Intention-To-Treat Vs Per-Protocol Pdf

Graphical comparison of itt and PP point estimates. ARR = absolute risk reduction; ITT = Intention to treat; PP = per protocol. The size of the points in the graph is proportional to the sample size of the ITT population. A diagonal line is drawn at y = x, so that the itT analysis is more conservative for the points above the line and the PP analysis is more conservative for the points below the line While the itT analysis aims to maintain the original randomization and avoid potential biases due to the exclusion of patients, the objective of a PP (pro protocol) analysis is to: identify a treatment effect that would occur under optimal conditions; that is, to answer the question: What is the effect when patients are fully compliant? Therefore, some patients (from the full set of analyses) should be excluded from the population (PP population) used for PP analysis. In non-inferiority studies, there is concern that intention-to-treat (ITT) analysis involving participants who have not received the planned interventions may result in the treatment and control arms resembling each other and leading to false claims of non-inferiority. In contrast, PP (pro-protocol) analysis is considered less likely to make this error, and therefore preferable in non-inferiority studies. In a systematic review of studies of non-inferiority of antibiotics, we compared ITT and PP analyses to determine which analysis was most conservative. Porta N, Bonet C, Cobo E. Discrepancy between reported treatment intent and pro-protocol analyses. J. Clin Epidemiol. 2007;60(7):663–9

When conducting clinical trials, it is not uncommon for protocol violations or the inability to evaluate results to occur. This article in our series on common pitfalls of statistical analysis explains the complexity of analyzing the results of such studies and highlights the importance of intention-to-treat analysis. Why ask these questions when talking about intention to treat (ITT) versus Per-Protocol (PP)? Well, let`s start with some general definitions and explanations: In contrast, pp analysis (pro protocol) refers to the inclusion in the analysis only of patients who have strictly adhered to the protocol. PP analysis provides an estimate of the actual effectiveness of an intervention, that is, among those who completed treatment as planned. However, as discussed above, the results do not represent the actual situation and it is likely that they show an exaggerated treatment effect. The intention-to-treat principle defines that each patient randomized to the clinical trial must enter the primary analysis. As a result, patients who stop prematurely, do not comply with the study treatment or even use the study`s mistreatment are included in the primary analysis within the respective treatment group into which they were randomised during randomisation. In randomised controlled trials (RCTs), the most frequently analysed populations are intention-to-treat (ITT) and protocol (PP) populations [1, 2]. The ITT population includes all patients who are analyzed in their randomized treatment arms, whether they have used the treatment or completed the study [1].

In some studies, there are predefined changes in the ITT population, such as . B includes only patients who have received at least one dose of treatment [3]. This is sometimes referred to as the modified TTI [3]. In the following, we use the term ITT population to include this modified ITT population. The PP population generally includes only patients who have completed the study according to protocol [1, 2]. European Medicines Agency. Guidelines for the evaluation of drugs indicated for the treatment of bacterial infections. 2011. Retrieved 8 June 2020. The median estimated ART was 0% (IQR − 5.9 to 3.2%) for the excluded population and −0.2% (IQR − 2.6 to 2.2%) for the PP population (p = 0.4335) (Supplementary File 1: Appendix Figure 3). The median success rate for the treatment and control groups was 44% (IQR 23 to 60%) in the excluded population and 89% (IQR 82 to 93%) in the PP population (P < 0.0001) (Supplementary File 1: Appendix Figure 4). The success rate of the treatment group in the excluded and PYP population is shown in Supplementary File 1: Appendix Figure 5, while the success rate for the Control Group in the Excluded and PYP Population is reported in Supplementary File 1: Appendix Figure 6. Centre for Biologics Evaluation and Research (CBER), Centre for Drug Evaluation and Research (CDER). Unperiority Clinical Trials to Determine Efficacy: Industry Advice. 2016. Retrieved 8 June 2020. All tests were bilateral with a P < a significance level of 0.05.

All analyses were performed with R version 3.6.3 (R Foundation for Statistical Computing, Vienna, Austria). The funnel diagrams and the Egger regression test for funnel diagram asymmetry were performed using the metafor package [28]. The IC for ARR was calculated using the DescTools package [29]. Of the 154 studies, 152 (98.7%) defined non-inferiority as a function of the lower limit of the CI in terms of the margin of non-inferiority. Study characteristics related to the description and analysis of ITT and PP populations are described in Table 1. .