Feature importance analysis for patient management decisions - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

Feature importance analysis for patient management decisions

Résumé

The objective of this paper is to understand what characteristics and features of clinical data influence physician's decision about ordering laboratory tests or prescribing medications the most. We conduct our analysis on data and decisions extracted from electronic health records of 4486 post-surgical cardiac patients. The summary statistics for 335 different lab order decisions and 407 medication decisions are reported. We show that in many cases, physician's lab-order and medication decisions are predicted well by simple patterns such as last value of a single test result, time since a certain lab test was ordered or time since certain procedure was executed.
Fichier principal
Vignette du fichier
valko2010feature.pdf (117.72 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00643123 , version 1 (21-11-2011)

Identifiants

Citer

Michal Valko, Milos Hauskrecht. Feature importance analysis for patient management decisions. 13th International Congress on Medical Informatics MEDINFO 2010, Sep 2010, Cape Town, South Africa. pp.861-865, ⟨10.3233/978-1-60750-588-4-861⟩. ⟨hal-00643123⟩
142 Consultations
102 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More