Gaussian Bayesian network comparisons with graph ordering unknown

A Bayesian network perspective on neonatal pneumonia in pregnant women with diabetes mellitus

OBJECTIVE

To predict the influencing factors of neonatal pneumonia in pregnant women with diabetes mellitus using a Bayesian network model. By examining the intricate network connections between the numerous variables given by Bayesian networks (BN), this study aims to compare the prediction effect of the Bayesian network model and to analyze the influencing factors directly associated to neonatal pneumonia.

METHOD

Through the structure learning algorithms of BN, Naive Bayesian (NB), Tree Augmented Naive Bayes (TAN), and k-Dependence Bayesian Classifier (KDB), complex networks connecting variables were presented and their predictive abilities were tested. The BN model and three machine learning models computed using the R bnlean package were also compared in the data set.

RESULTS

In constraint-based algorithms, three algorithms had different presentation DAGs. KDB had a better prediction effect than NB and TAN, and it achieved higher AUC compared with TAN. Among three machine learning modes, Support Vector Machine showed a accuracy rate of 91.04% and 67.88% of precision, which was lower than TAN (92.70%; 72.10%).

CONCLUSION

KDB was applicable, and it can detect the dependencies between variables, identify more potential associations and track changes between variables and outcome.

The role of epigenetics in multi-generational transmission of asthma: An NIAID workshop report-based narrative review

There is mounting evidence that environmental exposures can result in effects on health that can be transmitted across generations, without the need for a direct exposure to the original factor, for example, the effect of grandparental smoking on grandchildren. Hence, an individual's health should be investigated with the knowledge of cross-generational influences. Epigenetic factors are molecular factors or processes that regulate genome activity and may impact cross-generational effects. Epigenetic transgenerational inheritance has been demonstrated in plants and animals, but the presence and extent of this process in humans are currently being investigated. Experimental data in animals support transmission of asthma risk across generations from a single exposure to the deleterious factor and suggest that the nature of this transmission is in part due to changes in DNA methylation, the most studied epigenetic process. The association of father's prepuberty exposure with offspring risk of asthma and lung function deficit may also be mediated by epigenetic processes. Multi-generational birth cohorts are ideal to investigate the presence and impact of transfer of disease susceptibility across generations and underlying mechanisms. However, multi-generational studies require recruitment and assessment of participants over several decades. Investigation of adult multi-generation cohorts is less resource intensive but run the risk of recall bias. Statistical analysis is challenging given varying degrees of longitudinal and hierarchical data but path analyses, structural equation modelling and multilevel modelling can be employed, and directed networks addressing longitudinal effects deserve exploration as an effort to study causal pathways.