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

doi:10.1186/s12859-018-2179-1

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

Fondazione IRCCS Istituto Nazionale dei Tumori

Research output: Contribution to journal › Article

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 language	English
Pages (from-to)	186
Journal	BMC Bioinformatics
Volume	19
Issue number	Suppl 7
DOIs	https://doi.org/10.1186/s12859-018-2179-1
Publication status	Published - Jul 9 2018

Access to Document

10.1186/s12859-018-2179-1

Fingerprint Dive into the research topics of 'Modeling the covariates effects on the hazard function by piecewise exponential artificial neural networks: an application to a controlled clinical trial on renal carcinoma'. Together they form a unique fingerprint.

Cite this

Fornili, M., Boracchi, P., Ambrogi, F., & Biganzoli, E. (2018). Modeling the covariates effects on the hazard function by piecewise exponential artificial neural networks: an application to a controlled clinical trial on renal carcinoma. BMC Bioinformatics, 19(Suppl 7), 186. https://doi.org/10.1186/s12859-018-2179-1

@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 = jul,

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

C2 - 30066658

VL - 19

SP - 186

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

IS - Suppl 7

ER -