Explore the vast range of titles available.

Handling missing values is a crucial step in preprocessing data in Machine Learning. Most available algorithms for analyzing datasets in the feature selection process and classification or estimation process analyze complete datasets. Consequently, in many cases, the strategy for dealing with missing values is to use only instances with full data or to replace missing values with a mean, mode, median, or a constant value. Usually, discarding missing samples or replacing missing values by means of fundamental techniques causes bias in subsequent analyzes on datasets. Aim : Demonstrate the positive impact of multivariate imputation in the feature selection process on datasets with missing values. Results : We compared the effects of the feature selection process using complete datasets, incomplete datasets with missingness rates between 5 and 50%, and imputed datasets by basic techniques and multivariate imputation. The feature selection algorithms used are well-known methods. The results showed that the datasets imputed by multivariate imputation obtained the best results in feature selection compared to datasets imputed by basic techniques or non-imputed incomplete datasets. Conclusions : Considering the results obtained in the evaluation, applying multivariate imputation by MICE reduces bias in the feature selection process.

Background Feature selection methods aim at identifying a subset of features that improve the prediction performance of subsequent classification models and thereby also simplify their interpretability. Preceding studies demonstrated that single feature selection methods can have specific biases, whereas an ensemble feature selection has the advantage to alleviate and compensate for these biases. Results The software EFS (Ensemble Feature Selection) makes use of multiple feature selection methods and combines their normalized outputs to a quantitative ensemble importance. Currently, eight different feature selection methods have been integrated in EFS, which can be used separately or combined in an ensemble. Conclusion EFS identifies relevant features while compensating specific biases of single methods due to an ensemble approach. Thereby, EFS can improve the prediction accuracy and interpretability in subsequent binary classification models. Availability EFS can be downloaded as an R-package from CRAN or used via a web application at http://EFS.heiderlab.de .

Feature selection (FS) has attracted the attention of many researchers in the last few years due to the increasing sizes of datasets, which contain hundreds or thousands of columns (features). Typically, not all columns represent relevant values. Consequently, the noise or irrelevant columns could confuse the algorithms, leading to a weak performance of machine learning models. Different FS algorithms have been proposed to analyze highly dimensional datasets and determine their subsets of relevant features to overcome this problem. However, very often, FS algorithms are biased by the data. Thus, methods for ensemble feature selection (EFS) algorithms have become an alternative to integrate the advantages of single FS algorithms and compensate for their disadvantages. The objective of this research is to propose a conceptual and implementation framework to understand the main concepts and relationships in the process of aggregating FS algorithms and to demonstrate how to address FS on datasets with high dimensionality. The proposed conceptual framework is validated by deriving an implementation framework, which incorporates a set of Phyton packages with functionalities to support the assembly of feature selection algorithms. The performance of the implementation framework was demonstrated in several experiments discovering relevant features in the Sonar, SPECTF, and WDBC datasets. The experiments contrasted the accuracy of two machine learning classifiers (decision tree and logistic regression), trained with subsets of features generated either by single FS algorithms or the set of features selected by the ensemble feature selection framework. We observed that for the three datasets used (Sonar, SPECTF, and WD), the highest precision percentages (86.95%, 74.73%, and 93.85%, respectively) were obtained when the classifiers were trained with the subset of features generated by our framework. Additionally, the stability of the feature sets generated using our ensemble method was evaluated. The results showed that the method achieved perfect stability for the three datasets used in the evaluation.

We present the package prosper_nn, that provides four neural network architectures dedicated to time series forecasting, implemented in PyTorch. In addition, prosper_nn contains the first sensitivity analysis suitable for recurrent neural networks (RNN) and a heatmap to visualize forecasting uncertainty, which was previously only available in Java. These models and methods have successfully been in use in industry for two decades and were used and referenced in several scientific publications. However, only now we make them publicly available on GitHub, allowing researchers and practitioners to benchmark and further develop them. The package is designed to make the models easily accessible, thereby enabling research and application in various fields like demand and macroeconomic forecasting.

The liver plays a critical role in integrating and controlling glucose metabolism. Thus, it is important that the liver receive and react to signals from other tissues regarding the nutrient status of the body. Leptin, which is produced and secreted from adipose tissue, is a hormone that relays information regarding the status of adipose depots to other parts of the body. Leptin has a profound influence on glucose metabolism, so we sought to determine if leptin may exert this effect in part through the liver. To explore this possibility, we created mice that have disrupted hepatic leptin signaling using a Cre-lox approach and then investigated aspects of glucose metabolism in these animals. The loss of hepatic leptin signaling did not alter body weight, body composition, or blood glucose levels in the mild fasting or random-fed state. However, mice with ablated hepatic leptin signaling had increased lipid accumulation in the liver. Further, as male mice aged or were fed a high-fat diet, the loss of hepatic leptin signaling protected the mice from glucose intolerance. Moreover, the mice displayed increased liver insulin sensitivity and a trend toward enhanced glucose-stimulated plasma insulin levels. Consistent with increased insulin sensitivity, mice with ablated hepatic leptin signaling had increased insulin-stimulated phosphorylation of Akt in the liver. These data reveal that unlike a complete deficiency of leptin action, which results in impaired glucose homeostasis, disruption of leptin action in the liver alone increases hepatic insulin sensitivity and protects against age- and diet-related glucose intolerance. Thus, leptin appears to act as a negative regulator of insulin action in the liver.

