Human-Computer interaction to learn scenarios from ICU multivariate time series - Inserm - Institut national de la santé et de la recherche médicale Accéder directement au contenu
Communication Dans Un Congrès Année : 2005

Human-Computer interaction to learn scenarios from ICU multivariate time series

Thomas Guyet
SIC
Catherine Garbay
  • Fonction : Auteur
  • PersonId : 829627
SIC

Résumé

Abstract. In the context of high dependent environments such as intensive care or operating room we would like to predict, as soon as possible, from past and present states, the evolution of the patient's condition. Based on the set of physiological dat, clinicians have difficulties to formalize typical high level scenes that are representative of specific patient's state sequences to recognize. On the other hand, signal processing algorithms are limited to low level pattern detection. We propose an interactive environment for an in-depth exploration by the clinician of data. We hypothesize that such human-computer collaboration could help with the definition of signatures representative of specific situations. To test our hypothesis, we have defined a multi-agent system (MAS) with the capacities of 1) segmenting, 2) classifying and 3) learning. These three tasks are continuously adapted based on interactions with the clinician. Preliminary results are presented to support our assumption.
Fichier principal
Vignette du fichier
AIME_Guyet05.pdf (387.16 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

inserm-00519870 , version 1 (08-06-2011)

Identifiants

  • HAL Id : inserm-00519870 , version 1

Citer

Thomas Guyet, Catherine Garbay, Michel Dojat. Human-Computer interaction to learn scenarios from ICU multivariate time series. Artificial Intelligence in Medicine. Proceedings of the European Conference on Artificial Intelligence in Medicine AIME'05, Jul 2005, Aberdeen- Scotland, United Kingdom. pp.424-428. ⟨inserm-00519870⟩
811 Consultations
336 Téléchargements

Partager

Gmail Facebook X LinkedIn More