Penalized Poisson model for network meta-analysis of individual patient time-to-event data

被引:2
作者
Ollier, Edouard [1 ,2 ,3 ]
Blanchard, Pierre [2 ,4 ]
Le Teuff, Gwenael [1 ,2 ]
Michiels, Stefan [1 ,2 ]
机构
[1] Univ Paris Saclay, Gustave Roussy, Serv Biostat & Epidemiol, Villejuif, France
[2] Univ Paris Saclay, Labeled Ligue Canc, Villejuif, France
[3] Univ Jean Monnet, Equipe DVH, SAINBIOSE U1059, St Etienne, France
[4] Univ Paris Saclay, Gustave Roussy, Dept Radiotherapie, Villejuif, France
关键词
frequentist; individual patient data; lasso; model selection; network meta-analysis; penalized likelihood; time-to-event data; TREATMENT-COVARIATE INTERACTIONS; ECOLOGICAL BIAS; REGRESSION; SELECTION; LASSO; LEVEL;
D O I
10.1002/sim.9240
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Network meta-analysis (NMA) allows the combination of direct and indirect evidence from a set of randomized clinical trials. Performing NMA using individual patient data (IPD) is considered as a "gold standard" approach as it provides several advantages over NMA based on aggregate data. For example, it allows to perform advanced modeling of covariates or covariate-treatment interactions. An important issue in IPD NMA is the selection of influential parameters among terms that account for inconsistency, covariates, covariate-by-treatment interactions or nonproportionality of treatments effect for time to event data. This issue has not been deeply studied in the literature yet and in particular not for time-to-event data. A major difficulty is to jointly account for between-trial heterogeneity which could have a major influence on the selection process. The use of penalized generalized mixed effect model is a solution, but existing implementations have several shortcomings and an important computational cost that precludes their use for complex IPD NMA. In this article, we propose a penalized Poisson regression model to perform IPD NMA of time-to-event data. It is based only on fixed effect parameters which improve its computational cost over the use of random effects. It could be easily implemented using existing penalized regression package. Computer code is shared for implementation. The methods were applied on simulated data to illustrate the importance to take into account between trial heterogeneity during the selection procedure. Finally, it was applied to an IPD NMA of overall survival of chemotherapy and radiotherapy in nasopharyngeal carcinoma.
引用
收藏
页码:340 / 355
页数:16
相关论文
共 29 条
  • [1] Asymptotic normality of posterior distributions for generalized linear mixed models
    Baghishani, Hossein
    Mohammadzadeh, Mohsen
    [J]. JOURNAL OF MULTIVARIATE ANALYSIS, 2012, 111 : 66 - 77
  • [2] Individual patient- versus group-level data meta-regressions for the investigation of treatment effect modifiers: ecological bias rears its ugly head
    Berlin, JA
    Santanna, J
    Schmid, CH
    Szczech, LA
    Feldman, HI
    [J]. STATISTICS IN MEDICINE, 2002, 21 (03) : 371 - 387
  • [3] Chemotherapy and radiotherapy in nasopharyngeal carcinoma: an update of the MAC-NPC meta-analysis
    Blanchard, Pierre
    Lee, Anne
    Marguet, Sophie
    Leclercq, Julie
    Ng, Wai Tong
    Ma, Jun
    Chan, Anthony T. C.
    Huang, Pei-Yu
    Benhamou, Ellen
    Zhu, Guopei
    Chua, Daniel T. T.
    Chen, Yong
    Mai, Hai-Qiang
    Kwong, Dora L. W.
    Cheah, Shie Lee
    Moon, James
    Tung, Yuk
    Chi, Kwan-Hwa
    Fountzilas, George
    Zhang, Li
    Hui, Edwin Pun
    Lu, Tai-Xiang
    Bourhis, Jean
    Pignon, Jean Pierre
    [J]. LANCET ONCOLOGY, 2015, 16 (06) : 645 - 655
  • [4] Individual patient data meta-analysis of survival data using Poisson regression models
    Crowther, Michael J.
    Riley, Richard D.
    Staessen, Jan A.
    Wang, Jiguang
    Gueyffier, Francois
    Lambert, Paul C.
    [J]. BMC MEDICAL RESEARCH METHODOLOGY, 2012, 12
  • [5] Degree irregularity and rank probability bias in network meta-analysis
    Davies, Annabel L.
    Galla, Tobias
    [J]. RESEARCH SYNTHESIS METHODS, 2021, 12 (03) : 316 - 332
  • [6] An overview of methods for network meta-analysis using individual participant data: when do benefits arise?
    Debray, Thomas P. A.
    Schuit, Ewoud
    Efthimiou, Orestis
    Reitsma, Johannes B.
    Ioannidis, John P. A.
    Salanti, Georgia
    Moons, Karel G. M.
    [J]. STATISTICAL METHODS IN MEDICAL RESEARCH, 2018, 27 (05) : 1351 - 1364
  • [7] Individual Participant Data Meta-Analysis for a Binary Outcome: One-Stage or Two-Stage?
    Debray, Thomas P. A.
    Moons, Karel G. M.
    Abo-Zaid, Ghada Mohammed Abdallah
    Koffijberg, Hendrik
    Riley, Richard David
    [J]. PLOS ONE, 2013, 8 (04):
  • [8] Least angle regression - Rejoinder
    Efron, B
    Hastie, T
    Johnstone, I
    Tibshirani, R
    [J]. ANNALS OF STATISTICS, 2004, 32 (02) : 494 - 499
  • [9] Stochastic proximal-gradient algorithms for penalized mixed models
    Fort, Gersende
    Ollier, Edouard
    Samson, Adeline
    [J]. STATISTICS AND COMPUTING, 2019, 29 (02) : 231 - 253
  • [10] A framework for identifying treatment-covariate interactions in individual participant data network meta-analysis
    Freeman, S. C.
    Fisher, D.
    Tierney, J. F.
    Carpenter, J. R.
    [J]. RESEARCH SYNTHESIS METHODS, 2018, 9 (03) : 393 - 407