Modeling the covariates effects on the hazard function by piecewise exponential artificial neural networks

an application to a controlled clinical trial on renal carcinoma

Marco Fornili, Patrizia Boracchi, Federico Ambrogi, Elia Biganzoli

Research output: Contribution to journalArticle

Abstract

BACKGROUND: In exploring the time course of a disease to support or generate biological hypotheses, the shape of the hazard function provides relevant information. For long follow-ups the shape of hazard function may be complex, with the presence of multiple peaks. In this paper we present the use of a neural network extension of the piecewise exponential model to study the shape of the hazard function in time in dependence of covariates. The technique is applied to a dataset of 247 renal cell carcinoma patients from a randomized clinical trial.

RESULTS: An interaction effect of treatment with number of metastatic lymph nodes but not with pathologic T-stage is highlighted.

CONCLUSIONS: Piecewise Exponential Artificial Neural Networks demonstrate a clinically useful and flexible tool in assessing interaction or time-dependent effects of the prognostic factors on the hazard function.

Original languageEnglish
Pages (from-to)186
JournalBMC Bioinformatics
Volume19
Issue numberSuppl 7
DOIs
Publication statusPublished - Jul 9 2018

Fingerprint

Hazard Function
Controlled Clinical Trials
Clinical Trials
Artificial Neural Network
Covariates
Hazards
Neural networks
Carcinoma
Kidney
Modeling
Prognostic Factors
Renal Cell Carcinoma
Randomized Clinical Trial
Exponential Model
Interaction Effects
Randomized Controlled Trials
Lymph Nodes
Cells
Neural Networks
Cell

Cite this

Modeling the covariates effects on the hazard function by piecewise exponential artificial neural networks : an application to a controlled clinical trial on renal carcinoma. / Fornili, Marco; Boracchi, Patrizia; Ambrogi, Federico; Biganzoli, Elia.

In: BMC Bioinformatics, Vol. 19, No. Suppl 7, 09.07.2018, p. 186.

Research output: Contribution to journalArticle

@article{cf0af4462a5d4e83ba375b5238262567,
title = "Modeling the covariates effects on the hazard function by piecewise exponential artificial neural networks: an application to a controlled clinical trial on renal carcinoma",
abstract = "BACKGROUND: In exploring the time course of a disease to support or generate biological hypotheses, the shape of the hazard function provides relevant information. For long follow-ups the shape of hazard function may be complex, with the presence of multiple peaks. In this paper we present the use of a neural network extension of the piecewise exponential model to study the shape of the hazard function in time in dependence of covariates. The technique is applied to a dataset of 247 renal cell carcinoma patients from a randomized clinical trial.RESULTS: An interaction effect of treatment with number of metastatic lymph nodes but not with pathologic T-stage is highlighted.CONCLUSIONS: Piecewise Exponential Artificial Neural Networks demonstrate a clinically useful and flexible tool in assessing interaction or time-dependent effects of the prognostic factors on the hazard function.",
author = "Marco Fornili and Patrizia Boracchi and Federico Ambrogi and Elia Biganzoli",
year = "2018",
month = "7",
day = "9",
doi = "10.1186/s12859-018-2179-1",
language = "English",
volume = "19",
pages = "186",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central Ltd.",
number = "Suppl 7",

}

TY - JOUR

T1 - Modeling the covariates effects on the hazard function by piecewise exponential artificial neural networks

T2 - an application to a controlled clinical trial on renal carcinoma

AU - Fornili, Marco

AU - Boracchi, Patrizia

AU - Ambrogi, Federico

AU - Biganzoli, Elia

PY - 2018/7/9

Y1 - 2018/7/9

N2 - BACKGROUND: In exploring the time course of a disease to support or generate biological hypotheses, the shape of the hazard function provides relevant information. For long follow-ups the shape of hazard function may be complex, with the presence of multiple peaks. In this paper we present the use of a neural network extension of the piecewise exponential model to study the shape of the hazard function in time in dependence of covariates. The technique is applied to a dataset of 247 renal cell carcinoma patients from a randomized clinical trial.RESULTS: An interaction effect of treatment with number of metastatic lymph nodes but not with pathologic T-stage is highlighted.CONCLUSIONS: Piecewise Exponential Artificial Neural Networks demonstrate a clinically useful and flexible tool in assessing interaction or time-dependent effects of the prognostic factors on the hazard function.

AB - BACKGROUND: In exploring the time course of a disease to support or generate biological hypotheses, the shape of the hazard function provides relevant information. For long follow-ups the shape of hazard function may be complex, with the presence of multiple peaks. In this paper we present the use of a neural network extension of the piecewise exponential model to study the shape of the hazard function in time in dependence of covariates. The technique is applied to a dataset of 247 renal cell carcinoma patients from a randomized clinical trial.RESULTS: An interaction effect of treatment with number of metastatic lymph nodes but not with pathologic T-stage is highlighted.CONCLUSIONS: Piecewise Exponential Artificial Neural Networks demonstrate a clinically useful and flexible tool in assessing interaction or time-dependent effects of the prognostic factors on the hazard function.

U2 - 10.1186/s12859-018-2179-1

DO - 10.1186/s12859-018-2179-1

M3 - Article

VL - 19

SP - 186

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

IS - Suppl 7

ER -