Prediction of non-muscle invasive bladder cancer outcomes assessed by innovative multimarker prognostic models

the SBC/EPICURO Study Investigators

doi:10.1186/s12885-016-2361-7

Prediction of non-muscle invasive bladder cancer outcomes assessed by innovative multimarker prognostic models

the SBC/EPICURO Study Investigators

Research output: Contribution to journal › Article › peer-review

8 Scopus citations

Abstract

Background: We adapted Bayesian statistical learning strategies to the prognosis field to investigate if genome-wide common SNP improve the prediction ability of clinico-pathological prognosticators and applied it to non-muscle invasive bladder cancer (NMIBC) patients. Methods: Adapted Bayesian sequential threshold models in combination with LASSO were applied to consider the time-to-event and the censoring nature of data. We studied 822 NMIBC patients followed-up >10years. The study outcomes were time-to-first-recurrence and time-to-progression. The predictive ability of the models including up to 171,304 SNP and/or 6 clinico-pathological prognosticators was evaluated using AUC-ROC and determination coefficient. Results: Clinico-pathological prognosticators explained a larger proportion of the time-to-first-recurrence (3.1%) and time-to-progression (5.4%) phenotypic variances than SNPs (1 and 0.01%, respectively). Adding SNPs to the clinico-pathological-parameters model slightly improved the prediction of time-to-first-recurrence (up to 4%). The prediction of time-to-progression using both clinico-pathological prognosticators and SNP did not improve. Heritability (ĥ²) of both outcomes was <1% in NMIBC. Conclusions: We adapted a Bayesian statistical learning method to deal with a large number of parameters in prognostic studies. Common SNPs showed a limited role in predicting NMIBC outcomes yielding a very low heritability for both outcomes. We report for the first time a heritability estimate for a disease outcome. Our method can be extended to other disease models.

Original language	English
Article number	351
Journal	BMC Cancer
Volume	16
Issue number	1
DOIs	https://doi.org/10.1186/s12885-016-2361-7
State	Published - 3 Jun 2016

Bibliographical note

Funding Information:
The work was partially supported by Red Temática de Investigación Cooperativa en Cáncer (#RD12/0036/0050), Fondo de Investigaciones Sanitarias (FIS), Instituto de Salud Carlos III, (Grant numbers #PI00–0745, #PI05–1436, and #PI06–1614), and Asociación Española Contra el Cáncer (AECC), Spain; the Intramural Research Program of the Division of Cancer Epidemiology and Genetics, National Cancer Institute, USA (Contract NCI NO2-CP-11015); and EU-FP7-HEALTH-F2–2008–201663-UROMOL and EU-7FP-HEALTH-TransBioBC #601933. ELM was funded by a Sara Borrell fellowship, Instituto de Salud Carlos III, Spain; and AML by a fellowship of the European Urological Scholarship Program for Research (EUSP Scholarship S-01–2013).

Publisher Copyright:
© 2016 de Maturana et al.

Keywords

AUC-ROC
Bayesian LASSO
Bayesian regression
Bayesian statistical learning method
Bladder cancer outcome
Determination coefficient
Genome-wide common SNP
Heritability
Illumina Infinium HumanHap 1M array
Multimarker models
Predictive ability
Prognosis
Progression
Recurrence

Access to Document

10.1186/s12885-016-2361-7

Cite this

@article{b95f3482f7204edfa81102df0cc91179,

title = "Prediction of non-muscle invasive bladder cancer outcomes assessed by innovative multimarker prognostic models",

