Altered relaxation times in MRI indicate bronchopulmonary dysplasia.

We developed a MRI protocol using transverse (T2) and longitudinal (T1) mapping sequences to characterise lung structural changes in preterm infants with bronchopulmonary dysplasia (BPD). We prospectively enrolled 61 infants to perform 3-Tesla MRI of the lung in quiet sleep. Statistical analysis was performed using logistic Group Lasso regression and logistic regression. Increased lung T2 relaxation time and decreased lung T1 relaxation time indicated BPD yielding an area under the curve (AUC) of 0.80. Results were confirmed in an independent study cohort (AUC 0.75) and mirrored by lung function testing, indicating the high potential for MRI in future BPD diagnostics. TRIAL REGISTRATION: DRKS00004600.

Modeling of radon exhalation from soil influenced by environmental parameters.

Atmospheric radioactive noble gas radon (Rn-222) originates from soil gas exhaled in the atmospheric surface layer. Radon exhalation rates from soil as well as corresponding meteorological and soil parameters were recorded for two subsequent years. Based on long-term field data, a statistical regression model for the radon exhalation and the most important influencing parameters soil water content, temperature of soil and air, air pressure and autocorrelation of the exhalation rate was established. The fitting result showed that the multivariate model can explain up to 61% of the variation of the exhalation rate. First, the exhalation rate increases up to 80 Bq m-2 h-1 with increasing soil water content. Later, at water content >10%, increasing soil wetness suppressed the exhalation rate: at values higher than 24% to approximately one third. The air temperature had a distinct positive effect while the soil temperature had a strong negative effect on the exhalation rate, indicating their different influencing-mechanisms on the exhalation. The air pressure was negligible. The lagged values of radon exhalation had to be included in the model, as the variable shows strong autocorrelation.

Making complex prediction rules applicable for readers: Current practice in random forest literature and recommendations.

Ideally, prediction rules should be published in such a way that readers may apply them, for example, to make predictions for their own data. While this is straightforward for simple prediction rules, such as those based on the logistic regression model, this is much more difficult for complex prediction rules derived by machine learning tools. We conducted a survey of articles reporting prediction rules that were constructed using the random forest algorithm and published in PLOS ONE in 2014-2015 in the field "medical and health sciences", with the aim of identifying issues related to their applicability. Making a prediction rule reproducible is a possible way to ensure that it is applicable; thus reproducibility is also examined in our survey. The presented prediction rules were applicable in only 2 of 30 identified papers, while for further eight prediction rules it was possible to obtain the necessary information by contacting the authors. Various problems, such as nonresponse of the authors, hampered the applicability of prediction rules in the other cases. Based on our experiences from this illustrative survey, we formulate a set of recommendations for authors who aim to make complex prediction rules applicable for readers. All data including the description of the considered studies and analysis codes are available as supplementary materials.