Bioequivalence and Bioavailability Forum • R code for the EMA’s ABEL

R code for the EMA’s ABEL [🇷 for BE/BA]

posted by Helmut – Vienna, Austria, 2017-06-10 03:44 (2782 d 06:34 ago) – Posting: # 17480
Views: 19,019

Hi Mahmoud,

❝ […] an R code to do data analysis of partial replicate design "2x3x3" BE study according to FDA and EMA guidelines.

Good news: The EMA’s ‘Method A’ and ‘Method B’ are fairly easy to implement in R. I have code covering the following designs: RTRT|TRTR, RTTR|TRRT, RTR|TRT, RTT|TRR, RRT|RTR|TRR. The code handles balanced/unbalanced sequences and complete/incomplete data (i.e., periods missing). Example output:

This code is copyright © by Helmut Schütz, Michael Tomashevskiy, Detlew Labes. This code is open source; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foun- dation; either version 3, or (at your option) any later version. See the GNU GPL for more details. Copies of the GPL-3 versions are available at: http://www.gnu.org/licenses/gpl-3.0.html ╔════════════════════════════════════════════════════════════════════════════╗ ║ Program offered for Use without any Guarantees and Absolutely No Warranty. ║ ║ No Liability is accepted for any Loss and Risk to Public Health Resulting ║ ║ from Use of this R-Code. ║ ╚════════════════════════════════════════════════════════════════════════════╝ Directory : E:/Public/Documents/BEBAC/Publications/AAPS J/RepVal/Data/ File [sheet] : DS.xls [01] System : BEBAC-PC User : HS Operating System : Windows 7 x64 build 7601, Service Pack 1 R version : 3.4.0 (2017-04-21) readxl version : 1.0.0 (2017) PowerTOST version : 1.4.5 (2017) EMA_methodAB vers. : 0.95 (2017-06-11) ────────────────────────────────────────────────────────────────────── Function : CV.calc(); exec. 2017-06-11 18:10:33 CEST Fixed effects : sequence + subject(sequence) + period Data : treatment = R Function : method.A(); exec. 2017-06-11 18:10:33 CEST Fixed effects : sequence + subject(sequence) + period + treatment Data : all ────────────────────────────────────────────────────────────────────── Data set I given by the EMA (Q&A document) available at http://www.ema.europa.eu/docs/en_GB/document_library/Scientific_guideline/2009/09/WC500002963.pdf Analysis performed on column ‘PK’ (data internally log-transformed) Sequences (design) : RTRT|TRTR (4-period full replicate) Subjects / sequence: 38|39 (unbalanced) Missings / sequence: 3|7 (incomplete) Missings / period : 0|1|7|2 (incomplete) Subjects (total) : 77 Sub’s with T and R : 77 (calculation of the CI) Sub’s with two Ts : 71 Sub’s with two Rs : 73 Degrees of freedom : 217 alpha : 0.05 (90% CI) Switching CV : 30.00% Scaling cap : 50.00% Regulatory constant: 0.760 GMR restriction : 80.00% ... 125.00% CVwT : 35.16% CVwR : 46.96% (reference-scaling applicable) Expanded limits : 71.23% ... 140.40% Recalculation due to presence of 2 outliers (subj. 45|52) ───────────────────────────────────────────────────────── CVwR (outl. excl.) : 32.16% (reference-scaling applicable) Expanded limits : 78.79% ... 126.93% Assessment based on original CVwR 46.96% ──────────────────────────────────────── Confidence interval: 107.11% ... 124.89% (pass) Point estimate : 115.66% (pass) Overall conclusion : pass Assessment based on recalculated CVwR 32.16% ──────────────────────────────────────────── Confidence interval: pass Point estimate : pass Overall conclusion : pass This code is copyright © by Helmut Schütz, Michael Tomashevskiy, Detlew Labes. This code is open source; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foun- dation; either version 3, or (at your option) any later version. See the GNU GPL for more details. Copies of the GPL-3 versions are available at: http://www.gnu.org/licenses/gpl-3.0.html ╔════════════════════════════════════════════════════════════════════════════╗ ║ Program offered for Use without any Guarantees and Absolutely No Warranty. ║ ║ No Liability is accepted for any Loss and Risk to Public Health Resulting ║ ║ from Use of this R-Code. ║ ╚════════════════════════════════════════════════════════════════════════════╝ Directory : E:/Public/Documents/BEBAC/Publications/AAPS J/RepVal/Data/ File [sheet] : DS.xls [01] System : BEBAC-PC User : HS Operating System : Windows 7 x64 build 7601, Service Pack 1 R version : 3.4.0 (2017-04-21) readxl version : 1.0.0 (2017) PowerTOST version : 1.4.5 (2017) nlme version : 3.1.131 (2017) EMA_methodAB vers. : 0.95 (2017-06-11) ───────────────────────────────────────────────────────────────────────────────── Function : CV.calc(); exec. 2017-06-11 18:10:37 CEST Fixed effects : sequence + subject(sequence) + period Data : treatment = R Function : method.B(option=2): nlme/lme; exec. 2017-06-11 18:10:37 CEST Fixed effects : sequence + period + treatment Random effect : subject(sequence) Data : all ───────────────────────────────────────────────────────────────────────────────── Data set I given by the EMA (Q&A document) available at http://www.ema.europa.eu/docs/en_GB/document_library/Scientific_guideline/2009/09/WC500002963.pdf Analysis performed on column ‘PK’ (data internally log-transformed) Sequences (design) : RTRT|TRTR (4-period full replicate) Subjects / sequence: 38|39 (unbalanced) Missings / sequence: 3|7 (incomplete) Missings / period : 0|1|7|2 (incomplete) Subjects (total) : 77 Sub’s with T and R : 77 (calculation of the CI) Sub’s with two Ts : 71 Sub’s with two Rs : 73 Degrees of freedom : 217 alpha : 0.05 (90% CI) Switching CV : 30.00% Scaling cap : 50.00% Regulatory constant: 0.760 GMR restriction : 80.00% ... 125.00% CVwT : 35.16% CVwR : 46.96% (reference-scaling applicable) Expanded limits : 71.23% ... 140.40% Recalculation due to presence of 2 outliers (subj. 45|52) ───────────────────────────────────────────────────────── CVwR (outl. excl.) : 32.16% (reference-scaling applicable) Expanded limits : 78.79% ... 126.93% Assessment based on original CVwR 46.96% ──────────────────────────────────────── Confidence interval: 107.17% ... 124.97% (pass) Point estimate : 115.73% (pass) Overall conclusion : pass Assessment based on recalculated CVwR 32.16% ──────────────────────────────────────────── Confidence interval: pass Point estimate : pass Overall conclusion : pass

