Markov blanket-based approach for learning multi-dimensional Bayesian network classifiers: An application to predict the European Quality of Life-5 Dimensions (EQ-5D) from the 39-item Parkinson's Disease Questionnaire (PDQ-39)

Multi-dimensional Bayesian network classifiers (MBCs) are probabilistic graphical models recently proposed to deal with multi-dimensional classification problems, where each instance in the data set has to be assigned to more than one class variable. In this paper, we propose a Markov blanket-based approach for learning MBCs from data. Basically, it consists of determining the Markov blanket around each class variable using the HITON algorithm, then specifying the directionality over the MBC subgraphs. Our approach is applied to the prediction problem of the European Quality of Life-5 Dimensions (EQ-5D) from the 39-item Parkinson’s Disease Questionnaire (PDQ-39) in order to estimate the health-related quality of life of Parkinson’s patients. Fivefold cross-validation experiments were carried out on randomly generated synthetic data sets, Yeast data set, as well as on a real-world Parkinson’s disease data set containing 488 patients. The experimental study, including comparison with additional Bayesian network-based approaches, back propagation for multi-label learning, multi-label k-nearest neighbor, multinomial logistic regression, ordinary least squares, and censored least absolute deviations, shows encouraging results in terms of predictive accuracy as well as the identification of dependence relationships among class and feature variables.

Changes in rumen microbes in sheep in response to dietary forage quality and relationships with fermentation characteristics

An in vitro experiment was carried out using the Hohenheim gas production technique to evaluate 24-h gas production, apparently and truly degraded dry matter (DM), partitioning factor (PF), short chain fatty acids, crude protein (CP) and carbohydrate (CHO) fractionation of grass and multipurpose tree species (MPTS) foliage diets. Four grasses and three MPTS were used to formulate 12 diets of equal mixtures (0.5:0.5 on DM basis) of each grass with each MPTS. In vitro gas production was terminated after 24 h for each diet. True DM degradability was measured from incubated samples and combined with gas volume to estimate PF. Diets had greater (P<0.001) CP (102–183 g/kg DM) content than sole grasses (66–131 g/kg DM) and lower (P<0.001) concentrations of fibre fractions. Contrary to in vitro apparently degraded DM, in vitro truly degraded DM coefficient was greater (P<0.001) in diets (0.63–0.77) than in sole grasses (0.48–0.68). The PF was on average higher in diets than in sole grasses. The proportion of potentially degradable CP fractions (A1, B1, B2 and B3, based on the Cornell Net Carbohydrate and Protein System) in the diets ranged from 971 to 989 g/kg CP. Crude protein fractions, A and B2 were greater in diets but B1 and B3 fractions were less in diets than in sole grasses. A similar trend was also observed in the CHO fractions. Results showed that the nutritive value of the four grasses was improved when MPTS leaves were incorporated into the diet and this could ensure higher productivity of the animals.