Obesity, characterized by an excessive increase in body fat, is not only a significant disease but also a condition that serves as the basis for many other illnesses. Therefore, early intervention and necessary precautions for diagnosing and treating obesity are of paramount importance. Classical machine learning algorithms are actively utilized in medical fields to expedite prediction processes. However, the increasing volume of data renders even effective classification algorithms inadequate for experts to diagnose diseases. Quantum computing-based algorithms come into play at this point, offering a new perspective in machine learning by utilizing quantum physics, which is contrary to the rules of classical physics. Dimensionality reduction techniques required for the use of quantum-based algorithms play an essential role in both classical and quantum applications. In this study, Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA), classical dimensionality reduction methods, were applied to the obesity dataset and analyzed with Quantum Support Vector Machine (QSVM) and Support Vector Machine (SVM) algorithms. To conduct QSVM studies, the comparison of three different quantum feature maps providing the qubit transformation of classical bit data is also included in this study. As a result of the analysis, it was determined that the proposed method as LDA-QSVM achieved 100% success when used with Z and Pauli X feature maps. This success, which is rare in literature studies on obesity data, emphasizes the future potential of quantum-based algorithms in obesity diagnosis and treatment.
Obesity, characterized by an excessive increase in body fat, is not only a significant disease but also a condition that serves as the basis for many other illnesses. Therefore, early intervention and necessary precautions for diagnosing and treating obesity are of paramount importance. Classical machine learning algorithms are actively utilized in medical fields to expedite prediction processes. However, the increasing volume of data renders even effective classification algorithms inadequate for experts to diagnose diseases. Quantum computing-based algorithms come into play at this point, offering a new perspective in machine learning by utilizing quantum physics, which is contrary to the rules of classical physics. Dimensionality reduction techniques required for the use of quantum-based algorithms play an essential role in both classical and quantum applications. In this study, Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA), classical dimensionality reduction methods, were applied to the obesity dataset and analyzed with Quantum Support Vector Machine (QSVM) and Support Vector Machine (SVM) algorithms. To conduct QSVM studies, the comparison of three different quantum feature maps providing the qubit transformation of classical bit data is also included in this study. As a result of the analysis, it was determined that the proposed method as LDA-QSVM achieved 100% success when used with Z and Pauli X feature maps. This success, which is rare in literature studies on obesity data, emphasizes the future potential of quantum-based algorithms in obesity diagnosis and treatment.
A chronic metabolic disease, diabetes mellitus has become a serious global public health concern. Using the Indian Pima Diabetes Dataset, this study compares Classical Support Vector Machines (CSVM) with Quantum Support Vector Machines (QSVM) for diabetes prediction. To address the challenges associated with high-dimensional data and feature redundancy, before classification, a feature reduction method called Principal Component Analysis (PCA) is used. Experimental results demonstrate that PCA effectively reduces computational complexity while preserving essential information required for classification. Furthermore, the study investigates the potential advantages of quantum-enhanced learning in healthcare prediction tasks by comparing the predictive capabilities and computational characteristics of QSVM against its classical counterpart. The findings provide insights into the applicability of quantum machine learning techniques for medical diagnosis and highlight the opportunities and challenges associated with implementing quantum algorithms on real-world healthcare datasets.
The analysis of data and the development of Quantum Support Vector Machine (QSVM) models for disease classification have rapidly become crucial, commanding significant attention from the research community. Principal Component Analysis (PCA) is a powerful dimensionality reduction technique that effectively eliminates noise and optimizes processing in machine learning applications. When integrated with QSVM, PCA plays an essential role in reducing the number of qubits required and significantly enhancing model performance. In this study, we present a robust breast cancer diagnosis model that seamlessly incorporates PCA into QSVM, clearly demonstrating its effectiveness in improving classification performance on biomedical data compared to traditional methods. Our experimental results decisively show that PCA not only optimizes computational resources but also substantially increases model accuracy, affirming its transformative potential for quantum applications in large-scale data analysis. Our proposed model achieves an exceptional classification accuracy of 98%, unequivocally highlighting the impact of PCA in strengthening QSVM performance for biomedical applications.
