ANOVA model for network meta-analysis of diagnostic test accuracy data

Statistical Methods in Medical Research - Tập 27 Số 6 - Trang 1766-1784 - 2018
Victoria Nyawira Nyaga1,2, Marc Aerts1, Marc Arbyn2
1Hasselt University, I-BioStat, Diepenbeek, Belgium
2Scientific Institute of Public Health, Unit of Cancer Epidemiology/Belgian Cancer Center, Belgium

Tóm tắt

Procedures combining and summarising direct and indirect evidence from independent studies assessing the diagnostic accuracy of different tests for the same disease are referred to network meta-analysis. Network meta-analysis provides a unified inference framework and uses the data more efficiently. Nonetheless, handling the inherent correlation between sensitivity and specificity continues to be a statistical challenge. We developed an arm-based hierarchical model which expresses the logit transformed sensitivity and specificity as the sum of fixed effects for test, correlated study-effects to model the inherent correlation between sensitivity and specificity and a random error associated with various tests evaluated in a given study. We present the accuracy of 11 tests used to triage women with minor cervical lesions to detect cervical precancer. Finally, we compare the results with those from a contrast-based model which expresses the linear predictor as a contrast to a comparator test. The proposed arm-based model is more appealing than the contrast-based model since the former permits more straightforward interpretation of the parameters, makes use of all available data yielding shorter credible intervals, and models more natural variance–covariance matrix structures.

Từ khóa


Tài liệu tham khảo

Higgins J, 1996, Stat Med, 15, 2733, 10.1002/(SICI)1097-0258(19961230)15:24<2733::AID-SIM562>3.0.CO;2-0

Fisher L, 1989, Statistical issues in drug research and development, 331

Lumley T, 2002, Stat Med, 21, 2313, 10.1002/sim.1201

Menten J, 2015, BMC Med Res Methodol, 15, 1, 10.1186/s12874-015-0061-7

10.1177/009286150003400222

Whitehead A, 2002, Meta-analysis of controlled clinical trials, 7, 10.1002/0470854200

Piepho HP, 2012, Biometrics, 68, 1269, 10.1111/j.1541-0420.2012.01786.x

Zhou XH, 2011, Design of diagnostic accuracy studies, 10.1002/9780470906514.ch3

Sinclair JC, 1994, J Clin Epidemiol, 47, 881, 10.1016/0895-4356(94)90191-0

Davies HTO, 1998, BMJ, 316, 989, 10.1136/bmj.316.7136.989

10.1177/1740774513498322

Arbyn M, 2012, Vaccine, 30, F88, 10.1016/j.vaccine.2012.06.095

Arbyn M, 2013, Cochrane Database Syst Rev, 3, CD008054

Arbyn M, 2013, Int J Cancer, 132, 101, 10.1002/ijc.27636

Roelens J, 2012, Cancer Cytopathol, 120, 294, 10.1002/cncy.21205

Verdoodt F, 2013, Cancer Cytopathol, 121, 675, 10.1002/cncy.21325

Bosch F, 2002, J Clin Pathol, 55, 244, 10.1136/jcp.55.4.244

Arbyn M, 2009, Int J Cancer, 125, 2489, 10.1002/ijc.24774

Daniels MJ, 2009, J Multivariate Anal, 100, 2352, 10.1016/j.jmva.2009.04.015

Reitsma JB, 2005, J Clin Epidemiol, 58, 982, 10.1016/j.jclinepi.2005.02.022

Chu H, 2006, J Clin Epidemiol, 59, 1331, 10.1016/j.jclinepi.2006.06.011

Altham PM, 1984, J Royal Stat Soc Ser B, 46, 118, 10.1111/j.2517-6161.1984.tb01283.x

Verbeke G, 2002, Linear mixed models for longitudinal data, 64

Watanabe S, 2010, J Mach Learn Res, 11, 3571

Glas AS, 2003, J Clin Epidemiol, 56, 1129, 10.1016/S0895-4356(03)00177-X

Deutsch R, 2009, J Data Sci, 7, 161, 10.6339/JDS.2009.07(2).450

Rubin DB, 1976, Biometrika, 63, 581, 10.1093/biomet/63.3.581

Little RJ, 1987, Statistical analysis with missing data

Lewandowski D, 2009, J Multivariate Anal, 100, 1989, 10.1016/j.jmva.2009.04.008

Gelman A, 2006, Data analysis using regression and multilevel/hierarchical models, 286, 10.1017/CBO9780511790942

Carpenter B, Journal of Statistical Software

Hoffman MD, 2014, J Mach Learn Res, 15, 1593

Schafer JL, 2002, Psychol Meth, 7, 147, 10.1037/1082-989X.7.2.147

Agresti A, 2002, Categorical data analysis, 2, 131, 10.1002/0471249688

Crowder MJ, 1978, Appl Stat, 27, 34, 10.2307/2346223

Nyaga V, 2015, Archive Public Health, 73, O4, 10.1186/2049-3258-73-S1-O4

Lu G, 2004, Stat Med, 23, 3105, 10.1002/sim.1875

Dias S, 2010, Stat Med, 29, 932, 10.1002/sim.3767

Krahn U, 2014, BMC Med Res Method, 14, 131, 10.1186/1471-2288-14-131

Hong H, 2015, Res Synth Meth, 7, 6, 10.1002/jrsm.1153

Piepho HP, 2014, BMC Med Res Methodol, 14, 61, 10.1186/1471-2288-14-61

Valenstein PN, 1990, Am J Clin Pathol, 93, 252, 10.1093/ajcp/93.2.252

Reitsma JB, 2009, J Clin Epidemiol, 62, 797, 10.1016/j.jclinepi.2009.02.005

Arbyn M, 2009, Int J Cancer, 125, 2489, 10.1002/ijc.24774

Thông tin
Thông tin xuất bản

Statistical Methods in Medical Research

Tập 27 Số 6

1766-1784

Thông tin tác giả