English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Multivariate classification methods using explanatory and predictive modelsare necessary for characterizing subgroups of patients according to their riskprofiles. Popular methods include logistic regression and classification treeswith performances that vary according to the nature and the characteristics ofthe dataset. In the context of imported malaria, we aimed at classifyingseverity criteria based on a heterogeneous patient population. We investigatedthese approaches by implementing two different strategies: L1 logisticregression (L1LR) that models a single global solution and classification treesthat model multiple local solutions corresponding to discriminant subregions ofthe feature space. For each strategy, we built a standard model, and a sparserversion of it. As an alternative to pruning, we explore a promising approachthat first constrains the tree model with an L1LR-based feature selection, anapproach we called L1LR-Tree. The objective is to decrease its vulnerability tosmall data variations by removing variables corresponding to unstable localphenomena. Our study is twofold: i) from a methodological perspective comparingthe performances and the stability of the three previous methods, i.e L1LR,classification trees and L1LR-Tree, for the classification of severe forms ofimported malaria, and ii) from an applied perspective improving the actualclassification of severe forms of imported malaria by identifying morepersonalized profiles predictive of several clinical criteria based onvariables dismissed for the clinical definition of the disease. The mainmethodological results show that the combined method L1LR-Tree builds sparseand stable models that significantly predicts the different severity criteriaand outperforms all the other methods in terms of accuracy.

L1 logistic regression as a feature selection step for training stable  classification trees for the prediction of severity criteria in imported  malaria