The fuzzy signature structure has proven to be a dependable classifier by determining the compatibility and diversity of features of any complex structured data. One highly demanding arena for fuzzy structured applications is a medical diagnosis, such as COVID or SARS, where the aspects are difficult to categorize. A multitude of aggregation combinations can be adopted to obtain the highest accuracy of fuzzy signatures, which is what has been implemented in this paper. The number of classes was five, including patients with SARS, Normal, High blood pressure, Pneumonia, and COVID, where the comparison and significant differences between classes were analyzed. For several aggregation results, even the accuracy 100% was obtained, whereas, for a few combinations, the model did not work well, so it was necessary to select a suitable combination of aggregation to obtain a better outcome. Along with the implementation of the fuzzy signature model with multiple aggregations, the K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) have also been executed for classification upon the identical fuzzy signatures, and validation of the proposed Fuzzy signature model has been established in terms of resultant accuracies. Approximately 98% precision has been observed for both the KNN test and the training score as the maximum, while the minimum score was 22% using combinations of aggregation. SVM also showed a maximum accuracy of 87%. So, statistical and computational validity checks proved the feasibility of the proposed fuzzy model. Implementation is publicly available at https://github.com/ZakirANU/Fuzzy-for-Medical-Diagnosis .