Causality and clinical medicine: Using fuzzy measures for patient prediction and experimental design

Background: Scientific medicine regards causality in terms of conditions of chance, and expressed in probabilities. The large double blind controlled randomized trial and Bayes' theorem are the foundation of Evidence Based Medicine. Evidence -Based Medicine has the purpose of bringing science to the bedside. Comparison between experimental subjects or real patients and the average patient of a group study requires uniform conditions.Probability theory satisfies this requirement. Methods: The fundamental concept of fuzzy subset hood and measure space of fuzzy theory allow for the comparison of subjects or patients without the requirement of uniform conditions. The fuzzy measure of breaking of symmetry of conditions, K, allows for measures of fuzzy similarity, comparison, prediction to be made between two fuzzy sets as points while accounting for different conditions. Results: Using the fuzzy measure of prediction , F Pred (A,B) , it is possible to precisely compare a clinical patient to the average patient of any large group study, and in addition, with fuzzy entropy it is possible to carry out experiments where test and control groups are compared. Conclusion: The scientific requirement of uniform conditions for each repetition of an experiment is no longer a necessity for the comparison of patients or groups of patients. This is because fuzzy measures of symmetry breaking and similarity can account for any difference between patients due to different conditions. Fuzzy entropy can then measure the difference between two groups of patients in the experimental setting.