abstract = "Background: We adapted Bayesian statistical learning strategies to the prognosis field to investigate if genome-wide common SNP improve the prediction ability of clinico-pathological prognosticators and applied it to non-muscle invasive bladder cancer (NMIBC) patients. Methods: Adapted Bayesian sequential threshold models in combination with LASSO were applied to consider the time-to-event and the censoring nature of data. We studied 822 NMIBC patients followed-up >10years. The study outcomes were time-to-first-recurrence and time-to-progression. The predictive ability of the models including up to 171,304 SNP and/or 6 clinico-pathological prognosticators was evaluated using AUC-ROC and determination coefficient. Results: Clinico-pathological prognosticators explained a larger proportion of the time-to-first-recurrence (3.1%) and time-to-progression (5.4%) phenotypic variances than SNPs (1 and 0.01%, respectively). Adding SNPs to the clinico-pathological-parameters model slightly improved the prediction of time-to-first-recurrence (up to 4%). The prediction of time-to-progression using both clinico-pathological prognosticators and SNP did not improve. Heritability (ĥ2) of both outcomes was <1% in NMIBC. Conclusions: We adapted a Bayesian statistical learning method to deal with a large number of parameters in prognostic studies. Common SNPs showed a limited role in predicting NMIBC outcomes yielding a very low heritability for both outcomes. We report for the first time a heritability estimate for a disease outcome. Our method can be extended to other disease models.",

keywords = "AUC-ROC, Bayesian LASSO, Bayesian regression, Bayesian statistical learning method, Bladder cancer outcome, Determination coefficient, Genome-wide common SNP, Heritability, Illumina Infinium HumanHap 1M array, Multimarker models, Predictive ability, Prognosis, Progression, Recurrence",

author = "{the SBC/EPICURO Study Investigators} and {L{\'o}pez de Maturana}, E. and A. Picornell and A. Masson-Lecomte and M. Kogevinas and M. M{\'a}rquez and A. Carrato and A. Tard{\'o}n and J. Lloreta and M. Garc{\'i}a-Closas and D. Silverman and N. Rothman and S. Chanock and Real, {F. X.} and Goddard, {M. E.} and N. Malats and M. Sala and G. Casta{\~n}o and M. Tor{\`a} and D. Puente and C. Villanueva and C. Murta-Nascimento and J. Fortuny and E. L{\'o}pez and S. Hern{\'a}ndez and R. Jaramillo and G. Vellalta and L. Palencia and F. Ferm{\'a}ndez and A. Amor{\'o}s and A. Alfaro and G. Carretero and S. Serrano and L. Ferrer and A. Gelabert and J. Carles and O. Bielsa and K. Villadiego and L. Cecchini and Saladi{\'e}, {J. M.} and L. Ibarz and M. C{\'e}spedes and C. Serra and D. Garc{\'i}a and J. Pujadas and R. Hernando and A. Cabezuelo and C. Abad and A. Prera and J. Prat and Soto, {J. L.}",

note = "Publisher Copyright: {\textcopyright} 2016 de Maturana et al.",

year = "2016",

month = jun,

day = "3",

doi = "10.1186/s12885-016-2361-7",

language = "Ingl{\'e}s",

volume = "16",

journal = "BMC Cancer",

issn = "1471-2407",

publisher = "BioMed Central Ltd.",

number = "1",

}

TY - JOUR

T1 - Prediction of non-muscle invasive bladder cancer outcomes assessed by innovative multimarker prognostic models

AU - the SBC/EPICURO Study Investigators

AU - López de Maturana, E.

AU - Picornell, A.

AU - Masson-Lecomte, A.

AU - Kogevinas, M.

AU - Márquez, M.

AU - Carrato, A.

AU - Tardón, A.

AU - Lloreta, J.

AU - García-Closas, M.

AU - Silverman, D.

AU - Rothman, N.

AU - Chanock, S.

AU - Real, F. X.

AU - Goddard, M. E.

AU - Malats, N.

AU - Sala, M.

AU - Castaño, G.

AU - Torà, M.

AU - Puente, D.

AU - Villanueva, C.

AU - Murta-Nascimento, C.

AU - Fortuny, J.

AU - López, E.

AU - Hernández, S.

AU - Jaramillo, R.

AU - Vellalta, G.

AU - Palencia, L.

AU - Fermández, F.

AU - Amorós, A.

AU - Alfaro, A.

AU - Carretero, G.

AU - Serrano, S.

AU - Ferrer, L.

AU - Gelabert, A.

AU - Carles, J.

AU - Bielsa, O.

AU - Villadiego, K.

AU - Cecchini, L.

AU - Saladié, J. M.

AU - Ibarz, L.

