Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is...
-
Upload
duongquynh -
Category
Documents
-
view
226 -
download
3
Transcript of Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is...
![Page 1: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/1.jpg)
Subject Randomization SystemInfrastructure for Clinical Trials
Balasubramanian Narasimhan
Stanford University
July 9, 2009
![Page 2: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/2.jpg)
A Clinical Trial is launched
A researcher comes to me with a straightforward problem.Two arm trial A and B. Need to randomize subjects to either arm (1:1).Say 60 subjects overall.Easy thing to do: Permuted Block randomization.After all, paper is a versatile instrument. . .
There ought to be a better way!
B. Narasimhan (SU) Subject Randomization System userR! 2009 2 / 24
![Page 3: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/3.jpg)
A Clinical Trial is launched
A researcher comes to me with a straightforward problem.Two arm trial A and B. Need to randomize subjects to either arm (1:1).Say 60 subjects overall.Easy thing to do: Permuted Block randomization.After all, paper is a versatile instrument. . .There ought to be a better way!
B. Narasimhan (SU) Subject Randomization System userR! 2009 2 / 24
![Page 4: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/4.jpg)
Efron’s Biased Coin Design (Biometrika, 1971)
Two arms in a clinical trial: A and B.Idea: Allocation probability to treatment A changes to keep balance ineach group nearly equalThe total number of subjects so far: n = nA + nB , where nA is numberassigned to A and nB is number assigned to B.Initially, n = nA = nB = 0. Let p = P(Subject gets treatment A).
Let “running difference” D = nA − nB
Set
p =
12 , if D = 0;23 , if D < 0;13 , if D > 0.
B. Narasimhan (SU) Subject Randomization System userR! 2009 3 / 24
![Page 5: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/5.jpg)
Implementation for a Multicenter Trial
Note that nA and nB (and consequently D) change with each newsubject recruited into the trial
Some persistence (or a mechanism) is necessary to implement thescheme in real time.
Hook into Clinical Informatics!.
B. Narasimhan (SU) Subject Randomization System userR! 2009 4 / 24
![Page 6: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/6.jpg)
Other Methods
Urn designs (Wei and Lachin, Controlled Clinical Trials, 1988);generalizations of Efron’s design.
Make treatment groups balanced with respect to prognostic or riskfactors (co-variates). By far the most common.Divide risk factor into strata and randomize within each stratum.Example: Sex (M or F) and Risk (H or L) yielding 2× 2 = 4 strata.
Minimization: A method to balance treatment assignment simultaneouslyover many strata. Multiple risk factors need to be incorporated into ascore for degree of imbalance (need to keep a running total of allocationby strata). Described by Taves (1974) and Pocock and Simon (1975).
B. Narasimhan (SU) Subject Randomization System userR! 2009 5 / 24
![Page 7: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/7.jpg)
Minimization Example
Three stratification factors: Sex (2 levels), age (3 levels), and diseasestage (3 levels)Suppose there are 50 patients enrolled and the 51st patient is male, age63, and stage III.
Trt A Trt B
Sex Male 16 14Female 10 10
Age < 41 13 1241− 60 9 6≥ 60 4 6
Stage I 6 4II 13 16III 7 4
Total 26 24
B. Narasimhan (SU) Subject Randomization System userR! 2009 6 / 24
![Page 8: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/8.jpg)
Minimization Example (contd.)
Look only at the marginal distribution. The person we want to assign to atreatment is male, age 63, and stage III.
Trt A Trt B Sign of diff.
Sex Male 16 14 +
Age ≥ 60 4 6 -
Stage III 7 4 +
Total 26 24 2+ and 1-
Possible approaches:
Count sign of diff. A is “ahead” in two categories out of three, soassign to B.
Add the total overall categories (27 As vs 24 Bs). Since A is ahead,assign B.
Or flip a biased coin in favor of redressing imbalance.
B. Narasimhan (SU) Subject Randomization System userR! 2009 7 / 24
![Page 9: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/9.jpg)
Package SRS
Provides two S4 classes: ClinicalExperiment andPocockSimonRandomizer implementing minimizationTypical use:
Construct the ClinicalExperiment
Contruct the PocockSimonRandomizer class with the above asargument
Call the randomization method with a subject ID and a list of factorsfor the subject.
B. Narasimhan (SU) Subject Randomization System userR! 2009 8 / 24
![Page 10: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/10.jpg)
SRS Usage
1 l i b r a r y (SRS)2 e x p t ← C l i n i c a l E x p e r i m e n t ( number . o f . f a c t o r s = 3 ,3 f ac to r . names = c ("Sex" , "Age" , "Stage" ) ,4 number . o f . f ac to r . l e v e l s = c ( 2 , 3 , 3 ) ,5 f ac to r . l e v e l . names =6 l i s t ( c ("Female" , "Male" ) ,7 c ("<41" , "41-60" , ">=60" ) ,8 c ("I" , "II" , "III" ) ) ,9 number . o f . t r e a t m e n t s = 2 ,
10 t r e a t m e n t . names ← c ("A" , "B" ) )11 r a n d o m i z e r ← new("PocockSimonRandomizer" ,12 e x p t=expt ,13 s e e d=as . i n teger ( 1 2 3 4 5 ) )
B. Narasimhan (SU) Subject Randomization System userR! 2009 9 / 24
![Page 11: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/11.jpg)
SRS Usage (contd.)
