Feature importance analysis for patient management decisions - Archive ouverte HAL Access content directly
Conference Papers Year : 2010

Feature importance analysis for patient management decisions

(1, 2) , (1)


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
Origin : Files produced by the author(s)

Dates and versions

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



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⟩
139 View
94 Download



Gmail Facebook Twitter LinkedIn More