Bayesian Estimation of Performance Measures of Cervical Cancer Screening Tests in the Presence of Covariates and Absence of a Gold Standard

Cancer Informatics - Tập 6 - Trang 117693510800600 - 2008
Edson Zangiacomí Martínez1, Francisco Louzada2, Sophie Derchain3, Jorge Alberto Achcar2,1, Renata Clementino Gontijo3, Luı́s Otávio Sarian3, Karí Syrjänen4
1Departamento de Medicina Social, Faculdade de Medicina de Ribeir≈o Preto, Universidade de S≈o Paulo, Ribeir≈o Preto, SP, Brazil.
2Departamento de Estatística, Universidade Federal de S≈o Carlos, S≈o Carlos, SP, Brazil.
3Departamento de Tocoginecologia, Faculdade de Ciências Mέdicas, Universidade Estadual de Campinas, Campinas, SP, Brazil.
4Department of Oncology and Radiotherapy, Turku University Hospital, Turku, Finland

Tóm tắt

In this paper we develop a Bayesian analysis to estimate the disease prevalence, the sensitivity and specificity of three cervical cancer screening tests (cervical cytology, visual inspection with acetic acid and Hybrid Capture II) in the presence of a covariate and in the absence of a gold standard. We use Metropolis-Hastings algorithm to obtain the posterior summaries of interest. The estimated prevalence of cervical lesions was 6.4% (a 95% credible interval [95% CI] was 3.9, 9.3). The sensitivity of cervical cytology (with a result of ≥ ASC-US) was 53.6% (95% CI: 42.1, 65.0) compared with 52.9% (95% CI: 43.5, 62.5) for visual inspection with acetic acid and 90.3% (95% CI: 76.2, 98.7) for Hybrid Capture II (with result of >1 relative light units). The specificity of cervical cytology was 97.0% (95% CI: 95.5, 98.4) and the specificities for visual inspection with acetic acid and Hybrid Capture II were 93.0% (95% CI: 91.0, 94.7) and 88.7% (95% CI: 85.9, 91.4), respectively. The Bayesian model with covariates suggests that the sensitivity and the specificity of the visual inspection with acetic acid tend to increase as the age of the women increases.The Bayesian method proposed here is an useful alternative to estimate measures of performance of diagnostic tests in the presence of covariates and when a gold standard is not available. An advantage of the method is the fact that the number of parameters to be estimated is not limited by the number of observations, as it happens with several frequentist approaches. However, it is important to point out that the Bayesian analysis requires informative priors in order for the parameters to be identifiable. The method can be easily extended for the analysis of other medical data sets.

Từ khóa


Tài liệu tham khảo

10.2307/2530820

10.1080/03610929308831209

10.2307/2530508

10.1093/oxfordjournals.aje.a117428

10.1016/S1470-2045(03)00973-2

Mitchell M.F., 1998, Obstet Gynecol, 91, 626

10.1097/00006254-199802000-00021

10.1002/sim.4780060402

10.1177/096228029800700404

10.1177/096228029800700403

10.1111/j.0006-341X.2001.00158.x

10.1176/ajp.151.5.650

10.2307/2533043

Hadgu A., 1998, Appl Statist, 47, 603

10.1080/01621459.1987.10478458

10.1080/01621459.1990.10476213

10.1080/01621459.2000.10474335

Syrjanen K., 2005, Anticancer Res, 25, 3469

10.1258/0969141054855328

10.1001/jama.287.16.2114

Blumenthal P., 1997, Atlas for unaided visual inspection of the cervix.

10.7326/0003-4819-132-10-200005160-00009

Belinson J.L., 2001, Obstet Gynecol, 98, 441

10.1016/S0140-6736(98)07033-0

10.1001/jama.283.1.87

10.1001/jama.283.1.81

10.1002/9781118033197

10.1136/bmj.309.6947.102

10.1093/oxfordjournals.jncimonographs.a003488

Geweke J., 1992, Bayesian Statistics 4, 169, 10.1093/oso/9780198522669.003.0010

10.1201/9781420057669

10.1001/jama.283.19.2525

Shlay J.C., 2000, Obstet Gynecol, 96, 410

10.1111/1467-9868.00353

10.1016/S0002-9378(99)70586-7

10.1002/sim.1227

Brenner H., Stat Med

10.2307/2531499

10.2307/2533555

Ratman S., 2000, Cancer Epidemiol Biomarkers Prev, 9, 945

10.1136/bmj.326.7392.733

10.1001/jama.283.19.2525

Londhe M., 1997, Indian J Cancer, 34, 88

10.1002/(SICI)1097-0142(19981115)83:10<2150::AID-CNCR13>3.0.CO;2-0

10.1002/(SICI)1097-0215(19990105)80:1<161::AID-IJC28>3.0.CO;2-8

10.1002/1097-0142(20000815)89:4<826::AID-CNCR15>3.0.CO;2-5

10.1002/cncr.10381

10.1191/0962280202sm307ra

10.1001/jama.283.19.2525

Smith AFM., 1993, J R Stat SocB, 55, 3, 10.1111/j.2517-6161.1993.tb01466.x

Thông tin
Thông tin xuất bản

Cancer Informatics

Tập 6

117693510800600

Thông tin tác giả