Current non-invasive scores for the assessment of severity of non-alcoholic fatty liver disease (NAFLD) and identification of patients with non-alcoholic steatohepatitis (NASH) have insufficient performance to be included in clinical routine. In the current study, we developed a novel machine learning approach to overcome the caveats of existing approaches. Non-invasive parameters were selected by an ensemble feature selection (EFS) from a retrospectively collected training cohort of 164 obese individuals (age: 43.5±10.3y; BMI: 54.1±10.1kg/m2) to develop a model able to predict the histological assessed NAFLD activity score (NAS). The model was evaluated in an independent validation cohort (122 patients, age: 45.2±11.75y, BMI: 50.8±8.61kg/m2). EFS identified age, γGT, HbA1c, adiponectin, and M30 as being highly associated with NAFLD. The model reached a Spearman correlation coefficient with the NAS of 0.46 in the training cohort and was able to differentiate between NAFL (NAS≤4) and NASH (NAS>4) with an AUC of 0.73. In the independent validation cohort, an AUC of 0.7 was achieved for this separation. We further analyzed the potential of the new model for disease monitoring in an obese cohort of 38 patients under lifestyle intervention for one year. While all patients lost weight under intervention, increasing scores were observed in 15 patients. Increasing scores were associated with significantly lower absolute weight loss, lower reduction of waist circumference and basal metabolic rate. A newly developed model (http://CHek.heiderlab.de) can predict presence or absence of NASH with reasonable performance. The new score could be used to detect NASH and monitor disease progression or therapy response to weight loss interventions.

Aims/hypothesis Leptin has profound glucose-lowering effects in rodent models of type 1 diabetes, and is currently being tested clinically to treat this disease. In addition to reversing hyperglycaemia, leptin therapy corrects multiple lipid, energy and neuroendocrine imbalances in rodent models of type 1 diabetes, yet the precise mechanism has not been fully defined. Thus, we performed metabolic analyses to delineate the downstream metabolic pathway mediating leptin-induced glucose lowering in diabetic mice. Methods Mice were injected with streptozotocin (STZ) to induce insulin-deficient diabetes, and were subsequently treated with 20 μg/day recombinant murine leptin or vehicle for 5 to 14 days. Energy-yielding substrates were measured in the liver and plasma, and endogenous glucose production was assessed by tolerance to extended fasting. Results STZ–leptin-treated mice developed severe hypoketotic hypoglycaemia during prolonged fasting, indicative of suppressed endogenous ketone and glucose production. STZ–leptin mice displayed normal gluconeogenic and glycogenolytic capacity, but had depleted circulating glycerol and NEFA. The depletion of glycerol and NEFA correlated tightly with the kinetics of glucose lowering in response to chronic leptin administration, and was not mimicked by single leptin injection. Administration of glycerol acutely reversed fasting-induced hypoglycaemia in leptin-treated mice. Conclusions/interpretation The findings of this study suggest that the diminution of circulating glycerol reduces endogenous glucose production, contributing to severe fasting-induced hypoglycaemia in leptin-treated rodent models of type 1 diabetes, and support that depletion of glycerol contributes to the glucose-lowering action of leptin.

Liver parameters are associated with cardiovascular disease risk and severity of stenosis. It is unclear whether liver parameters could predict the long-term outcome of patients after acute myocardial infarction (AMI). We performed an unbiased analysis of the predictive value of serum parameters for long-term prognosis after AMI. In a retrospective, observational, single-center, cohort study, 569 patients after AMI were enrolled and followed up until 6 years for major adverse cardiovascular events, including cardiac death. Patients were classified into non-survivors ( = 156) and survivors ( = 413). Demographic and laboratory data were analyzed using ensemble feature selection (EFS) and logistic regression. Correlations were performed for serum parameters. Age (73; 64; < 0.01), alanine aminotransferase (ALT; 93 U/l; 40 U/l; < 0.01), aspartate aminotransferase (AST; 162 U/l; 66 U/l; < 0.01), C-reactive protein (CRP; 4.7 U/l; 1.6 U/l; < 0.01), creatinine (1.6; 1.3; < 0.01), γ-glutamyltransferase (GGT; 71 U/l; 46 U/l; < 0.01), urea (29.5; 20.5; < 0.01), estimated glomerular filtration rate (eGFR; 49.6; 61.4; < 0.01), troponin (13.3; 7.6; < 0.01), myoglobin (639; 302; < 0.01), and cardiovascular risk factors (hypercholesterolemia < 0.02, family history < 0.01, and smoking < 0.01) differed significantly between non-survivors and survivors. Age, AST, CRP, eGFR, myoglobin, sodium, urea, creatinine, and troponin correlated significantly with death ( = -0.29; 0.14; 0.31; -0.27; 0.20; -0.13; 0.33; 0.24; 0.12). A prediction model was built including age, CRP, eGFR, myoglobin, and urea, achieving an AUROC of 77.6% to predict long-term survival after AMI. Non-invasive parameters, including liver and renal markers, can predict long-term outcome of patients after AMI.

[This corrects the article DOI: 10.1371/journal.pone.0254720.].

Motivation Biomarker discovery methods are essential to identify a minimal subset of features (e.g., serum markers in predictive medicine) that are relevant to develop prediction models with high accuracy. By now, there exist diverse feature selection methods, which either are embedded, combined, or independent of predictive learning algorithms. Many preceding studies showed the defectiveness of single feature selection results, which cause difficulties for professionals in a variety of fields (e.g., medical practitioners) to analyze and interpret the obtained feature subsets. Whereas each of these methods is highly biased, an ensemble feature selection has the advantage to alleviate and compensate for such biases. Concerning the reliability, validity, and reproducibility of these methods, we examined eight different feature selection methods for binary classification datasets and developed an ensemble feature selection system. Results By using an ensemble of feature selection methods, a quantification of the importance of the features could be obtained. The prediction models that have been trained on the selected features showed improved prediction performance.