Tools to identify linear combination of prognostic factors which maximizes area under receiver operator curve release_34yl54zlhnec3noh4x6m3cybom

by Nicolae Todor, Irina Todor, Gavril Săplăcan

Published in Journal of Clinical Bioinformatics by ClinTransMed, AB.

2014   Volume 4, p10

Abstract

The linear combination of variables is an attractive method in many medical analyses targeting a score to classify patients. In the case of ROC curves the most popular problem is to identify the linear combination which maximizes area under curve (AUC). This problem is complete closed when normality assumptions are met. With no assumption of normality search algorithm are avoided because it is accepted that we have to evaluate AUC n(d) times where n is the number of distinct observation and d is the number of variables. For d = 2, using particularities of AUC formula, we described an algorithm which lowered the number of evaluations of AUC from n(2) to n(n-1) + 1. For d > 2 our proposed solution is an approximate method by considering equidistant points on the unit sphere in R(d) where we evaluate AUC. The algorithms were applied to data from our lab to predict response of treatment by a set of molecular markers in cervical cancers patients. In order to evaluate the strength of our algorithms a simulation was added. In the case of no normality presented algorithms are feasible. For many variables computation time could be increased but acceptable.
In text/plain format

Archived Files and Locations

application/pdf  254.4 kB
file_jrn2xzhrsje3pi2uhli3vvdda4
archive.org (archive)
application/pdf  333.3 kB
file_6kv3ki6tzzfipj5dyncriyvx6m
jclinbioinformatics.biomedcentral.com (web)
web.archive.org (webarchive)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article-journal
Stage   published
Date   2014-07-04
Language   en ?
DOI  10.1186/2043-9113-4-10
PubMed  25068036
PMC  PMC4099021
Wikidata  Q42063442
Journal Metadata
Open Access Publication
Not in DOAJ
In ISSN ROAD
In Keepers Registry
ISSN-L:  2043-9113
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 22d01a6e-9bfd-4760-9c79-995b62a86a7f
API URL: JSON