Statistical analysis

Each clinical trial should be planned in accordance with recognized standards and legal regulations. This plan should include the purpose of the trial, endpoints, data capture methodology, inclusion and exclusion criteria, sample size with scientific justification, data processing method, statistical methods and assumptions.

Appropriate statistical analysis is the key element of a properly designed clinical trial. If a performance evaluation provides data that may disclose differences between the effects of two or more factors, statistical analyses are used to establish whether such differences are real or accidental. Additionally, one of the key aspects of statistical analysis is estimating the sample size.

Pure Clinical provides support for manufacturers throughout the entire in vitro diagnostics medical device performance evaluation process. Based on an appropriate statistical analysis, we are able to plan a reliable trial and summarize its results.

Q&A:

What is blinding?

Blinding in clinical trials is used in order to remove all bias and assumptions that may appear intentionally or unintentionally, if subjects or investigating team are aware of the expected result. A blinded trial is the opposite of an open label trial, in which all the parties are aware of the trial aspects.

What is diagnostic sensitivity?

Diagnostic sensitivity is defined as the percentage of true positives among all positive results. It means the ability of an in vitro diagnostic medical device to provide a positive result in a patient. This parameter is defined as the ratio of true positives and the total of true positives and false negatives.

What is diagnostic specificity?

Diagnostic specificity is the percentage of true negatives in all negative results. This parameter is defined as the ratio of true negatives and the total of true negatives and false negatives.

What is confusion matrix?

This is the so-called error table/matrix with two rows and two columns, which provides the number of true positives, false negatives, false positives and true negatives. The matrix allows an accurate analysis and visualization of quality test results.