Predicting local malaria exposure using a Lasso-based two-level cross validation algorithm

Abstract : Recent studies have highlighted the importance of local environmental factors to determine the fine-scale heterogeneity of malaria transmission and exposure to the vector. In this work, we compare a classical GLM model with backward selection with different versions of an automatic LASSO-based algorithm with 2-level cross-validation aiming to build a predic-tive model of the space and time dependent individual exposure to the malaria vector, using entomological and environmental data from a cohort study in Benin. Although the GLM can outperform the LASSO model with appropriate engineering, the best model in terms of pre-dictive power was found to be the LASSO-based model. Our approach can be adapted to different topics and may therefore be helpful to address prediction issues in other health sciences domains.
Type de document :
Article dans une revue
PLoS ONE, Public Library of Science, 2017, 12 (10), 〈10.1371/journal.pone.0187234〉
Liste complète des métadonnées

Littérature citée [38 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01736935
Contributeur : Bienvenue Kouwaye <>
Soumis le : dimanche 18 mars 2018 - 23:55:21
Dernière modification le : jeudi 7 février 2019 - 16:52:41
Document(s) archivé(s) le : mardi 11 septembre 2018 - 08:50:12

Fichier

Kouwaye_Publication_2.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

Collections

Citation

Bienvenue Kouwaye, Fabrice Rossi, Noël Fonton, André Garcia, Simplice Dossou-Gbété, et al.. Predicting local malaria exposure using a Lasso-based two-level cross validation algorithm. PLoS ONE, Public Library of Science, 2017, 12 (10), 〈10.1371/journal.pone.0187234〉. 〈hal-01736935〉

Partager

Métriques

Consultations de la notice

103

Téléchargements de fichiers

30