This analysis was confirmed in a population of MPS II treated with ERT and the results were studied in a group of patients with MPS I. New studies need to determine whether outcomes can be generalized for other diseases and patient profiles. An important point to consider is the limit of vain chosen in our analysis (zero hypothesis). The objective of Bradley et al.  and his meta-analyses was to identify the benefits and damage of ERT, the study being defined as a pilot. There were no significant clinical effect criteria. Therefore, the purpose of the meta-analysis was similar to that of The Phase II designs, which were designed to examine the benefits and damage of a given treatment. According to previous publications on the evaluation of treatment activity in Phase II studies , a percentage of patients with a reaction of 5% or less was considered a null hypothesis. As a result, we found that the best match with the results of the meta-analysis of clinical trials was observed with the pre-programmed limit of 5%, which corresponds to previous recommendations in designs with the same objective .
Case report meta-analyses for other purposes, such as identifying.B effects greater than an active comparator, may require that the zero hypothesis be based on historical control estimates. Our proposal provided a meta-analysis of cases of patients with MPS II treated with ERT, comparing the degree of evidence assigned to each result with what was attributed in a previous meta-analysis clinical trial published by an independent research group. In a population with MPS-II, we tried to confirm the impressive consistency between case reports and meta-analyses of clinical trials in patients with MPS-I . Suchsyntax used in different databases to collect bibliographic data. Table S2. Case reports of men with MPS-II published prior to the literature search for meta-analyses of clinical trials (January 2008 to December 2015). Table S3. Case reports of men with MPS-II that were then published in the literature meta-analysis research of clinical trials (January 2016 to April 2018). Table S4. Agreement between the classification of the results on the basis of the analysis of the case report and the SOE classification on the basis of the meta-analysis of the clinical trial. The confirmation method is weak.
Table S5. Sensitivity analysis to different limits of inefficiency. Figure S1. Consistency between analysis of evidence from the case meta-analysis and SOE from the Meta-Analysis clinical trial. The confirmation method is weak. Other methods of evaluating associations such as t-test/analysis of variance (ANOVA) are also not appropriate to analyze contract studies for the same reasons. Duran R et al., uses ANOVA to compare 3 methods of measuring the temperature of low birth weight infants . He made a good agreement because there was no statistically significant difference between average front and axillary temperatures. It should be noted that there is an appropriate way to use the regression that Bland himself used before the development of this technique, but it is quite complicated. Alanen E. proposed another technique based on the modeling of structural equations (SEM) .
It is criticized that the Bland Altman method considers reliability to be contrary to the comparison of methods.