OpenLB
Open Library of Bioscience
Advanced Search
Statistics in medicine
12 10, 2016;35 (28): 5267-5282.

Bayesian joint ordinal and survival modeling for breast cancer risk assessment.

C Armero, C Forné, M Rué, A Forte, H Perpiñán, G Gómez, M Baré
Author Information
  1. C Armero: Department of Statistics and Operational Research, Universitat de València, Doctor Moliner, 50, 46100, Burjassot, Spain. Carmen.Armero@uv.es.
  2. C Forné: Department of Basic Medical Sciences, Universitat de Lleida-IRBLleida, Avda. Rovira Roure, 80, 25198, Lleida, Spain.
  3. M Rué: Department of Basic Medical Sciences, Universitat de Lleida-IRBLleida, Avda. Rovira Roure, 80, 25198, Lleida, Spain.
  4. A Forte: Department of Statistics and Operational Research, Universitat de València, Doctor Moliner, 50, 46100, Burjassot, Spain.
  5. H Perpiñán: Department of Statistics and Operational Research, Universitat de València, Doctor Moliner, 50, 46100, Burjassot, Spain.
  6. G Gómez: Department of Statistics and Operations Research, Universitat Politècnica de Catalunya, Barcelona, Spain. ORCID
  7. M Baré: Clinical Epidemiology and Cancer Screening, Corporació Sanitària Parc Taulí-UAB, Sabadell, Parc Taulí s/n, Sabadell, 08208, Spain.
PMID: 27523800 DOI: 10.1002/sim.7065

Abstract

We propose a joint model to analyze the structure and intensity of the association between longitudinal measurements of an ordinal marker and time to a relevant event. The longitudinal process is defined in terms of a proportional-odds cumulative logit model. Time-to-event is modeled through a left-truncated proportional-hazards model, which incorporates information of the longitudinal marker as well as baseline covariates. Both longitudinal and survival processes are connected by means of a common vector of random effects. General inferences are discussed under the Bayesian approach and include the posterior distribution of the probabilities associated to each longitudinal category and the assessment of the impact of the baseline covariates and the longitudinal marker on the hazard function. The flexibility provided by the joint model makes possible to dynamically estimate individual event-free probabilities and predict future longitudinal marker values. The model is applied to the assessment of breast cancer risk in women attending a population-based screening program. The longitudinal ordinal marker is mammographic breast density measured with the Breast Imaging Reporting and Data System (BI-RADS) scale in biennial screening exams. © 2016 The Authors. Statistics in Medicine Published by John Wiley & Sons Ltd.

Keywords

BI-RADS scale Latent process Proportional-odds cumulative logit model left-truncated proportional-hazards model