I will send you the code by PM.

Bad news: Evaluation of replicate designs which will give exactly the same results as SAS’ PROC MIXED according to the FDA’s progesterone guidance is not (and likely will never be) possible in R. Too different philosophies.

Edit: Updated the output according to v0.95 of the R-code.

—
Dif-tor heh smusma 🖖🏼 Довге життя Україна!
Helmut Schütz

The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes

Complete thread:

R code for analysis of data from partial replicate design "2x3x3" BE study mahmoud-teaima 2017-06-08 17:45 [🇷 for BE/BA]
- R code for the EMA’s ABELHelmut 2017-06-10 01:44
  - R code for the EMA’s ABEL mahmoud-teaima 2017-06-10 22:48
    - R code for the EMA’s ABEL Helmut 2017-06-11 01:24
      - R code for the EMA’s ABEL mahmoud-teaima 2017-06-11 03:01
  - R code for the EMA’s ABEL Yura 2017-09-04 21:22
    - R code for the EMA’s ABEL Helmut 2017-09-05 01:55
      - R code for the EMA’s ABEL Yura 2017-09-05 22:21
        
        R code for the EMA’s ABEL Helmut 2017-09-06 14:24
        
        R code for the EMA’s ABEL Yura 2017-09-08 08:54
  - R code for the EMA’s ABEL sschivu 2019-04-22 13:50
    - package replicateBE for R Helmut 2019-04-22 18:46
      - package replicateBE for R gvk 2019-05-03 09:15