Bioimpedance analysis of body composition in the diagnosis of physical development disorders in children and adolescents

Traditionally, anthropometric method is used in clinical practice for the diagnosis of excess body weight. Obesity is the excess development of primarily visceral and subcutaneous adipose tissue, which can be diagnosed by bioimpedance analysis (BIA). The study was aimed to assess the role of BIA of body composition in the diagnosis of the physical development disorders in children and adolescents. Anthropometric assessment and BIA were performed in 431 Samara school students aged 12–16 of the health status groups I and II (230 boys and 201 girls). The results were analyzed with the use of the regional regression scores, BAZ indices, and the body fat percentage values. The results of estimation using the regression scores showed that 22.61% of boys and 23.43% of girls were overweight, while more than 2/3 of the sample had a normal pattern of physical development. The BAZ indices revealed a significantly higher proportion of overweight children among boys (25.7%), than among girls (11.5%, p < 0.01). The body fat percentage fluctuations based on the BIA data were found not only in children with disharmonious physical development, but also in 60% of children with normal body weight. Moreover, the data of BIA confirmed the body weight fluctuations, revealed with the use of the regression scores, in the significantly larger number of cases compared to the low body weight and excess body weight, diagnosed based on the BAZ indices. Accordingly, anthropometric analysis with the use of the regional regression scores may be used at the baseline for the early diagnosis of the nutritional status disorders in children. To confirm overweight and obesity in children, as well as to provide further treatment, the reliable method for estimation of the body fat content is required, which may be the method of BIA.

Quantifying the Regional Water Balance of the Ethiopian Rift Valley Lake Basin Using an Uncertainty Estimation Framework

In Ethiopia more than 80 % of big freshwater lakes are located in the Rift Valley Lake Basin (RVLB), serving over 15 million people a multipurpose water supply. The basin covers an area of 53,035 km2, and most of the catchments recharging these lakes are ungauged and their water balance is not well quantified, hence limiting the development of appropriate water resource management strategies. Prediction for ungauged basins (PUB) has demonstrated its effectiveness in hydro-climatic data-rich regions. However, these approaches are not well evaluated in climatic data-limited conditions and the consequent uncertainty is not adequately quantified. In this study we use the Hydrologiska Byråns Vattenbalansavdelning (HBV) model to simulate streamflow at a regional scale using global precipitation and potential evapotranspiration products as forcings. We develop and apply a Monte-Carlo scheme to estimate model parameters and quantify uncertainty at 16 catchments in the basin where gauging stations are available. Out of these 16, we use the 14 most reliable catchments to derive the best regional regression model. We use three different strategies to extract possible parameter sets for regionalization by correlating the best calibration parameters, the best validation parameters, and parameters that give the most stable predictions with catchment properties that are available throughout the basin. A weighting scheme in the regional regression accounts for parameter uncertainty in the calibration. A spatial cross-validation is applied multiple times to test the quality of the regionalization and to estimate the regionalization uncertainty. Our results show that, other than the commonly used best-calibrated parameters, the best parameter sets of the validation period provide the most robust estimates of regionalized parameters. We then apply the regionalized parameter sets to the remaining 35 ungauged catchments in the RVLB to provide regional water balance estimations, including quantifications of regionalization uncertainty. The uncertainties of elasticities from the regionalization in the ungauged catchments are higher than those obtained from the simulations in the gauged catchments. With these results, our study provides a new procedure to use global precipitation and evapotranspiration products to predict and evaluate streamflow simulation for hydro-climatically data-scarce regions considering uncertainty. This procedure enhances the confidence to understand the water balance of under-represented regions like ours and supports the planning and development of water resources.

An Uncertainty Estimation Framework to Quantify the Water Balance of Ethiopian Rift Valley Lake basin

&lt;p&gt;In Ethiopia, more than 80% of big freshwater lakes are located in the Rift Valley Lake Basin, which is serving for multipurpose water use of over 30 million people. The basin is one of the most densely populated regions in Ethiopia and it covers an area of 53,035 km&lt;sup&gt;2&lt;/sup&gt;. However, most of the catchments recharging these lakes are ungauged and their water balance is not well quantified, and hence, limiting the development of appropriate water resource management strategies. Prediction for ungauged catchments has demonstrated its effectiveness in hydro-climatic data-rich regions. However, these approaches are not well evaluated in the climatic data-limited condition and the consecutive uncertainty emerging in the small catchments is not adequately quantified. In this study, we use the HBV model to simulate streamflow using global precipitation and potential evapotranspiration products as forcings. We develop and apply a Monte-Carlo scheme to calibrate the model and quantify uncertainty at 16 catchments in the basin where gauging stations are available. Out of these, we use 14 best catchments to derive the best regional regression model by correlating the best calibration parameters, the best validation parameters, and parameters that give the most stable predictions with catchment attributes that are available throughout the basin. A weighting scheme in the regional regression accounts for parameter uncertainty in the calibration. A spatial cross-valuation that is applied 14 times always leaving out one of the gauged catchments provides 14 regional regression functions that express uncertainty regionalization. It also shows that the regionalization procedure that uses the best validation parameters for regionalization provides the most robust results. We then subsequently apply the 14 spatial regression functions of the cross-validation to the remaining 35 ungauged catchments in the Rift Valley Lake Basin to provide regional water balance estimations including quantification of regionalization uncertainty. With these results, our study provides a new procedure to use global precipitation and evapotranspiration products to predict and evaluate streamflow simulation for hydro-climatically data scares regions considering uncertainty. It, therefore, enhances the confidence in the understanding of water balance in those regions and will support the planning and development of appropriate water resource management strategies.&lt;/p&gt;&lt;p&gt;&amp;#160;&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Keywords&lt;/strong&gt;: Parameters Estimation, Uncertainties, Ungauged Catchment, Weighted Regression, Water Balance&lt;/p&gt;

Brain age prediction in schizophrenia: does the choice of machine learning algorithm matter?

BackgroundSchizophrenia has been associated with lifelong deviations in the normative trajectories of brain structure. These deviations can be captured using the brain-predicted age difference (brainPAD), which is the difference between the biological age of an individual’s brain, as inferred from neuroimaging data, and their chronological age. Various machine learning algorithms are currently used for this purpose but their comparative performance has yet to be systematically evaluated.MethodsSix linear regression algorithms, ordinary least squares (OLS) regression, ridge regression, least absolute shrinkage and selection operator (Lasso) regression, elastic-net regression, linear support vector regression (SVR), and relevance vector regression (RVR), were applied to brain structural data acquired on the same 3T scanner using identical sequences from patients with schizophrenia (n=90) and healthy individuals (n=200). The performance of each algorithm was quantified by the mean absolute error (MAE) and the correlation (R) between predicted brain-age and chronological age. The inter-algorithm similarity in predicted brain-age, brain regional regression weights and brainPAD were compared using correlation analyses and hierarchical clustering.ResultsIn patients with schizophrenia, ridge regression, Lasso regression, elastic-net regression, and RVR performed very similarly and showed a high degree of correlation in predicted brain-age (R>0.94) and brain regional regression weights (R>0.66). By contrast, OLS regression, which was the only algorithm without a penalty term, performed markedly worse and showed a lower similarity with the other algorithms. The mean brainPAD was higher in patients than in healthy individuals but varied by algorithm from 3.8 to 5.2 years although all analyses were performed on the same dataset.ConclusionsLinear machine learning algorithms, with the exception of OLS regression, have comparable performance for age prediction on the basis of a combination of cortical and subcortical structural measures. However, algorithm choice introduced variation in brainPAD estimation, and therefore represents an important source of inter-study variability.