DI-UMONS : Dépôt institutionnel de l’université de Mons

Recherche transversale
Rechercher
(titres de publication, de périodique et noms de colloque inclus)
2016-09-12 - Colloque/Article dans les actes avec comité de lecture - Anglais - 2 page(s)

Itani Sarah , Fortemps Philippe , Lecron Fabian , "Data Mining for Aiding Diagnosis of Attention Deficit Hyperactivity Disorder by a Multilevel Approach" in Belgian-Dutch Conference on Machine Learning, BeneLearn, Courtrai, Belgique, 2016

  • Codes CREF : Intelligence artificielle (DI1180), Modèles mathématiques d'aide à la décision (DI1151), Informatique médicale (DI3314), Neurosciences cognitives (DI4296), Ingénierie biomédicale (DI3900)
  • Unités de recherche UMONS : Management de l'Innovation Technologique (F113), Mathématique et Recherche opérationnelle (F151)
  • Instituts UMONS : Institut de Recherche en Technologies de l’Information et Sciences de l’Informatique (InforTech)
Texte intégral :

Abstract(s) :

(Anglais) In the last years, neuroimaging has shown ability to be used in the detection of mental diseases. However, a pathophysiological model of Attention Decit Hyperactivity Disorder (ADHD) hasn't been established yet. This work aimed to aiding diagnosis of ADHD from the ADHD-200 collection launched in the context of a worldwide competition in 2011. The heterogeneous dataset, regarding on nearly one thousand patients assessed in eight research sites, includes both phenotypical and neuroimaging data. Through this work, we propose to integrate a multilevel approach to our hierachical structure of classication in order to : (1) adress the heterogeneity of the ADHD-200 collection, (2) provide praticians with a convenient and understandable diagnosis tool through decision trees, (3) raise a subset of cerebral regions of interest as biomarkers of the trouble.