DOI QR코드

DOI QR Code

Misclassification Adjustment of Family History of Breast Cancer in a Case-Control Study: a Bayesian Approach

  • Moradzadeh, Rahmatollah (Department of Epidemiology and Biostatistics, School of Public Health, Tehran University of Medical Sciences) ;
  • Mansournia, Mohammad Ali (Department of Epidemiology and Biostatistics, School of Public Health, Tehran University of Medical Sciences) ;
  • Baghfalaki, Taban (Department of Statistics, Faculty of Mathematical Sciences, Tarbiat Modares University) ;
  • Ghiasvand, Reza (Oslo Center for Biostatistics and Epidemiology, Institute of Basic Medical Sciences, University of Oslo) ;
  • Noori-Daloii, Mohammad Reza (Department of Medical Genetics, School of Medicine, Tehran University of Medical Sciences) ;
  • Holakouie-Naieni, Kourosh (Department of Epidemiology and Biostatistics, School of Public Health, Tehran University of Medical Sciences)
  • Published : 2016.01.11

Abstract

Background: Misreporting self-reported family history may lead to biased estimations. We used Bayesian methods to adjust for exposure misclassification. Materials and Methods: A hospital-based case-control study was used to identify breast cancer risk factors among Iranian women. Three models were jointly considered; an outcome, an exposure and a measurement model. All models were fitted using Bayesian methods, run to achieve convergence. Results: Bayesian analysis in the model without misclassification showed that the odds ratios for the relationship between breast cancer and a family history in different prior distributions were 2.98 (95% CRI: 2.41, 3.71), 2.57 (95% CRI: 1.95, 3.41) and 2.53 (95% CRI: 1.93, 3.31). In the misclassified model, adjusted odds ratios for misclassification in the different situations were 2.64 (95% CRI: 2.02, 3.47), 2.64 (95% CRI: 2.02, 3.46), 1.60 (95% CRI: 1.07, 2.38), 1.61 (95% CRI: 1.07, 2.40), 1.57 (95% CRI: 1.05, 2.35), 1.58 (95% CRI: 1.06, 2.34) and 1.57 (95% CRI: 1.06, 2.33). Conclusions: It was concluded that self-reported family history may be misclassified in different scenarios. Due to the lack of validation studies in Iran, more attention to this matter in future research is suggested, especially while obtaining results in accordance with sensitivity and specificity values.