AU - Céspedes, M.

AU - Serra, C.

AU - García, D.

AU - Pujadas, J.

AU - Hernando, R.

AU - Cabezuelo, A.

AU - Abad, C.

AU - Prera, A.

AU - Prat, J.

AU - Soto, J. L.

PY - 2016/6/3

Y1 - 2016/6/3

N2 - Background: We adapted Bayesian statistical learning strategies to the prognosis field to investigate if genome-wide common SNP improve the prediction ability of clinico-pathological prognosticators and applied it to non-muscle invasive bladder cancer (NMIBC) patients. Methods: Adapted Bayesian sequential threshold models in combination with LASSO were applied to consider the time-to-event and the censoring nature of data. We studied 822 NMIBC patients followed-up >10years. The study outcomes were time-to-first-recurrence and time-to-progression. The predictive ability of the models including up to 171,304 SNP and/or 6 clinico-pathological prognosticators was evaluated using AUC-ROC and determination coefficient. Results: Clinico-pathological prognosticators explained a larger proportion of the time-to-first-recurrence (3.1%) and time-to-progression (5.4%) phenotypic variances than SNPs (1 and 0.01%, respectively). Adding SNPs to the clinico-pathological-parameters model slightly improved the prediction of time-to-first-recurrence (up to 4%). The prediction of time-to-progression using both clinico-pathological prognosticators and SNP did not improve. Heritability (ĥ2) of both outcomes was <1% in NMIBC. Conclusions: We adapted a Bayesian statistical learning method to deal with a large number of parameters in prognostic studies. Common SNPs showed a limited role in predicting NMIBC outcomes yielding a very low heritability for both outcomes. We report for the first time a heritability estimate for a disease outcome. Our method can be extended to other disease models.

AB - Background: We adapted Bayesian statistical learning strategies to the prognosis field to investigate if genome-wide common SNP improve the prediction ability of clinico-pathological prognosticators and applied it to non-muscle invasive bladder cancer (NMIBC) patients. Methods: Adapted Bayesian sequential threshold models in combination with LASSO were applied to consider the time-to-event and the censoring nature of data. We studied 822 NMIBC patients followed-up >10years. The study outcomes were time-to-first-recurrence and time-to-progression. The predictive ability of the models including up to 171,304 SNP and/or 6 clinico-pathological prognosticators was evaluated using AUC-ROC and determination coefficient. Results: Clinico-pathological prognosticators explained a larger proportion of the time-to-first-recurrence (3.1%) and time-to-progression (5.4%) phenotypic variances than SNPs (1 and 0.01%, respectively). Adding SNPs to the clinico-pathological-parameters model slightly improved the prediction of time-to-first-recurrence (up to 4%). The prediction of time-to-progression using both clinico-pathological prognosticators and SNP did not improve. Heritability (ĥ2) of both outcomes was <1% in NMIBC. Conclusions: We adapted a Bayesian statistical learning method to deal with a large number of parameters in prognostic studies. Common SNPs showed a limited role in predicting NMIBC outcomes yielding a very low heritability for both outcomes. We report for the first time a heritability estimate for a disease outcome. Our method can be extended to other disease models.

KW - AUC-ROC

KW - Bayesian LASSO

KW - Bayesian regression

KW - Bayesian statistical learning method

KW - Bladder cancer outcome

KW - Determination coefficient

KW - Genome-wide common SNP

KW - Heritability

KW - Illumina Infinium HumanHap 1M array

KW - Multimarker models

KW - Predictive ability

KW - Prognosis

KW - Progression

KW - Recurrence

UR - http://www.scopus.com/inward/record.url?scp=84971595193&partnerID=8YFLogxK

U2 - 10.1186/s12885-016-2361-7

DO - 10.1186/s12885-016-2361-7

M3 - Artículo

C2 - 27259534

AN - SCOPUS:84971595193

SN - 1471-2407

VL - 16

JO - BMC Cancer

JF - BMC Cancer

IS - 1

M1 - 351

ER -

Prediction of non-muscle invasive bladder cancer outcomes assessed by innovative multimarker prognostic models

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this