balakotu
★    

India,
2015-09-22 15:05
(3110 d 06:07 ago)

Posting: # 15441
Views: 5,594
 

 BA/BE Studies for Early Termination [Two-Stage / GS Designs]

Dear all,

We are planning to conduct one "Replicate 4-period" bio-equivalence study with 70 subjects.

After completion of clinical phase we will analyze only 40 subjects.

If 40 subject’s data is shown bio-equivalent then we will stop the analysis of remaining 30 subjects. If the data is predictable then we will analyze remaining 30 subjects.

Please clarify whether this approach/design is acceptable to regulatory are not.

Regards

Kotu


Edit: Category changed. [Helmut]
ElMaestro
★★★

Denmark,
2015-09-22 15:35
(3110 d 05:37 ago)

@ balakotu
Posting: # 15444
Views: 4,617
 

 BA/BE Studies for Early Termination

Hi balakotu,

❝ We are planning to conduct one "Replicate 4-period" bio-equivalence study with 70 subjects.

❝ After completion of clinical phase we will analyze only 40 subjects.

❝ If 40 subject’s data is shown bio-equivalent then we will stop the analysis of remaining 30 subjects. If the data is predictable then we will analyze remaining 30 subjects.


This sounds like a two-stage approach. If you allow yourself two chances of showing BE at the usual alpha of 5% then some regulators may protest due to overall type I error inflation. Check publications by Diane Potvin and coworkers for ways forward which retain control of the error.
In addition, I think you should use all available data: If you have data from 70 subjects, then I believe all 70 subjects should be analysed to avoid ethics issues.

"Replicate 4-period" in connection to two-stage designs is so far uncharted territory. I don't recommend trotting down that avenue.

Pass or fail!
ElMaestro
d_labes
★★★

Berlin, Germany,
2015-09-22 15:49
(3110 d 05:24 ago)

@ balakotu
Posting: # 15445
Views: 4,556
 

 Dose subjects but not using them

Dear Kotu,

sounds to me in contrast to our Capt'n like something similar to 'spare' subjects.

The EMA guidance states in this respect:
"The data from all treated subjects should be treated equally. It is not acceptable to have a protocol which specifies that ‘spare’ subjects will be included in the analysis only if needed as replacements for other subjects who have been excluded. It should be planned that all treated subjects should be included in the analysis, even if there are no drop-outs."

Moreover it is IMHO highly unethical to expose subjects to the API and taking blood samples from them for nothing (not to use their data).

Regards,

Detlew
Helmut
★★★
avatar
Homepage
Vienna, Austria,
2015-09-22 15:58
(3110 d 05:14 ago)

@ balakotu
Posting: # 15446
Views: 4,556
 

 IMHO, that’s a TSD…

Hi Kotu,

whatever you might call it, I agree with ElMaestro that this is essentially a Two-Stage Design (even if you aim at early stopping in the interim) – which would require adjusting α in order to maintain the Type I Error.
αadj suitable for replicate designs (both for reference-scaled and conventional ABE) depends on the assumed GMR, target power, design (and the scaling method if applicable). The numerical values are currently un­known. See this thread for background information.

BTW, agencies consider analyzing only part of the data (in order to cut costs) unethical.

You estimated the sample size with 70 subjects and showed BE with only 40. Such an outcome might be pure chance. Please assess BE for the complete data set of 70.



Edit after reading Detlew’s post above: I would emphasize part of the EMA’s last sentence “It should be planned that all treated subjects should be included in the analysis […]”.
Four members of the forum warned you last year that such a design is not acceptable. Have you forgotten that?

Dif-tor heh smusma 🖖🏼 Довге життя Україна! [image]
Helmut Schütz
[image]

The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes
UA Flag
Activity
 Admin contact
22,957 posts in 4,819 threads, 1,636 registered users;
88 visitors (0 registered, 88 guests [including 6 identified bots]).
Forum time: 20:13 CET (Europe/Vienna)

Nothing shows a lack of mathematical education more
than an overly precise calculation.    Carl Friedrich Gauß

The Bioequivalence and Bioavailability Forum is hosted by
BEBAC Ing. Helmut Schütz
HTML5