Framework for the Development of Data-Driven Mamdani-Type Fuzzy Clinical Decision Support Systems

摘要: Clinical decision support systems (CDSS) have been designed, implemented, and validated to help clinicians practitioners for decision-making about diagnosing some diseases. Within the CDSSs, we can find Fuzzy inference systems. For reasons above, objective of this study was design, implement, validate a methodology developing data-driven Mamdani-type fuzzy clinical using clusters pivot tables. validating proposed methodology, applied our algorithms on five public datasets including Wisconsin, Coimbra breast cancer, wart treatment (Immunotherapy cryotherapy), caesarian section, compared them with other related works (Literature). The results show that Kappa Statistics accuracies were close 1.0% 100%, respectively each output variable, which shows better accuracy than literature results. framework could be considered as deep learning technique because it is composed various processing layers learn representations data multiple levels abstraction.