Fuzzy quantum machine learning (FQML) logic for optimized disease prediction

Quantum computing, based on quantum mechanics, has evolved due to the cross-pollination of concepts, methods, and strategies. The fusion of quantum computing with machine learning (ML) algorithms has shown satisfactory results in the case of low dimensionality spaces. However, in high dimensionality spaces, the computational complexity increases, thus leading to average accuracy and computation time. To combat this issue in this research work, a mathematical technique known as fuzzy logic (FL) has been integrated with quantum ML (QML) and applied to a medicine dataset of chronic disease. The fusion of two variables into one variable reduces the number of features hence transforming the high dimensional space into low dimensional space. ML implementation on the considered dataset has shown poor accuracy and took a large computation time. The integration of FL with ML (FML) has overcome this issue and optimized computation time and accuracy. Since QML shows poor accuracy and takes large computations when data sizes get larger as seen in different studies, therefore fuzzy concepts are integrated with QML, particularly with support vector machine (SVM) and K-nearest neighbor (KNN). Thus leading to the development of a hybrid model called FQML. The FQML has optimized the computation time and accuracy of the model as compared to QML. Moreover, all necessary features can be considered for the prediction of output which is very crucial, especially in medical diagnosis. Results of statistical analysis have also been performed between QML and FQML which has concluded that models are significantly different. Thus, a combination of FQML can overcome the QML computational complexity in high dimensional spaces by utilizing fuzzy logic concepts and can consider all necessary features required for better outcome prediction without compromising on computational complexity.