Instrumental variable estimation of early treatment effect in randomized screening trials

被引:1
作者
Saha, Sudipta [1 ]
Liu, Zhihui [2 ]
Saarela, Olli [1 ]
机构
[1] Univ Toronto, Dalla Lana Sch Publ Hlth, 155 Coll St, Toronto, ON M5T 3M7, Canada
[2] Univ Hlth Network, Princess Margaret Canc Ctr, Toronto, ON, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
Causal inference; Instrumental variable estimation; Multi-state model; Randomized screening trial; LUNG-CANCER MORTALITY; COMPETING RISKS; REDUCTIONS; IDENTIFICATION; NONCOMPLIANCE; PROSTATE; SURVIVAL; MODELS; BIAS;
D O I
10.1007/s10985-021-09527-3
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
The primary analysis of randomized screening trials for cancer typically adheres to the intention-to-screen principle, measuring cancer-specific mortality reductions between screening and control arms. These mortality reductions result from a combination of the screening regimen, screening technology and the effect of the early, screening-induced, treatment. This motivates addressing these different aspects separately. Here we are interested in the causal effect of early versus delayed treatments on cancer mortality among the screening-detectable subgroup, which under certain assumptions is estimable from conventional randomized screening trial using instrumental variable type methods. To define the causal effect of interest, we formulate a simplified structural multi-state model for screening trials, based on a hypothetical intervention trial where screening detected individuals would be randomized into early versus delayed treatments. The cancer-specific mortality reductions after screening detection are quantified by a cause-specific hazard ratio. For this, we propose two estimators, based on an estimating equation and a likelihood expression. The methods extend existing instrumental variable methods for time-to-event and competing risks outcomes to time-dependent intermediate variables. Using the multi-state model as the basis of a data generating mechanism, we investigate the performance of the new estimators through simulation studies. In addition, we illustrate the proposed method in the context of CT screening for lung cancer using the US National Lung Screening Trial data.
引用
收藏
页码:537 / 560
页数:24
相关论文
共 47 条
[1]   Does Cox analysis of a randomized survival study yield a causal treatment effect? [J].
Aalen, Odd O. ;
Cook, Richard J. ;
Roysland, Kjetil .
LIFETIME DATA ANALYSIS, 2015, 21 (04) :579-593
[2]   Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic Screening [J].
Aberle, Denise R. ;
Adams, Amanda M. ;
Berg, Christine D. ;
Black, William C. ;
Clapp, Jonathan D. ;
Fagerstrom, Richard M. ;
Gareen, Ilana F. ;
Gatsonis, Constantine ;
Marcus, Pamela M. ;
Sicks, JoRean D. .
NEW ENGLAND JOURNAL OF MEDICINE, 2011, 365 (05) :395-409
[3]   Latent Subgroup Analysis of a Randomized Clinical Trial through a Semiparametric Accelerated Failure Time Mixture Model [J].
Altstein, L. ;
Li, G. .
BIOMETRICS, 2013, 69 (01) :52-61
[4]   A method to estimate treatment efficacy among latent subgroups of a randomized clinical trial [J].
Altstein, Lily L. ;
Li, Gang ;
Elashoff, Robert M. .
STATISTICS IN MEDICINE, 2011, 30 (07) :709-717
[5]  
Angrist JD, 1996, J AM STAT ASSOC, V91, P444, DOI 10.2307/2291629
[6]   Instrumental variable methods for causal inference [J].
Baiocchi, Michael ;
Cheng, Jing ;
Small, Dylan S. .
STATISTICS IN MEDICINE, 2014, 33 (13) :2297-2340
[7]   THE PAIRED AVAILABILITY DESIGN - A PROPOSAL FOR EVALUATING EPIDURAL ANALGESIA DURING LABOR [J].
BAKER, SG ;
LINDEMAN, KS .
STATISTICS IN MEDICINE, 1994, 13 (21) :2269-2278
[8]   Analysis of survival data from a randomized trial with all-or-none compliance: Estimating the cost-effectiveness of a cancer screening program [J].
Baker, SG .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1998, 93 (443) :929-934
[9]   Latent class instrumental variables: a clinical and biostatistical perspective [J].
Baker, Stuart G. ;
Kramer, Barnett S. ;
Lindeman, Karen S. .
STATISTICS IN MEDICINE, 2016, 35 (01) :147-160
[10]  
Beyersmann J., 2011, COMPETING RISKS MULT