Comparison of decision tree, support vector machines, and Bayesian network approaches for classification of falls in Parkinson’s disease

Being able to accurately predict the risk of falling is crucial in patients with Parkinson’s dis- ease (PD). This is due to the unfavorable effect of falls, which can lower the quality of life as well as directly impact on survival. Three methods considered for predicting falls are decision trees (DT), Bayesian networks (BN), and support vector machines (SVM). Data on a 1-year prospective study conducted at IHBI, Australia, for 51 people with PD are used. Data processing are conducted using rpart and e1071 packages in R for DT and SVM, con- secutively; and Bayes Server 5.5 for the BN. The results show that BN and SVM produce consistently higher accuracy over the 12 months evaluation time points (average sensitivity and specificity > 92%) than DT (average sensitivity 88%, average specificity 72%). DT is prone to imbalanced data so needs to adjust for the misclassification cost. However, DT provides a straightforward, interpretable result and thus is appealing for helping to identify important items related to falls and to generate fallers’ profiles.

Directional dominance on stature and cognition in diverse human populations

Homozygosity has long been associated with rare, often devastating, Mendelian disorders1, and Darwin was one of the first to recognize that inbreeding reduces evolutionary fitness2. However, the effect of the more distant parental relatedness that is common in modern human populations is less well understood. Genomic data now allow us to investigate the effects of homozygosity on traits of public health importance by observing contiguous homozygous segments (runs of homozygosity), which are inferred to be homozygous along their complete length. Given the low levels of genome-wide homozygosity prevalent in most human populations, information is required on very large numbers of people to provide sufficient power3, 4. Here we use runs of homozygosity to study 16 health-related quantitative traits in 354,224 individuals from 102 cohorts, and find statistically significant associations between summed runs of homozygosity and four complex traits: height, forced expiratory lung volume in one second, general cognitive ability and educational attainment (P < 1 × 10−300, 2.1 × 10−6, 2.5 × 10−10 and 1.8 × 10−10, respectively). In each case, increased homozygosity was associated with decreased trait value, equivalent to the offspring of first cousins being 1.2 cm shorter and having 10 months’ less education. Similar effect sizes were found across four continental groups and populations with different degrees of genome-wide homozygosity, providing evidence that homozygosity, rather than confounding, directly contributes to phenotypic variance. Contrary to earlier reports in substantially smaller samples5, 6, no evidence was seen of an influence of genome-wide homozygosity on blood pressure and low density lipoprotein cholesterol, or ten other cardio-metabolic traits. Since directional dominance is predicted for traits under directional evolutionary selection7, this study provides evidence that increased stature and cognitive function have been positively selected in human evolution, whereas many important risk factors for late-onset complex diseases may not have been.

Impact of exercise selection on hamstring muscle activation

Objective: To determine the extent to which different strength training exercises selectively activate the commonly injured biceps femoris long head (BFLH) muscle. Methods: This two-part observational study recruited 24 recreationally active males. Part 1 explored the amplitudes and the ratios of lateral to medial hamstring (BF/MH) normalised electromyography (nEMG) during the concentric and eccentric phases of 10 common strength training exercises. Part 2 used functional magnetic resonance imaging (fMRI) to determine the spatial patterns of hamstring activation during two exercises which i) most selectively, and ii) least selectively activated the BF in part 1. Results: Eccentrically, the largest BF/MH nEMG ratio was observed in the 45° hip extension exercise and the lowest was observed in the Nordic hamstring (NHE) and bent-knee bridge exercises. Concentrically, the highest BF/MH nEMG ratio was observed during the lunge and 45° hip extension and the lowest was observed for the leg curl and bent-knee bridge. fMRI revealed a greater BFLH to semitendinosus activation ratio in the 45° hip extension than the NHE (p<0.001). The T2 increase after hip extension for BFLH, semitendinosus and semimembranosus muscles were greater than that for BFSH (p<0.001). During the NHE, the T2 increase was greater for the semitendinosus than for the other hamstrings (p≤0.002). Conclusion: This investigation highlights the non-uniformity of hamstring activation patterns in different tasks and suggests that hip extension exercise more selectively activates the BFLH while the NHE preferentially recruits the semitendinosus. These findings have implications for strength training interventions aimed at preventing hamstring injury.

Evaluating the effectiveness of a self-management exercise intervention on wound healing, functional ability and health-related quality of life outcomes in adults with venous leg ulcers: a randomised controlled trial

Exercise that targets ankle joint mobility may lead to improvement in calf muscle pump function and subsequent healing. The objectives of this research were to assess the impact of an exercise intervention in addition to routine evidence-based care on the healing rates, functional ability and health-related quality of life for adults with venous leg ulcers (VLUs). This study included 63 patients with VLUs. Patients were randomised to receive either a 12-week exercise intervention with a telephone coaching component or usual care plus telephone calls at the same timepoints. The primary outcome evaluated the effectiveness of the intervention in relation to wound healing. The secondary outcomes evaluated physical activity, functional ability and health-related quality of life measures between groups at the end of the 12 weeks. A per protocol analysis complemented the effectiveness (intention-to-treat) analysis to highlight the importance of adherence to an exercise intervention. Intention-to-treat analyses for the primary outcome showed 77% of those in the intervention group healed by 12 weeks compared to 53% of those in the usual care group. Although this difference was not statistically significant due to a smaller than expected sample size, a 24% difference in healing rates could be considered clinically significant. The per protocol analysis for wound healing, however, showed that those in the intervention group who adhered to the exercise protocol 75% or more of the time were significantly more likely to heal and showed higher rates for wound healing than the control group (P = 0·01), that is, 95% of those who adhered in the intervention group healed in 12 weeks. The secondary outcomes of physical activity, functional ability and health-related quality of life were not significantly altered by the intervention. Among the secondary outcomes (physical activity, functional ability and health-related quality of life), intention-to-treat analyses did not support the effectiveness of the intervention. However, per protocol analyses revealed encouraging results with those participants who adhered more than 75% of the time (n = 19) showing significantly improved Range of Ankle Motion from the self-management exercise programme (P = 0·045). This study has shown that those participants who adhere to the exercise programme as an adjunctive treatment to standard care are more likely to heal and have better functional outcomes than those who do not adhere to the exercises in conjunction with usual care.