alzheimer's disease in electrical brain activity (EEG)

The early detection of subjects with probable Alzheimer's disease (AD) is crucial for effective appliance of treatment strategies. Here we explored the ability of a multitude of linear and non-linear classification algorithms to discriminate between the electroencephalograms (EEGs) of patients with varying degree of AD and their age-matched control subjects. Absolute and relative spectral power, distribution of spectral power, and measures of spatial synchronization were calculated from recordings of resting eyes-closed continuous EEGs of 45 healthy controls, 116 patients with mild AD and 81 patients with moderate AD, recruited in two different centers (Stockholm, New York). The applied classification algorithms were: principal component linear discriminant analysis (PC LDA), partial least squares LDA (PLS LDA), principal component logistic regression (PC LR), partial least squares logistic regression (PLS LR), bagging, random forest, support vector machines (SVM) and feed-forward neural network. Based on 10-fold cross-validation runs it could be demonstrated that even tough modern computer-intensive classification algorithms such as random forests, SVM and neural networks show a slight superiority, more classical classification algorithms performed nearly equally well. Using random forests classification a considerable sensitivity of up to 85% and a specificity of 78%, respectively for the test of even only mild AD patients has been reached, whereas for the comparison of moderate AD vs. controls, using SVM and neural networks, values of 89% and 88% for sensitivity and specificity were achieved. Such a remarkable performance proves the value of these classification algorithms for clinical diagnostics.

Influence of physical activity and acute exercise on cognitive performance and saliva testosterone in preadolescent school children

We investigated whether the chronic physical activity participation had an impact on the acute effects of a short bout of 12 min of intensive physical activity on cognitive performance and testosterone concentration in primary school students (n = 42, mean age = 9.69, SD = .44; experimental group (EG), n = 27; control group (CG), n = 15). Furthermore, we looked for associations between testosterone concentration and cognitive performance. After the intervention, participants of the EG showed better cognitive performances as compared to the CG. We further observed a significant group (EG, CG) test (pre, post) activity level (high, low) interaction. Post hoc pairwise comparisons revealed that after acute physical activity the testosterone concentration was diminished only in habitually low active children. The results indicate that intensive physical activity only attenuates the reactivity of the hypothalamic-pituitary-gonadal axis in habitually low active preadolescents, but had a beneficial effect on cognitive performance for all participants independent of their physical activity level and testosterone.

Exercise capacity, physical activity patterns and outcomes six years after cardiac rehabilitation in patients with heart failure.

OBJECTIVE To determine the short- and long-term effects of an intensive, concentrated rehabilitation programme in patients with chronic heart failure. DESIGN Randomized controlled trial, with one-month and six-year evaluations. SETTING Residential rehabilitation centre in Switzerland. SUBJECTS Fifty patients with chronic heart failure, randomized to exercise or control groups. INTERVENTIONS A rehabilitation programme lasting one month, including educational sessions, a low-fat diet, and 2 hours of individually prescribed exercise daily. MAIN MEASURES Exercise test responses, health outcomes and physical activity patterns. RESULTS Peak Vo(2) increased 21.4% in the exercise group during the rehabilitation programme (P<0.05), whereas peak Vo(2) did not change among controls. After the six-year follow-up period, peak Vo(2) was only slightly higher than that at baseline in the trained group (7%, NS), while peak Vo(2) among controls was unchanged. During long-term follow-up, 9 and 12 patients died in the exercise and control groups, respectively (P = 0.63). At six years, physical activity patterns tended to be higher in the exercise group; the mean energy expenditure values over the last year were 2,704 +/- 1,970 and 2,085 +/- 1,522 kcal/week during recreational activities for the exercise and control groups, respectively. However, both groups were more active compared to energy expenditure prior to their cardiac event (P<0.001). CONCLUSIONS Six years after participation in a residential rehabilitation programme, patients with chronic heart failure had slightly better outcomes than control subjects, maintained exercise capacity and engaged in activities that exceed the minimal amount recommended by guidelines for cardiovascular health.