Amarin Corp Plc (AMRN)

[Biobillionair]

Akanz

http://www.ncbi.nlm.nih.gov/pubmed/9351164


Stat Med. 1997 Oct 30;16(20):2267-82.

Sizing clinical trials with variable endpoint event rates.

Moyé LA1.


Author information

Abstract

Although many researchers in cardiovascular clinical trials have disciplined themselves to execute sample size calculations in the design of their studies, these computations become difficult in the presence of control group endpoint event rate uncertainty. Recent experience in cardiovascular clinical trials suggests that, although one may know the control group event rate during the design phase of the trial, it can decrease during the trial's execution. Its resultant overestimation can lead to a power reduction with serious consequences for the trial's interpretation. Although the investigators may acknowledge the likelihood that the control group event rate will decrease during the time course of the trial, there is no formal means to adjust the design phase estimate. In this paper, I first formulate the sample size as a function of the control group event rate theta and then I place a proper probability distribution on theta, allowing for the uncertainty in this parameter's value during the course of the study. From this assumption, the sample size itself becomes a random variable, whose expectation and variance are computed. I explore the implications for sample size for various reasonable proper probability distributions on the control group event rate.
==========================================
Potential REDUCEIT MODEL


E 5.9
V 5.85
E 5.80
N 5.75
T 5.70
5.65
R 5.60
A 5.55
T 5.50
E 4.45
4.40
4.35
4.30
2011 2013 2015
Time

Both arms are equally enrolled with age/level of disease...if over time your event rate tracks as enrollment increases something other than age/level of disease is effecting the decreased event rate. When you drop $100 million into study, you have to look at the possible reasons why your event rate is decreasing over time...one possible reason is you have an effective drug. An active placebo would increase event rate over time, an ineffective drug would keep event rate the same, a dangerous drug would increase event rate, a dangerous drug and placebo would greatly increase event rate. If enrolment is held constant, number and level of disease equally enrolled into both arms then you can make these asumptions. So a drop in event rates to 5 from 5.9 equates to about a 32% reduction in events.

Amarin gets blinded quarterly events, they know the number of enrolled and the times when enrolled...they might not see the results but the xrays show no broken bones...

Also consider...AIM-HIGH
"The DSMB also noted a small and unexplained increase in ischemic stroke rates in the high dose, extended-release niacin group. This contributed to the NHLBI acting director's decision to stop the trial before its planned conclusion. During the 32-month follow-up period, there were 28 strokes (1.6 percent) reported during the trial among participants taking high dose, extended-release niacin versus 12 strokes (0.7 percent) reported in the control group. Nine of the 28 strokes in the niacin group occurred in participants who had discontinued the drug at least two months and up to four years before their stroke. Previous studies do not suggest that stroke is a potential complication of niacin, and it remains unclear whether this trend in AIM-HIGH arose by chance, was related to niacin administration or some other issue." The increasing event rate tipped the scales and shut the study down.
BB