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.

Modeling the covariates effects on the hazard function by piecewise exponential artificial neural networks : an application to a controlled clinical trial on renal carcinoma / M. Fornili, P. Boracchi, F. Ambrogi, E. Biganzoli. - In: BMC BIOINFORMATICS. - ISSN 1471-2105. - 19:suppl. 7(2018 Jul), pp. 186.1-186.7. [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

M. Fornili
Primo
;
P. Boracchi;F. Ambrogi;E. Biganzoli
2018

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.
Hazard function; Neural networks; Piecewise exponential model; Survival analysis
Settore MED/01 - Statistica Medica
lug-2018
Article (author)
File in questo prodotto:
File Dimensione Formato  
s12859-018-2179-1.pdf

accesso aperto

Tipologia: Publisher's version/PDF
Dimensione 734.59 kB
Formato Adobe PDF
734.59 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/581345
Citazioni
  • ???jsp.display-item.citation.pmc??? 0
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
social impact