Blood glucose is one of the key indicators influencing the body’s metabolic performance. Accurate prediction and proactive management of this parameter are of paramount clinical importance. In this context, the analysis and evaluation of quantum machine learning (QML) algorithms for processing medical data and enhancing the predictive accuracy of health-related models have emerged as cutting-edge research directions in recent studies. Leveraging the principles of quantum physics and computation, QML algorithms serve as a promising alternative to classical methods for predicting chronic diseases. By mapping classical data into a quantum feature space and exploiting intrinsic quantum properties such as superposition and entanglement, these algorithms significantly enhance the ability to detect complex and latent patterns within datasets. In this study, the dataset was first preprocessed using Principal Component Analysis (PCA) for dimensionality reduction and noise suppression. Subsequently, the predictive performance of two quantum machine learning models—the Quantum Support Vector Machine (QSVM) and the Variational Quantum Circuit (VQC)—was evaluated and compared with that of the classical Support Vector Machine (SVM) for blood glucose level prediction. The results indicate that the QSVM model achieves a prediction accuracy of 90%, outperforming the classical SVM, which attained an accuracy of 74.4%. Moreover, the hybrid classical–quantum VQC model demonstrated the highest predictive performance, achieving an accuracy of 94.2%, thereby establishing it as the most effective approach for blood glucose level forecasting in this experimental setting.
This paper evaluates the performance of two quantum machine learning algorithms: Quantum Support Vector Machine (QSVM) and Quantum Principal Component Analysis (Q-PCA). The scalability of QSVM is analyzed across increasing dataset sizes and feature dimensions, revealing faster-than-linear growth in kernel evaluation and SVM training times. However, this computational overhead is accompanied by a notable decline in classification accuracy, highlighting challenges in applying QSVM to larger or more complex datasets. In contrast, Q-PCA demonstrates near-linear scalability with dataset size and qubit count, leveraging the independence of quantum circuit execution and structured operations to maintain efficiency. A QNN-based implementation of Q-PCA further validates its ability to align data with principal components, maximize variance, and enable effective dimensionality reduction. These findings emphasize the potential of Q-PCA for efficient quantum-enhanced data analysis while underscoring the need for optimization in QSVM and further exploration of Q-PCA’s capabilities for real-world quantum computing applications.
Background The kidney is one of the most essential organs in our body, and any problems with it are perilous, hence, the early diagnosis of chronic kidney disease (CKD) is crucial. support vector machine (SVM), a popular machine learning (ML) technique, is an effective solution for building an early CKD diagnosis system. Nowadays ML techniques like SVM are often combined with upcoming quantum computing technology to improve over classical ML. Methods This research uses classical SVM (CSVM) and Quantum SVM (QSVM) to develop a CKD diagnosis system and compare the efficiency of the two diagnosis systems. This research performs different preprocessing on a CKD dataset. Based on the analysis and preprocessing, two data optimization approaches principal component analysis (PCA) and singular value decomposition (SVD) are applied to generate two optimized datasets. Moreover, classification is done on these two datasets by utilizing both CSVM and QSVM. Findings The comprehensive analysis of various techniques reveals that PCA outperforms SVD when paired with both CSVM and QSVM. Utilizing PCA, CSVM achieves a remarkable accuracy of 98.75 %, while QSVM achieves 87.5 % accuracy. In contrast, by utilizing SVD, both CSVM and QSVM achieve relatively lower accuracies, with CSVM achieving 96.25 % accuracy and QSVM achieving 60 % accuracy. Interpretation The final assessment of this research confirms that QSVM requires more time in classical experimental settings compared to CSVM. Furthermore, the research aims to make it easier to catch CKD early by providing reliable and efficient diagnosis methods. At the same time, it opens the door for trying out new quantum ML ideas in healthcare down the line.
The support vector machine algorithm with a quantum kernel estimator (QSVM-Kernel), as a leading example of a quantum machine learning technique, has undergone significant advancements. Nevertheless, its integration with classical data presents unique challenges. While quantum computers primarily interact with data in quantum states, embedding classical data into quantum states using feature mapping techniques is essential for leveraging quantum algorithms Despite the recognized importance of feature mapping, its specific impact on data classification outcomes remains largely unexplored. This study addresses this gap by comprehensively assessing the effects of various feature mapping methods on classification results, taking medical data analysis as a case study. In this study, the QSVM-Kernel method was applied to classification problems in two different and publicly available medical datasets, namely, the Wisconsin Breast Cancer (original) and The Cancer Genome Atlas (TCGA) Glioma datasets. In the QSVM-Kernel algorithm, quantum kernel matrices obtained from 9 different quantum feature maps were used. Thus, the effects of these quantum feature maps on the classification results of the QSVM-Kernel algorithm were examined in terms of both classifier performance and total execution time. As a result, in the Wisconsin Breast Cancer (original) and TCGA Glioma datasets, when Rx and Ry rotational gates were used, respectively, as feature maps in the QSVM-Kernel algorithm, the best classification performances were achieved both in terms of classification performance and total execution time. The contributions of this study are that (1) it highlights the significant impact of feature mapping techniques on medical data classification outcomes using the QSVM-Kernel algorithm, and (2) it also guides undertaking research for improved QSVM classification performance.