Different Methodologies for Patient Stratification Using Survival Data

José Manuel Matos Ribeiro da Fonseca; DEE Group Author

doi:10.1007/978-3-642-14571-1_21

Different Methodologies for Patient Stratification Using Survival Data

José Manuel Matos Ribeiro da Fonseca, DEE Group Author

Research output: Chapter in Book/Report/Conference proceeding › Chapter

2 Citations (Scopus)

Abstract

Clinical characterization of breast cancer patients related to their risk and profiles is an important part for making their correct prognostic assessments. This paper first proposes a prognostic index obtained when it is applied a flexible non-linear time-to-event model and compares it to a widely used linear survival estimator. This index underpins different stratification methodologies including informed clustering utilising the principle of learning metrics, regression trees and recursive application of the log-rank test. Missing data issue was overcome using multiple imputation, which was applied to a neural network model of survival fitted to a data set for breast cancer (n=743). It was found the three methodologies broadly agree, having however important differences.

Original language	Unknown
Title of host publication	Computational Intelligence Methods for Bioinformatics and Biostatistics Lecture Notes in Computer Science
Editors	Springer
Place of Publication	GERMANY
Publisher	Springer
Pages	276-290
Volume	6160
ISBN (Print)	978-3-642-14570-4
DOIs	https://doi.org/10.1007/978-3-642-14571-1_21
Publication status	Published - 1 Jan 2010

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer

Cite this

Fonseca, J. M. M. R. D., & DEE Group Author (2010). Different Methodologies for Patient Stratification Using Survival Data. In Springer (Ed.), Computational Intelligence Methods for Bioinformatics and Biostatistics Lecture Notes in Computer Science (Vol. 6160, pp. 276-290). (Lecture Notes in Computer Science). GERMANY: Springer. https://doi.org/10.1007/978-3-642-14571-1_21

@inbook{d3464f88d703491b9146e65f4cfd2224,

title = "Different Methodologies for Patient Stratification Using Survival Data",

abstract = "Clinical characterization of breast cancer patients related to their risk and profiles is an important part for making their correct prognostic assessments. This paper first proposes a prognostic index obtained when it is applied a flexible non-linear time-to-event model and compares it to a widely used linear survival estimator. This index underpins different stratification methodologies including informed clustering utilising the principle of learning metrics, regression trees and recursive application of the log-rank test. Missing data issue was overcome using multiple imputation, which was applied to a neural network model of survival fitted to a data set for breast cancer (n=743). It was found the three methodologies broadly agree, having however important differences.",

author = "Fonseca, {Jos{\'e} Manuel Matos Ribeiro da} and {DEE Group Author}",

year = "2010",

month = "1",

day = "1",

doi = "10.1007/978-3-642-14571-1_21",

language = "Unknown",

isbn = "978-3-642-14570-4",

volume = "6160",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "276--290",

editor = "Springer",

booktitle = "Computational Intelligence Methods for Bioinformatics and Biostatistics Lecture Notes in Computer Science",

}

Different Methodologies for Patient Stratification Using Survival Data. / Fonseca, José Manuel Matos Ribeiro da; DEE Group Author.

Computational Intelligence Methods for Bioinformatics and Biostatistics Lecture Notes in Computer Science. ed. / Springer. Vol. 6160 GERMANY : Springer, 2010. p. 276-290 (Lecture Notes in Computer Science).

Research output: Chapter in Book/Report/Conference proceeding › Chapter

TY - CHAP

T1 - Different Methodologies for Patient Stratification Using Survival Data

AU - Fonseca, José Manuel Matos Ribeiro da

AU - DEE Group Author

PY - 2010/1/1

Y1 - 2010/1/1

N2 - Clinical characterization of breast cancer patients related to their risk and profiles is an important part for making their correct prognostic assessments. This paper first proposes a prognostic index obtained when it is applied a flexible non-linear time-to-event model and compares it to a widely used linear survival estimator. This index underpins different stratification methodologies including informed clustering utilising the principle of learning metrics, regression trees and recursive application of the log-rank test. Missing data issue was overcome using multiple imputation, which was applied to a neural network model of survival fitted to a data set for breast cancer (n=743). It was found the three methodologies broadly agree, having however important differences.

AB - Clinical characterization of breast cancer patients related to their risk and profiles is an important part for making their correct prognostic assessments. This paper first proposes a prognostic index obtained when it is applied a flexible non-linear time-to-event model and compares it to a widely used linear survival estimator. This index underpins different stratification methodologies including informed clustering utilising the principle of learning metrics, regression trees and recursive application of the log-rank test. Missing data issue was overcome using multiple imputation, which was applied to a neural network model of survival fitted to a data set for breast cancer (n=743). It was found the three methodologies broadly agree, having however important differences.

U2 - 10.1007/978-3-642-14571-1_21

DO - 10.1007/978-3-642-14571-1_21

M3 - Chapter

SN - 978-3-642-14570-4

VL - 6160

T3 - Lecture Notes in Computer Science

SP - 276

EP - 290

BT - Computational Intelligence Methods for Bioinformatics and Biostatistics Lecture Notes in Computer Science

A2 - Springer, null

PB - Springer

CY - GERMANY

ER -

Access to Document

10.1007/978-3-642-14571-1_21

http://oa.uninova.pt/4826/