Evidence-based Anomaly Detection in Clinical Domains

Abstract : Anomaly detection methods can be very useful in identifying interesting or concerning events. In this work, we develop and examine new probabilistic anomaly detection methods that let us evaluate management decisions for a specific patient and identify those decisions that are highly unusual with respect to patients with the same or similar condition. The statistics used in this detection are derived from probabilistic models such as Bayesian networks that are learned from a database of past patient cases. We evaluate our methods on the problem of detection of unusual hospitalization patterns for patients with community acquired pneumonia. The results show very encouraging detection performance with 0.5 precision at 0.53 recall and give us hope that these techniques may provide the basis of intelligent monitoring systems that alert clinicians to the occurrence of unusual events or decisions.
Type de document :
Communication dans un congrès
Annual American Medical Informatics Association Symposium, 2007, Chicago, United States. pp.319--324
Liste complète des métadonnées

Littérature citée [7 références]  Voir  Masquer  Télécharger

Contributeur : Michal Valko <>
Soumis le : lundi 21 novembre 2011 - 17:31:18
Dernière modification le : jeudi 21 avril 2016 - 16:48:53
Document(s) archivé(s) le : mercredi 22 février 2012 - 02:31:23


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-00643401, version 1
  • PUBMED : 18693850



Milos Hauskrecht, Michal Valko, Branislav Kveton, Shyam Visweswaran, Gregory Cooper. Evidence-based Anomaly Detection in Clinical Domains. Annual American Medical Informatics Association Symposium, 2007, Chicago, United States. pp.319--324. 〈hal-00643401〉



Consultations de la notice


Téléchargements de fichiers