Additional file 3 of Comparison of machine learning methods with logistic regression analysis in creating predictive models for risk of critical in-hospital events in COVID-19 patients on hospital admission

Autor: Sievering, Aaron W., Wohlmuth, Peter, Geßler, Nele, Gunawardene, Melanie A., Herrlinger, Klaus, Bein, Berthold, Arnold, Dirk, Bergmann, Martin, Nowak, Lorenz, Gloeckner, Christian, Koch, Ina, Bachmann, Martin, Herborn, Christoph U., Stang, Axel
Rok vydání: 2022
DOI: 10.6084/m9.figshare.21629416
Popis: Additional file 3: Table S3. Variable importance for each model for prediction of critical in-hospital events using COVID-19-infected patient’s data on admission (A–F). Permutation based performance loss for the LR model (A), the regularized regression models L1 (B), L2 (C) and EN (D), and the SVM (E) and RF (F) model. The values are summarized by medians and interquartile ranges. The tables only contain predictors with median losses higher 0.
Databáze: OpenAIRE