Feature importance analysis for patient management decisions

Michal Valko 1, 2 Milos Hauskrecht 1
1 Department of Computer Science - University of Pittsburgh
2 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
Abstract : 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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download
https://hal.inria.fr/hal-00643123
Contributor : Michal Valko <>
Submitted on : Monday, November 21, 2011 - 11:29:09 AM
Last modification on : Thursday, August 22, 2019 - 12:10:38 PM
Long-term archiving on: Wednesday, February 22, 2012 - 2:27:32 AM

File

valko2010feature.pdf
Files produced by the author(s)

Identifiers

Collections

CNRS | INRIA | UNIV-LILLE3 | LAGIS

Citation

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⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

376

Files downloads

211

 

 

Contact

archive-ouverte@inria.fr