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.
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.
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.
In this study, we develop and compare quantum and classical machine learning-based chronic kidney disease prediction models. We used the "Chronic_Kidney_Disease Data Set" of the UCI Machine Learning Repository. We performed data preprocessing and applied feature engineering techniques to select the best features. We developed two quantum machine learning-based models and two classical machine learning-based models. We used a hybrid classical-quantum environment for building quantum machine learning models. Finally, we compared the performances of all four models. We found that the Quantum Support Vector Machine performs best among the quantum models. The model’s accuracy was 95% with a k-fold cross-validation score of 94.5% and an ROC-AUC score of 0.987. Among the classical models, the Support Vector Machine showed the highest performance with an accuracy of 92.5%, a k-fold cross-validation score of 93.9%, and a ROC-AUC score of 0.974. Overall, the Quantum Support Vector Machine outperformed all other developed models in terms of accuracy and validation scores. If the quantum models can be executed in a quantum computer instead of a hybrid environment, the models will exhibit higher accuracy and faster execution time. As the models are precisely predicting chronic kidney disease with high accuracy, we believe this study will act as an inspiring framework in the less-investigated field of quantum machine learning-based chronic kidney disease prediction.
Chronic Kidney Disease (CKD) does not present symptoms in early phases so often goes undiagnosed. This increases risk of severe clinical outcomes. Hence, efficient patient management demands prompt diagnosis and an accurate diagnosis. Classical machine learning models effectively diagnose CKD but they struggle with learning representations and interpretability, which undermines the potential for clinical deployment. Quantum Machine Learning (QML) enables greater feature expressivity with quantum features spaces. However, quantum classifiers executed on Noisy Intermediate-scale Quantum (NISQ) devices may be susceptible to noise-induced instability. This work proposes an Explainable Bagging-Based Quantum Support Vector Classification (EB-QSVC) framework which enhances CKD detection robustness and interpretability. This framework uses classical preprocessing followed by dimensionality reduction with Principal Component Analysis, qubit feature encoding for quantum mechanics and ensemble bagging to suppress NISQ. The use of explainable artificial intelligence methods is employed to deliver clinically useful information.The experiment shows that the accuracy of a QSVC with no extended-attribute is about 0.70, while the proposed EB-QSVC achieves accuracy up to 0.95 matching with the strong classical baselines. The results show that ensemble-based and interpretable quantum learning methods can stabilize quantum models subjected to the hardware limitations at hand, thus providing a reliable decision-support framework for healthcare.
As a degenerative disease that seriously affects the central nervous system, early diagnosis of Parkinson's disease is important for slowing down the course of the disease and improving patients' quality of life.In recent years, machine learning has shown great potential in medical data analysis, and support vector machines (SVMs) are widely used in classification and prediction tasks.However, traditional SVMs have some limitations in high dimensionality and complex data processing.With the rapid development of quantum computing, quantum support vector machines (QSVMs) have become an emerging technology that has attracted much attention due to its ability to process largescale data and its potential for modeling high-dimensional features.In this paper, we compare traditional SVMs and QSVMs in the analysis of Parkinson's disease data, and evaluate their performance in terms of classification accuracy.The experiments are conducted on a publicly available dataset and analyzed in detail through the steps of model construction, data preprocessing, algorithm implementation, and performance evaluation.The results show that QSVM outperforms traditional SVM in complex feature space, which demonstrates its potential advantages and application prospects in medical data analysis.
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.
The application of machine learning has shown significant progress in various fields, including clinical data classification. This study presents a comparative analysis between the classical Support Vector Machine (SVM) and Quantum Support Vector Machine (QSVM) for breast cancer classification using the Wisconsin Diagnostic Breast Cancer (WDBC) dataset. Principal Component Analysis (PCA) was applied as dimension reduction strategy across three configurations (PCA = 2, PCA = 4, and PCA = 6) to evaluate the sensitivity of both models to the feature space dimension. Preprocessing included log1p transformation on 22 skewed features, Manual SMOTE balancing, and MinMaxScaler normalization. SVM was optimized via GridSearchCV (80 parameter combinations, cv = 5), while QSVM employed a ZZFeatureMap quantum kernel (reps = 2, entanglement = full) on qasm_simulator. Experimental results demonstrate that SVM achieved superior accuracy across all configurations, with peak performance at PCA = 6 (Accuracy= 98.83%, AUC = 0.9985, Specificity = 1.0000, Sensitivity = 0.9688, Precision = 1.0000, NPV = 0.9817, and F1-score for malignant = 0.98). QSVM achieved its highest accuracy at PCA = 4 (92.98%), AUC = 0.9622, Sensitivity = 0.9219, Precision = 0.8939, NPV = 0.9524, and F1-score for malignant = 0.91. Across the three PCA configurations, QSVM exhibited a non-monotonic relationship between PCA dimensions and quantum kernel performance . These findings provide a quantitative benchmark for comparing quantum and classical machine learning in breast cancer diagnosis.