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.
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.
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 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.
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.
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.
Machine Learning (ML) approaches have achieved high performance by discovering underlying data patterns and structures. Diabetes is a life-threatening disease that affects vital organs such as the eyes (retinopathy), nerves (neuropathy), heart and kidneys (nephropathy). Although various ML models have been proposed for diabetes prediction, most struggle to effectively handle large, multi-feature datasets. Quantum Machine Learning (QML), which integrates quantum computing principles with machine learning, offers a promising solution for complex classification tasks. However, effective feature extraction remains challenging on current NISQ (Noisy Intermediate-Scale Quantum) devices due to hardware limitations. In this study, a Differentiable Quantum Circuit with Classical PCA Feature Compression is proposed for medical disease classification using a SMOTE-ENN resampled dataset and a penalized binary cross-entropy cost function to enhance quantum learning. The efficient ansatz designed in this work plays a crucial role in determining the model’s learning capability and feature extraction performance. To evaluate the robustness and generalization capability of the proposed model, three categories of medical datasets are considered. The primary focus is on diabetes classification using four diabetes-related datasets, while additional experiments are conducted on liver disease and chronic kidney disease datasets to assess the adaptability of the proposed framework across multiple healthcare domains. Six datasets from UCI, Mendeley and IEEE repositories are used: PIMA Indian Diabetes, Type-2 Diabetes, a private RTML Insulin dataset, Indian Liver Patient Dataset (ILPD), Early-Stage Diabetes Risk Prediction Dataset (ESDRPD) and Chronic Kidney Disease (CKD). The proposed quantum model is simulated using the PennyLane quantum simulator and compared against preprocessed classical classifiers. Experimental results demonstrate remarkable efficiency and rapid convergence within 10--20 epochs, achieving high F1-scores of 96.15% (PIMA), 97.50% (Type-2), 98.04% (RTML), 89.47% (ILPD), 98.66% (ESDRPD) and 97.84% (CKD). These findings demonstrate that the proposed quantum model efficiently extracts relevant features and effectively handles medical disease classification tasks, highlighting its strong potential for practical healthcare applications.
Abstract Background Diabetes, the fastest growing health emergency, has created several life-threatening challenges to public health globally. It is a metabolic disorder and triggers many other chronic diseases such as heart attack, diabetic nephropathy, brain strokes, etc. The prime objective of this work is to develop a prognosis tool based on the PIMA Indian Diabetes dataset that will help medical practitioners in reducing the lethality associated with diabetes. Methods Based on the features present in the dataset, two prediction models have been proposed by employing deep learning (DL) and quantum machine learning (QML) techniques. The accuracy has been used to evaluate the prediction capability of these developed models. The outlier rejection, filling missing values, and normalization have been used to uplift the discriminatory performance of these models. Also, the performance of these models has been compared against state-of-the-art models. Results The performance measures such as precision, accuracy, recall, F1 score, specificity, balanced accuracy, false detection rate, missed detection rate, and diagnostic odds ratio have been achieved as 0.90, 0.95, 0.95, 0.93, 0.95, 0.95, 0.03, 0.02, and 399.00 for DL model respectively, However for QML, these measures have been computed as 0.74, 0.86, 0.85, 0.79, 0.86, 0.86, 0.11, 0.05, and 35.89 respectively. Conclusion The proposed DL model has a high diabetes prediction accuracy as compared with the developed QML and existing state-of-the-art models. It also uplifts the performance by 1.06% compared to reported work. However, the performance of the QML model has been found as satisfactory and comparable with existing literature.