Display options
Cite
Kang L, Carter R, Darcy K, et al. A fast Monte Carlo EM algorithm for estimation in latent class model analysis with an application to assess diagnostic accuracy for cervical neoplasia in women with AGC. J Appl Stat. 2013;40(12):2699-2719doi: 10.1080/02664763.2013.825704.
Kang, L., Carter, R., Darcy, K., Kauderer, J., & Liao, S. Y. (2013). A fast Monte Carlo EM algorithm for estimation in latent class model analysis with an application to assess diagnostic accuracy for cervical neoplasia in women with AGC. Journal of applied statistics, 40(12), 2699-2719. https://doi.org/10.1080/02664763.2013.825704
Kang, Le, et al. "A fast Monte Carlo EM algorithm for estimation in latent class model analysis with an application to assess diagnostic accuracy for cervical neoplasia in women with AGC." Journal of applied statistics vol. 40,12 (2013): 2699-2719. doi: https://doi.org/10.1080/02664763.2013.825704
Kang L, Carter R, Darcy K, Kauderer J, Liao SY. A fast Monte Carlo EM algorithm for estimation in latent class model analysis with an application to assess diagnostic accuracy for cervical neoplasia in women with AGC. J Appl Stat. 2013;40(12):2699-2719. doi: 10.1080/02664763.2013.825704. PMID: 24163493; PMCID: PMC3806648.
Copy Download .nbib Format: NLM
Share it on

J Appl Stat. 2013;40(12):2699-2719. doi: 10.1080/02664763.2013.825704.

A fast Monte Carlo EM algorithm for estimation in latent class model analysis with an application to assess diagnostic accuracy for cervical neoplasia in women with AGC.

Journal of applied statistics

Le Kang, Randy Carter, Kathleen Darcy, James Kauderer, Shu-Yuan Liao

Affiliations

  1. USFDA CDRH, 10903 New Hampshire Ave, Silver Spring, MD 20993.

PMID: 24163493 PMCID: PMC3806648 DOI: 10.1080/02664763.2013.825704

Abstract

In this article we use a latent class model (LCM) with prevalence modeled as a function of covariates to assess diagnostic test accuracy in situations where the true disease status is not observed, but observations on three or more conditionally independent diagnostic tests are available. A fast Monte Carlo EM (MCEM) algorithm with binary (disease) diagnostic data is implemented to estimate parameters of interest; namely, sensitivity, specificity, and prevalence of the disease as a function of covariates. To obtain standard errors for confidence interval construction of estimated parameters, the missing information principle is applied to adjust information matrix estimates. We compare the adjusted information matrix based standard error estimates with the bootstrap standard error estimates both obtained using the fast MCEM algorithm through an extensive Monte Carlo study. Simulation demonstrates that the adjusted information matrix approach estimates the standard error similarly with the bootstrap methods under certain scenarios. The bootstrap percentile intervals have satisfactory coverage probabilities. We then apply the LCM analysis to a real data set of 122 subjects from a Gynecologic Oncology Group (GOG) study of significant cervical lesion (S-CL) diagnosis in women with atypical glandular cells of undetermined significance (AGC) to compare the diagnostic accuracy of a histology-based evaluation, a CA-IX biomarker-based test and a human papillomavirus (HPV) DNA test.

Keywords: MCEM estimation; adjusted information matrix; bootstrap standard errors; diagnostic accuracy; imperfect gold standard; latent class model

References

  1. JAMA. 2007 Feb 28;297(8):813-9 - PubMed
  2. Stat Med. 2001 Jul 15;20(13):1987-2001 - PubMed
  3. Lifetime Data Anal. 2002 Dec;8(4):349-60 - PubMed
  4. JAMA. 1984 Nov 2;252(17):2418-22 - PubMed
  5. Diagn Cytopathol. 1995 Dec;13(5):463-9 - PubMed
  6. J Clin Epidemiol. 1988;41(9):923-37 - PubMed
  7. Biometrics. 2004 Jun;60(2):427-35 - PubMed
  8. Gynecol Oncol. 1996 Oct;63(1):14-8 - PubMed
  9. Biometrics. 1997 Sep;53(3):948-58 - PubMed
  10. Diagn Cytopathol. 1995 Oct;13(3):202-8 - PubMed
  11. N Engl J Med. 1975 Jul 31;293(5):211-5 - PubMed
  12. Semin Nucl Med. 1978 Oct;8(4):283-98 - PubMed
  13. Prev Vet Med. 2000 May 30;45(1-2):107-22 - PubMed
  14. Biometrics. 2009 Dec;65(4):1145-55 - PubMed
  15. Biostatistics. 2007 Apr;8(2):474-84 - PubMed
  16. Int J Cancer. 2009 Nov 15;125(10):2434-40 - PubMed
  17. Stat Methods Med Res. 1998 Dec;7(4):354-70 - PubMed
  18. Biometrics. 1985 Dec;41(4):959-68 - PubMed

Publication Types

Grant support