Keywords

Misclassification;bias;Bayesian assessment;self-report

Acknowledgement

Supported by : Tehran University of Medical Sciences

References

  1. Akbari A, Razzaghi Z, Homaee F, et al (2011). Parity and breastfeeding are preventive measures against breast cancer in Iranian women. Breast Cancer, 18, 51-5. https://doi.org/10.1007/s12282-010-0203-z
  2. Chu H, Wang Z, Cole S, et al (2006). Sensitivity analysis of misclassification: A graphical and a Bayesian approach. Ann Epidemiol, 16, 834-41. https://doi.org/10.1016/j.annepidem.2006.04.001
  3. Ebrahimi M, Vahdaninia M, Montazeri A (2002). Risk factors for breast cancer in Iran: a case-control study. Breast Cancer Res, 4, R10. https://doi.org/10.1186/bcr454
  4. Fox M, Lash T, Greenland S (2005). A method to automate probabilistic sensitivity analyses of misclassified binary variables. International J Epidemiol, 36, 1370-6.
  5. Gelman A, Carlin JB, Stern HS, et al 2003. Bayesian Data Analysis, London, CRC Press.
  6. Gelman A, Rubin DB ( 1992). Inference from iterative simulation using multiple sequences. Statistical Science, 7, 457-511. https://doi.org/10.1214/ss/1177011136
  7. Ghiasvand R, Bahmanyar S, Zendehdel K, et al (2012). Postmenopausal breast cancer in Iran; risk factors and their population attributable fractions. BMC Cancer, 12, 414. https://doi.org/10.1186/1471-2407-12-414
  8. Ghiasvand R, Maram ES, Tahmasebi S, et al (2011). Risk factors for breast cancer among young women in southern Iran. International J Cancer, 129, 1443-9. https://doi.org/10.1002/ijc.25748
  9. Greenland S (2005). Multiple-bias modelling for analysis of observational data. J Royal Statistical Society, A, 168, 1-25. https://doi.org/10.1111/j.1467-985X.2004.00333.x
  10. Greenland S (2008). Invited commentary: variable selection versus shrinkage in the control of multiple confounders. Am J Epidemiology, 167, 523-9.
  11. Greenland S (2009). Bayesian perspectives for epidemiologic research: III. Bias analysis via missing-data methods. International J Epidemiol, 38, 1662-73. https://doi.org/10.1093/ije/dyp278
  12. Greenland S, Lash T (2008). Bias analysis. In 'Modern Epidemiology', Eds Lippincott-Williams-Wilkins, Philadelphia, 345-80
  13. Greenland S, Mansournia MA (2015). Penalization, bias reduction, and default priors in logistic and related categorical and survival regressions. Statistics in Medicine, 34, 3133-43. https://doi.org/10.1002/sim.6537
  14. Hamra G, MacLehose R, Richardson D (2013a). Marcov Chain Monte Carlo: an introduction for epidemiologists. International J Epidemiol, 42, 627-34. https://doi.org/10.1093/ije/dyt043
  15. Hamra GB, MacLehose RF, Cole SR (2013b). Sensitivity analyses for sparse-data problems-using weakly informative bayesian priors. Epidemiology (Cambridge, Mass.), 24, 233-9. https://doi.org/10.1097/EDE.0b013e318280db1d
  16. Hassanzadeh J, Moradzadeh R, Rajaee fard A, et al (2012). A comparison of case-control and case-only designs to investigate gene-environment interactions using breast cancer data. Iranian Journal of Medical Sciences, 37, 112-8.
  17. Holakouie-Naieni K, Ardalan A, Mahmoodi M, et al (2007). Risk factors of breast cancer in North of Iran: A Case-Control in Mazandaran Province. Asian Pac J Cancer Prev, 8, 395-8.
  18. Hosseinzadeh M, Eivazi Ziaei J, Mahdavi N, et al (2014). Risk factors for breast cancer in Iranian women: a hospitalbased case-control study in tabriz, Iran. J Breast Cancer, 17, 236-43. https://doi.org/10.4048/jbc.2014.17.3.236
  19. Jurek AM, Lash TL, Maldonado G (2009). Specifying exposure classification parameters for sensitivity analysis: family breast cancer history. Clinical Epidemiology, 1, 109-17.
  20. Keil AP, Daniels JL, Hertz-Picciotto I (2014). Autism spectrum disorder, flea and tick medication, and adjustments for exposure misclassification: the CHARGE (CHildhood Autism Risks from Genetics and Environment) case-control study. Environmental Health, 13, 3. https://doi.org/10.1186/1476-069X-13-3
  21. Lash T, Fink A (2003). Semi-automated sensitivity analysis to assess systematic errors in observational data. Epidemiology, 14, 451-8.
  22. Lash TL, Fox MP, Fink AK 2009. Applying quantitative bias analysis to epidemiologic data, berlin, Germany, Springer.
  23. Lash TL, Fox MP, MacLehose RF, et al (2014). Good practices for quantitative bias analysis. International Journal of Epidemiology, 43, 1969-85. https://doi.org/10.1093/ije/dyu149
  24. MacLehose RF, Gustafson P (2012 January). Is probabilistic bias analysis approximately Bayesian? Epidemiology, 23, 151-8. https://doi.org/10.1097/EDE.0b013e31823b539c
  25. MacLehose RF, Olshan AF, Herring AH, et al (2009). Bayesian Methods for Correcting Misclassification: An Example from Birth Defects Epidemiology. Epidemiology, 20, 27-35. https://doi.org/10.1097/EDE.0b013e31818ab3b0
  26. Mahouri K, Dehghani-Zahedani M, Zare S (2007 Nov-Dec). Breast cancer risk factors in south of Islamic Republic of Iran: a case-control study. East Mediterr Health J, 13, 1265-73. https://doi.org/10.26719/2007.13.6.1265
  27. Marrie RA, Cutter G, Tyry T, et al (2008). Smoking status over two years in patients with multiple sclerosis. Neuroepidemiology, 32, 72-9.
  28. Prescott GJ, Garthwaite PH (2005). Bayesian analysis of misclassified binary data from a matched case-control study with a validation sub-study. Statistics in Medicine, 24, 379-401. https://doi.org/10.1002/sim.2000
  29. Rothman KJ, Greenland S, Lash TL (2008). Validity in epidemiologic studies. in 'modern epidemiology', eds lippincott williams and wilkins, Philadelphia, 128-47
  30. Sepandi M, Akrami M, Tabatabaee H, et al (2014). Breast Cancer Risk Factors in Women Participating in a Breast Screening Program: a Study on 11,850 Iranian Females. Asian Pac J Cancer Prev, 15, 8499-502. https://doi.org/10.7314/APJCP.2014.15.19.8499
  31. Szatmari P, Jones MB (1999). Effects of misclassification on estimates of relative risk in family history studies. Genetic Epidemiology, 16, 368-81. https://doi.org/10.1002/(SICI)1098-2272(1999)16:4<368::AID-GEPI4>3.0.CO;2-A
  32. Tehranifar P, Wu H-C, Shriver T, et al (2015). Validation of family cancer history data in high-risk families: the influence of cancer site, ethnicity, kinship degree, and multiple family reporters. American Journal of Epidemiology.
  33. van Gelder MMHJ, Donders ART, Devine O, et al (2014a). Using bayesian models to assess the effects of under-reporting of cannabis use on the association with birth defects, national birth defects prevention study, 1997-2005. Paediatric and Perinatal Epidemiology, 28, 424-33. https://doi.org/10.1111/ppe.12140
  34. van Gelder MMHJ, Donders ART, Devine O, et al (2014b). Using bayesian models to assess the effects of under-reporting of cannabis use on the association with birth defects, national birth defects prevention study, 1997-2005. Paediatric and Perinatal Epidemiology, n/a-n/a.
  35. Veisy A, Lotfinejad S, Salehi K, et al (2015). Risk of breast cancer in relation to reproductive factors in north-west of Iran, 2013-2014. Asian Pac J Cancer Prev, 16, 451-5. https://doi.org/10.7314/APJCP.2015.16.2.451
  36. Zare N, Haem E, Lankarani KB, et al (2013). Breast cancer risk factors in a defined population: weighted logistic regression approach for rare events. J Breast Cancer, 16, 214-9. https://doi.org/10.4048/jbc.2013.16.2.214

Cited by

  1. Incidence of Esophageal Cancer in Iran, a Population-Based Study: 2001–2015 pp.1941-6636, 2018, https://doi.org/10.1007/s12029-018-0114-3