References

  1. J Natl Cancer Inst. 2007 Mar 7;99(5):386-95 [PMID: 17341730]
  2. J Natl Cancer Inst. 1989 Dec 20;81(24):1879-86 [PMID: 2593165]
  3. PLoS One. 2014 Feb 03;9(2):e86858 [PMID: 24498285]
  4. Biometrics. 1997 Mar;53(1):330-9 [PMID: 9147598]
  5. Stat Med. 2014 Feb 20;33(4):580-94 [PMID: 24009073]
  6. Cancer Epidemiol Biomarkers Prev. 1998 Dec;7(12):1133-44 [PMID: 9865433]
  7. Stat Med. 2011 May 10;30(10):1090-104 [PMID: 21337591]
  8. Biometrics. 2011 Sep;67(3):819-29 [PMID: 21306352]
  9. Breast Cancer Res Treat. 2014 Apr;144(3):479-502 [PMID: 24615497]
  10. Stat Methods Med Res. 2016 Dec;25(6):2714-2732 [PMID: 24770852]
  11. Breast Cancer Res Treat. 2005 Nov;94(2):115-22 [PMID: 16261410]
  12. Stat Med. 2014 Aug 15;33(18):3167-78 [PMID: 24676841]
  13. Stat Med. 1996 Aug 15;15(15):1663-85 [PMID: 8858789]
  14. J Med Screen. 2006;13(4):183-91 [PMID: 17217607]
  15. Biometrics. 2013 Mar;69(1):206-13 [PMID: 23379600]
  16. Stat Methods Med Res. 2016 Oct;25(5):2180-2192 [PMID: 24448442]
  17. Stat Med. 2016 Feb 10;35(3):382-98 [PMID: 26376900]
  18. Stat Med. 2001 Aug 15;20(15):2261-85 [PMID: 11468763]
  19. Stat Med. 2004 Apr 15;23(7):1111-30 [PMID: 15057881]
  20. Cancer Epidemiol Biomarkers Prev. 2004 May;13(5):715-22 [PMID: 15159301]
  21. Stat Med. 1997 Jan 15-Feb 15;16(1-3):239-57 [PMID: 9004395]
  22. Breast Cancer Res. 2007;9(6):217 [PMID: 18190724]
  23. Stat Med. 2016 Dec 10;35(28):5267-5282 [PMID: 27523800]
  24. Comput Math Methods Med. 2010 Sep;11(3):281-95 [PMID: 20721765]
  25. Cancer Epidemiol Biomarkers Prev. 2015 Jun;24(6):889-97 [PMID: 25824444]
  26. Stat Med. 2010 Feb 28;29(5):546-57 [PMID: 19943331]
  27. Biometrics. 2010 Mar;66(1):20-9 [PMID: 19459832]
  28. Ann Intern Med. 2008 Mar 4;148(5):337-47 [PMID: 18316752]
  29. J Natl Cancer Inst. 2006 Sep 6;98(17):1215-26 [PMID: 16954474]
  30. Int J Cancer. 2014 Oct 1;135(7):1740-4 [PMID: 24599445]
  31. Stat Methods Med Res. 2016 Aug;25(4):1346-58 [PMID: 23592717]
  32. Eur J Cancer Prev. 2008 Oct;17(5):414-21 [PMID: 18714182]
  33. Eur J Cancer Prev. 2003 Dec;12(6):487-94 [PMID: 14639126]
  34. Eur J Cancer Prev. 1999 Dec;8(6):509-15 [PMID: 10643940]
  35. Cancer Epidemiol Biomarkers Prev. 2007 May;16(5):921-8 [PMID: 17507617]
  36. Stat Methods Med Res. 2018 Jan;27(1):298-311 [PMID: 26988933]
  37. Breast Cancer Res Treat. 2012 May;133(1):1-10 [PMID: 22076477]
  38. Cancer. 2014 Oct 1;120(19):2955-64 [PMID: 24830599]
  39. J Natl Cancer Inst. 1995 Nov 1;87(21):1622-9 [PMID: 7563205]
  40. Am J Epidemiol. 2013 Jul 1;178(1):101-9 [PMID: 23703889]
  41. J Natl Cancer Inst. 2006 Sep 6;98(17):1204-14 [PMID: 16954473]

MeSH Term

Bayes Theorem
Breast
Breast Density
Breast Neoplasms
Female
Humans
Risk Assessment
Journal Article
Article has an altmetric score of 4

Word Cloud

Created with Highcharts 10.0.0longitudinalmodelmarkerjointordinalassessmentbreastprocesscumulativelogitleft-truncatedproportional-hazardsbaselinecovariatessurvivalBayesianprobabilitiescancerriskscreeningBI-RADSscaleproposeanalyzestructureintensityassociationmeasurementstimerelevanteventdefinedtermsproportional-oddsTime-to-eventmodeledincorporatesinformationwellprocessesconnectedmeanscommonvectorrandomeffectsGeneralinferencesdiscussedapproachincludeposteriordistributionassociatedcategoryimpacthazardfunctionflexibilityprovidedmakespossibledynamicallyestimateindividualevent-freepredictfuturevaluesappliedwomenattendingpopulation-basedprogrammammographicdensitymeasuredBreastImagingReportingDataSystembiennialexams©2016AuthorsStatisticsMedicinePublishedJohnWiley&SonsLtdmodelingLatentProportional-odds

Similar Articles

Cited By