Per-protocol analysis

In general, it is advantageous to demonstrate a lack of sensitivity of the principle trials results to alternative choices of the set of subjects analysed. In confirmatory trials it is usually appropriate to plan to conduct both an analysis of the full analysis set and a per-protocol analysis, so that any differences between them can be the subject of explicit discussion and interpretation. ... 

One very simplistic way of handling missing data is to remove those patients with missing data from the analysis in a complete cases analysis or completers analysis. By definition this will be a per-protocol analysis which will omit all patients who do not provide a measure on the primary endpoint and will of course be subject to bias. Such an analysis may well be acceptable in an exploratory setting where we may be looking to get some idea of the treatment effect if every subject were to follow the protocol perfectly, but it would not be acceptable in a confirmatory setting as a primary analysis. 

It must be noted, however, that even if the sample size calculation gives enough power for the per-protocol analysis the potential for bias in that analysis still remains. 

In a non-inferiority trial, the full analysis set and the per-protocol analysis set have equal importance and their use should lead to similar conclusions for a robust interpretation. ... 

Safety analysis patient set was defined as all patients who received the Biod/VTs/o Batimastat OC stent, per-protocol analysis patient set was defined as all patients in the Safety analysis set who did not deviate from the protocol. Categorical variables were summarized using counts and percentages. Continuous variables were summarized using mean, standard deviation, minimum and maximum, and median for variable not showing a normal distribution. For comparison of subgroups, the unpaired two-tailed student s t-test was used. Results were considered statistically significant at P< 0.05. 

In contrast to the conservative ITT analysis, analysis of the per-protocol population may maximize the opportunity to demonstrate efficacy the per-protocol population is the population in which the treatment is likely to perform best. Adherence to the protocol may be related to the treatment and outcome (Kay, 2005). This is why the per-protocol analysis is considered secondary to the more conservative ITT analysis. 

If the picture painted by both the ITT analysis and the per-protocol analysis is similar, overall confidence in the trial results is increased. However, if they are... 

The goal of HP drug therapy is eradication of the organism. Treatment shonld be effective, well-tolerated, easy to comply with, and cost-effective. HP regimens should have eradication (cure) rates of at least 80% based on intention-to-treat analysis, or at least 90% based on per protocol analysis, and should minimize the potential for antimicrobial resistance. The use of a single antibiotic, bismuth salt, or antiulcer drug does not achieve this goal. However,... 

Table 3.5 PTP Pivotal study Part 1, Pharmacokinetics per-protocol analysis (n = 30) [25]...

For the per-protocol analysis population of 11 patients, the mean plasma half-life was 10.48 1.6 h, and adjusted recovery 2.0 0.5 lU dL plasma per lU kg body weight infused. These data are consistent with those seen in adolescents and older patients, when the greater weight-adjusted plasma volumes that affect the volume of distribution and adjusted recovery in young children, as well as potentially alter halflife, are taken into account [32]. 

These sorts of occurrences are common and have to be faced in analysis. In particular, a decision has to be made as to which patients are to be included in the analysis of the trial results. Two phrases commonly used in this connection are per-protocol and intention to treat (or sometimes, intent to treat ). A per-protocol analysis excludes... 

Although the issues of missing data and intention to treat are closely related, they are not identical. Intention to treat analysis is possible provided outcome and randomization data are not missing and (in its strict sense) impossible if they are. If data are not missing, then even if patients are noncompliant it is possible to analyse them as randomized provided only that their original treatment allocation is known. A per-protocol analysis requires knowledge of compliance. Also, depending on what one means by per protocol, it may or may not require complete outcome data. For example, one could simply say for a per-protocol analysis that one is only interested in patients who not only took the medicine as instructed but also recorded their outcomes. 

Nevertheless, where we are interested in the pharmacological consequence of treatments it seems intuitively reasonable that some sort of adjustment for compliance is relevant. In this connection, an interesting distinction between explanatory (or scientific) trials and pragmatic trials was introduced by Schwartz, and colleagues (Schwartz et al., 1980 Schwartz and Lellouch, 1967). For the former, a per-protocol analysis would be more relevant, whereas the latter might require intention to treat. 

The two extreme positions amount to this. A per-protocol analysis assumes that information from noncompliers is irrelevant to judging the effect of a treatment. An intention to treat analysis assumes that it is only safe if all information regarding outcomes is analysed, treating noncompliers as if they were compliers. I have drawn attention to two scientific views of causality in drug development the voluntary (which I associated more with statisticians) and the mechanistic (associated more with pharmacokineticists) (Senn, 1997). As regards the first I wrote ... 

IPP, Isoleucine-proline-proline VPP, valine-proline-proline SBP, systolic blood pressure DBP, diastolic blood pressure R, p-c, d-bld, randomized, placebo-controlled, double-blinded. Results reported as changes in SBP and DBP after each month of treatment for all subjects (intention-to-treat analysis), and as mean changes over the total intervention period among subjects who had BP measurements for each month (per protocol analysis). 

PMD lotion in addition to 25 mg/m deltamethrin-impregnated bed net 0.05 (0.01-0.20) Repellent provided 97% protection from Anopheles darlingi for 4 hours Anopheles darlingi 48% of biting before 9 Ptui >90% (Per protocol analysis) ... 

---