RE: [R] 21 CFR Part 11 Compliance and R

From: Berton Gunter <>
Date: Tue 24 May 2005 - 06:38:25 EST

To further add to and perhaps clarify Frank's remark: 21 CFR Part 11 defines certain requirements for electronics records. A general requirement relevant for statistical software used in submissions is, I presume (quoted):

  " Persons who use closed systems to create, modify, maintain, or transmit electronic records shall employ procedures and controls designed to ensure the authenticity, integrity, and, when appropriate, the confidentiality of electronic records, and to ensure that the signer cannot readily repudiate the signed record as not genuine. Such procedures and controls shall include the following:

    (a) Validation of systems to ensure accuracy, reliability, consistent intended performance, and the ability to discern invalid or altered records. "

Note that there is no requirement for ANY specific software -- only that a process for software validation has been followed. Presumably, ANY reasonable validation process can be used and, as R already has extensive built-in validation suites, these certainly should go a long way toward fulfilling the bulk of this validation requirement.

The widespread use of SAS within the pharmaceutical industry is simply a historical legacy (many would say an archaic one, but we won't go there). Because of a huge existing infrastructure and code base, many companies don't/can't even consider changing it. This is a common paradigm for technological change: RCA was working mightily on improving vaccuum tubes for their TV sets even as Sony was using transistors to blow them away. My understanding is that it will take decades at least for fiber optics to replace the gazillions of miles of copper in the phone network even though that copper is a major obstacle to wider bandwidth and new services.

Older technologies are frequently difficult to displace merely because they are there. This is certainly heightened in a regulatory environment where anything that slows approval of a submission -- for example, use of software that FDA reviewers may not be as familiar with -- is avoided. But that neither mandates nor argues for avoidance. If R produces better submissions more efficiently, then why not use it?

"The business of the statistician is to catalyze the scientific learning process." - George E. P. Box    

> -----Original Message-----
> From:
> [] On Behalf Of Frank
> E Harrell Jr
> Sent: Monday, May 23, 2005 12:37 PM
> To: Richard Haney
> Cc:
> Subject: Re: [R] 21 CFR Part 11 Compliance and R
> Richard Haney wrote:
> > I have used S-PLUS, R, MATLAB and SAS for many years, and I
> am actually
> > quite happy to use any of these four languages. The
> reason may in part
> > involve my using the various languages for the purposes to
> which they seem
> > most suited. Hence there are many things for which I would
> not use SAS or
> > MATLAB, but for which I would greatly prefer to use R instead.
> >
> > On the other hand ( to take one of a couple of examples),
> in the past I
> > have not even been permitted to use "R" whatsoever in
> clinical trials
> > applications, which also typically involve a need for CFR Part 11
> > compliance. In this context, though, may I ask if there
> are people who
> > have recently been able to use R for clinical trials work
> that is done
> > within an FDA-approved 21 CFR Part 11-compliant framework?
> Rich,
> Whoever told you that is not well-informed. CFR Part 11 has
> to do with
> critical software that runs medical devices and about certain primary
> data management software. It does not apply to statistical analysis
> software. We use R all the time in industry-sponsored and
> NIH sponsored
> clinical trials. You do not need to seek FDA's approval.
> FDA accepts
> all comers and does not dictate software policy for analysis.
> They even
> accept Excel and Minitab for NDAs. There are many messages
> related to
> this in the r-help archive; please look at them.
> Frank
> >
> > Thanks very much.
> >
> > Rich Haney
> >
> > Duke Comprehensive Cancer Center
> --
> Frank E Harrell Jr Professor and Chair School of Medicine
> Department of Biostatistics
> Vanderbilt University
> ______________________________________________
> mailing list
> PLEASE do read the posting guide!
> mailing list PLEASE do read the posting guide! Received on Tue May 24 06:43:04 2005

This archive was generated by hypermail 2.1.8 : Fri 03 Mar 2006 - 03:32:01 EST