Q: Need to calculate a sample size!
I'm a PhD student dentist. I want to make a randomized clinical trial research to compare 2 different treatment modalities groups
 and every group is subdivided into 2 subgroups.The first group is treatment by ( stem cells + bone graft ) and subdivided into 
 two subgroups ( with laser ) or ( without laser  )
 The second group : ( PRF + bone graft ) and subdivided into 2 subgroups ( with laser ) and ( without laser)i.e.
 The groups are: 
 1a : stem cells + bone graft + laser
 1b : stem cells + bone graft
 2a : PRF + bone graft + laser
 2b : PRF + bone graft
How to calculate the sample size?
Knowing that I found some previous articles with results regarding either ( Stem cells + bone graft ) 
or ( PRF + bone graft )  but didn't find any article about adding laser to the treatment
i.e I have mean values if improvement, st. Dev. , confidence level, confidence interval and sample 
size for previous studies like my groups 1b and 2b.
What data do I need? 
And what is the formula needed to calculate the sample size for the clinical trial or even the pilot study?


A: 
In the sample size for stem cells + bone graft.The sample size is on basis of the effect that they want to prove.
I think that it is useful EpiInfo or Epidat to calculate the sample size % of cure with one treatment vs % de cure 
with the second treatment 
If there are not evidence about laser in treatment why should be included in the treatment?

Comment: Regarding the laser, it has been proved that it is alone enhancing the healing, 
so I want to assess its added effect over the treatment modalities

Regarding the data, two different previous studies,
 - One compared the ( PRF + bone graft ) group vs (bone graft alone)
    N = 20 in each group
Measured parameters improved significantly :
PD  after 6 months  3.67 +_ 1.48 
RAL. After 6 months. 2.97 +_ 1.42 

- the other study  ( stem cells + bone graft) vs ( bone graft alone)
N = 20 in each group
Measured parameters improved significantly:
PD after 3 Months 3.8 +_ 1.03 
RAL after 3 months 4.42 +_ 1.19

A: With these data the sample size should be comparing two independent means. 
Epidat (Xunta de Galicia, PAHO and Universidad CES) can calculate it.
Expecting 3.67 + - 1.48 and 2.97 + - 1.42 (groups 1 and 2)
the sample size with a difference of means of 0.7 is 64 in each group with 95% of confidence and 80% of Power (Epidat 4.1)