As I see it, there is my PD (which may be different to yours) and my response to it (which almost certainly is different to yours). Given this, why focus on increasing n, the sample size? If X works for me, the fact that it doesn't work for you doesn't stop it working for me.

As I see it, what we really need is evidence that the therapy (including any placebo effect) is really working for Nan (taking into account the risks). If it is working, try to continue with the therapy, monitoring your progress, good and bad, as you go. If it stops working for you, then (possibly over a period of time) stop using it.

John