Flexible Hazard Modelling for Outcome Prediction in Cancer. Perspectives for the Use of Bioinformatics Knowledge.

Elia Biganzoli, Patrizia Boracchi

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Biological tumor markers are expected to improve outcome prediction and response to tailored therapies. However, complex effects could be underlying the dependence of the outcome from several variables measured on a continuous scale. Such a problem has been of increasing importance since the advent of high throughput genomic/ proteomic bioassay techniques. Linear and non-linear flexible regression analysis techniques, such as those based on splines and feed forward artificial neural networks (FFANN), are proposed for the statistical analysis of censored survival time data, to account for the presence of non-linear effects of predictors. Among survival functions, the hazard has a biological interest for the study of the disease dynamics. Moreover, it allows for the estimation of cumulative incidence functions for predicting outcome probabilities over follow-up. Therefore, specific error functions and data representation have been introduced for feed forward artificial neural networks (FFANN) extensions of generalized linear models, in the perspective of modeling the hazard function of censored survival data. These techniques can be exploited for the assessment of the prognostic contribution of new biological markers, investigated by means of genomic/proteomic techniques. The application of suitable measures of prognostic accuracy helps in the evaluation of the real improvement in outcome prediction due to the addition of the new molecular markers to the traditional clinical ones.

Original languageEnglish
Title of host publicationOutcome Prediction in Cancer
PublisherElsevier
Pages147-170
Number of pages24
ISBN (Print)9780444528551
DOIs
Publication statusPublished - 2007

Fingerprint

Bioinformatics
Computational Biology
Proteomics
Hazards
Survival Analysis
Tumor Biomarkers
Biological Assay
Linear Models
Neoplasms
Biomarkers
Regression Analysis
Neural networks
Bioassay
Incidence
Regression analysis
Splines
Statistical methods
Throughput
Therapeutics

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)

Cite this

Flexible Hazard Modelling for Outcome Prediction in Cancer. Perspectives for the Use of Bioinformatics Knowledge. / Biganzoli, Elia; Boracchi, Patrizia.

Outcome Prediction in Cancer. Elsevier, 2007. p. 147-170.

Research output: Chapter in Book/Report/Conference proceedingChapter

@inbook{6c36dce7dc8f4598959841ef5a839a17,
title = "Flexible Hazard Modelling for Outcome Prediction in Cancer. Perspectives for the Use of Bioinformatics Knowledge.",
abstract = "Biological tumor markers are expected to improve outcome prediction and response to tailored therapies. However, complex effects could be underlying the dependence of the outcome from several variables measured on a continuous scale. Such a problem has been of increasing importance since the advent of high throughput genomic/ proteomic bioassay techniques. Linear and non-linear flexible regression analysis techniques, such as those based on splines and feed forward artificial neural networks (FFANN), are proposed for the statistical analysis of censored survival time data, to account for the presence of non-linear effects of predictors. Among survival functions, the hazard has a biological interest for the study of the disease dynamics. Moreover, it allows for the estimation of cumulative incidence functions for predicting outcome probabilities over follow-up. Therefore, specific error functions and data representation have been introduced for feed forward artificial neural networks (FFANN) extensions of generalized linear models, in the perspective of modeling the hazard function of censored survival data. These techniques can be exploited for the assessment of the prognostic contribution of new biological markers, investigated by means of genomic/proteomic techniques. The application of suitable measures of prognostic accuracy helps in the evaluation of the real improvement in outcome prediction due to the addition of the new molecular markers to the traditional clinical ones.",
author = "Elia Biganzoli and Patrizia Boracchi",
year = "2007",
doi = "10.1016/B978-044452855-1/50008-8",
language = "English",
isbn = "9780444528551",
pages = "147--170",
booktitle = "Outcome Prediction in Cancer",
publisher = "Elsevier",

}

TY - CHAP

T1 - Flexible Hazard Modelling for Outcome Prediction in Cancer. Perspectives for the Use of Bioinformatics Knowledge.

AU - Biganzoli, Elia

AU - Boracchi, Patrizia

PY - 2007

Y1 - 2007

N2 - Biological tumor markers are expected to improve outcome prediction and response to tailored therapies. However, complex effects could be underlying the dependence of the outcome from several variables measured on a continuous scale. Such a problem has been of increasing importance since the advent of high throughput genomic/ proteomic bioassay techniques. Linear and non-linear flexible regression analysis techniques, such as those based on splines and feed forward artificial neural networks (FFANN), are proposed for the statistical analysis of censored survival time data, to account for the presence of non-linear effects of predictors. Among survival functions, the hazard has a biological interest for the study of the disease dynamics. Moreover, it allows for the estimation of cumulative incidence functions for predicting outcome probabilities over follow-up. Therefore, specific error functions and data representation have been introduced for feed forward artificial neural networks (FFANN) extensions of generalized linear models, in the perspective of modeling the hazard function of censored survival data. These techniques can be exploited for the assessment of the prognostic contribution of new biological markers, investigated by means of genomic/proteomic techniques. The application of suitable measures of prognostic accuracy helps in the evaluation of the real improvement in outcome prediction due to the addition of the new molecular markers to the traditional clinical ones.

AB - Biological tumor markers are expected to improve outcome prediction and response to tailored therapies. However, complex effects could be underlying the dependence of the outcome from several variables measured on a continuous scale. Such a problem has been of increasing importance since the advent of high throughput genomic/ proteomic bioassay techniques. Linear and non-linear flexible regression analysis techniques, such as those based on splines and feed forward artificial neural networks (FFANN), are proposed for the statistical analysis of censored survival time data, to account for the presence of non-linear effects of predictors. Among survival functions, the hazard has a biological interest for the study of the disease dynamics. Moreover, it allows for the estimation of cumulative incidence functions for predicting outcome probabilities over follow-up. Therefore, specific error functions and data representation have been introduced for feed forward artificial neural networks (FFANN) extensions of generalized linear models, in the perspective of modeling the hazard function of censored survival data. These techniques can be exploited for the assessment of the prognostic contribution of new biological markers, investigated by means of genomic/proteomic techniques. The application of suitable measures of prognostic accuracy helps in the evaluation of the real improvement in outcome prediction due to the addition of the new molecular markers to the traditional clinical ones.

UR - http://www.scopus.com/inward/record.url?scp=84882498225&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84882498225&partnerID=8YFLogxK

U2 - 10.1016/B978-044452855-1/50008-8

DO - 10.1016/B978-044452855-1/50008-8

M3 - Chapter

SN - 9780444528551

SP - 147

EP - 170

BT - Outcome Prediction in Cancer

PB - Elsevier

ER -