1 r a n d o m i z e r ←2 randomize ( randomizer ,3 s u b j e c t . i d="S051" ,4 f ac to r . v a l u e s=c ("Male" , ">=60" , "III" ) )5 > l a s t R a n d o m i z a t i o n ( r a n d o m i z e r )6 Sex Age Stage Treatment7 S051 Male >=60 I I I A
So this package can be used for treatment assignment. (In multi-centertrials, site is often used as one of the factors.)
B. Narasimhan (SU) Subject Randomization System userR! 2009 10 / 24
![Page 12: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/12.jpg)
Options
More than two arms can be specified
The ratio of treatement counts can be specified
Control over functions used for computing imbalance for eachtreatment
Control over function used for computing overall imbalance
The allocation probability can be customized
B. Narasimhan (SU) Subject Randomization System userR! 2009 11 / 24
![Page 13: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/13.jpg)
Web Interface
Slap on a web front-end utilizing Apache Tomcat with SimonUrbanek’s Rserve.
Database for persistence of R state and storing some experimentcharacteristics.
Transaction is to load state from database, randomize subject, savestate back in database. (Concurrency).
B. Narasimhan (SU) Subject Randomization System userR! 2009 12 / 24
![Page 14: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/14.jpg)
Web App
B. Narasimhan (SU) Subject Randomization System userR! 2009 13 / 24
![Page 15: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/15.jpg)
Experiment Setup
B. Narasimhan (SU) Subject Randomization System userR! 2009 14 / 24
![Page 16: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/16.jpg)
Enter Subject Details
B. Narasimhan (SU) Subject Randomization System userR! 2009 15 / 24
![Page 17: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/17.jpg)
Randomization
B. Narasimhan (SU) Subject Randomization System userR! 2009 16 / 24
![Page 18: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/18.jpg)
Reality on the Ground
Who is going to do the randomization?
Train trial coordinator in some good practices, let him/her handleeverything.
Hope everything works, despite the fact that several other systems arein use in the conduct of a trial and you have just added another.
So the situation is still unsatisfactory!
B. Narasimhan (SU) Subject Randomization System userR! 2009 17 / 24
![Page 19: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/19.jpg)
Meanwhile. . .
Modern adaptive designs that move smoothly from one phase to the next(Lai & Bartroff, for example) or response-adaptive designs need even moredetail on the trajectory of the trial so far, etc. in implementation.
Into such a milieu as exists now, how do we accomplish the translation? Inother words, not bench to bedside, but R code to clinical informatics?
B. Narasimhan (SU) Subject Randomization System userR! 2009 18 / 24
![Page 20: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/20.jpg)
Meanwhile. . .
Modern adaptive designs that move smoothly from one phase to the next(Lai & Bartroff, for example) or response-adaptive designs need even moredetail on the trajectory of the trial so far, etc. in implementation.
Into such a milieu as exists now, how do we accomplish the translation? Inother words, not bench to bedside, but R code to clinical informatics?
B. Narasimhan (SU) Subject Randomization System userR! 2009 18 / 24
![Page 21: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/21.jpg)
Clinical Informatics
Large and Complex
Typical systems include those that manage, protocols, trialregistration, CRFs, issue banking, Lab, Medication data, Outcometracking
Statistical tools not completely integrated (SAS may be close, butstill does not allow you open programming)
At least in Cancer, caBIG requirements apply. More and more centersare adopting caBIG technologies
The Clinical Trials Management Suite (CTMS) suite of tools isopen-source and is being recommended for use in Cancer Centers byNCI. Java/Web services based
B. Narasimhan (SU) Subject Randomization System userR! 2009 19 / 24
![Page 22: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/22.jpg)
Use of R in Clinical Trial Environments
B. Narasimhan (SU) Subject Randomization System userR! 2009 20 / 24
![Page 23: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/23.jpg)
CTMS
B. Narasimhan (SU) Subject Randomization System userR! 2009 21 / 24
![Page 24: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/24.jpg)
Module Acroynm FunctionCancer AdverseEvents ReportingSystem
caAERS Webapp for documenting, managing, re-porting, and analyzing AEs & SAEs
Cancer Center Par-ticipant Registry
C3PR Webapp for end-to-end registration of pa-tients (consent, eligibility, stratification,randomization, screening) with multi-sitecapabilities
Patient Study Cal-endar
PSC Tool for managing study calendar tem-plates, tracking patient activities duringa study
LabViewer Webapp for lab activities with messaging
caXchange Central hub for exchanging info in a gridsystem
B. Narasimhan (SU) Subject Randomization System userR! 2009 22 / 24
![Page 25: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/25.jpg)
Architecture
B. Narasimhan (SU) Subject Randomization System userR! 2009 23 / 24
![Page 26: Subject Randomization System - R: The R Project for ...Wood... · (In multi-center trials, site is ... Transaction is to load state from database, ... Subject Randomization System](https://reader030.fdocuments.us/reader030/viewer/2022021420/5acfca487f8b9ae2138cef6b/html5/thumbnails/26.jpg)
Future work
Work is proceeding on revising the SRS package with Rob Gentleman
Make the classes safe from tampering. (better naming convention,controlled access to slots, better pass by reference semantics etc.)
Integrate randomization into C3PR
A further distance away, once the R connection is established and working,integrate some new Phase I/II/III adaptive designs into CTMS
B. Narasimhan (SU) Subject Randomization System userR! 2009 24 / 24