Comparative Performance Evaluation of Classical Machine Learning and Quantum SVM for Heart Disease Prediction using a Quantum-Featured Dataset

Abhijit Pathak, Abhijit, Touhidul Alam Seyam, Zarin Hadika, Arifur Rahaman, Bulbul Ahamed

Published Dec 4, 2025• 0 citations

Abstract

Heart disease remains a leading cause of mortality globally, driving interest in advanced computational methods forearly prediction. This study presents a comparative analysis of classical machine learning techniques versus a QuantumSupport Vector Machine (QSVM) for predicting heart disease using a specialized dataset featuring standard clinicalmetrics alongside a unique 'QuantumPatternFeature. 'We implemented and evaluated six classical algorithms (LogisticRegression, K-Nearest Neighbors, Decision Tree, Random Forest, Naive Bayes, Gradient Boosting), employingRandomizedSearchCV for hyperparameter optimization. For the quantum approach, a QSVC utilizing Qiskit'sZZFeatureMap (reps=2) and FidelityQuantumKernel was trained and tested using a classical simulator. A classicalSupport Vector Classifier (SVC) with an RBF kernel served as an additional baseline. Performance was assessed on a20% hold-out test set using accuracy, precision, recall, F1-score, and confusion matrices. Results indicate that tunedclassical models, particularly Logistic Regression and Gradient Boosting, achieved the highest accuracy (93.0%),significantly outperforming the simulated QSVC (79.0%). The classical SVC baseline also surpassed the QSVM with89.0% accuracy. Furthermore, the QSVM exhibited substantially higher computational times for both training andprediction on the simulator compared to all classical methods. The findings suggest that for this dataset size and thespecific simulated QSVM configuration, classical machine learning approaches offer superior performance andefficiency, and the 'QuantumPatternFeature' did not confer a discernible advantage within this quantum implementationframework.

DOI: 10.5281/zenodo.17810231

Related papers

Heart Disease Prediction Using Hybrid Quantum-Classical Machine Learning Models

Pavan Reddy T, D Vishwachetan, S. Rajarajeswari

Cardiovascular diseases remain the leading cause of mortality globally, necessitating accurate diagnostic tools for early detection and intervention. This paper presents a comprehensive comparative and hybrid analysis of quantum and classical machine learning models for heart disease prediction using the UCI Cleveland dataset. We implement classical baseline models including Logistic Regression, Random Forest, Support Vector Machine (SVM), and XGBoost, alongside quantum models: Quantum Support Vector Machine (QSVM) with statevector fidelity kernels, Variational Quantum Classifier (VQC) with data-reuploading ansätze, and Quantum Convolutional Neural Networks (QCNN) with parametric pooling. The primary contribution is the development of a hybrid quantum classical ensemble meta-classifier that fuses predictions from all classical and quantum learners using XGBoost as a meta learner. Experiments conducted in Google Colab using Qiskit 1.2+ and Penny Lane 0.36+ demonstrate that the proposed hybrid ensemble achieves superior performance with 98.33accuracy, 100perfect AUC-ROC of 1.0, substantially outperforming standalone classical models (best: 88.33(best: 80hybrid model’s superiority. These results underscore the potential of quantum feature spaces combined with classical decision boundaries in healthcare prediction systems, and demonstrate the immediate utility of hybrid quantum-classical integration in medical diagnostics on near-term quantum hardware.

International Conference on Knowledge Engineering and Communication Systems (ICKECS)Apr 24, 20260 citations

A Comparative Study of Classical and Quantum Algorithms for Heart Disease Prediction Using Patients' Vital Signs

Paramita Basak Upama, Parama Sridevi, Masud Rabbani +5 more

The aim of this study is to enhance the accuracy and reduce the time complexity of predicting cardiac illnesses by utilizing patient vital signs exclusively. The importance of timely treatment in critical situations where quick decisions are necessary is emphasized here. Precise predictions have the potential to prevent health deterioration and even save lives. By analyzing vast datasets (images, texts etc.) and detecting subtle patterns, quantum machine learning algorithms (QML) can offer more accurate results in a shorter period compared to classical algorithms. The feature set used here is a novel one to be used for the quick detection and early prediction of cardiovascular diseases, and also a convenient one for this task. To predict heart diseases or abnormalities, both classical and quantum machine learning techniques have been employed in this paper. We have developed four models based on Support Vector Machine (SVM), Neural Network (NN), Quantum Support Vector Machine (QSVM), and Quantum Neural Network (QNN) and compared their performance on a balanced sample of a vast dataset for heart diseases prediction. After comparing the models' performance, we found that Quantum Support Vector Machine (QSVM) performed best with an accuracy of 75% and to-fold Cross-validation score of 80%.

IEEE Annual International Computer Software and Applications Conference (COMPSAC)Jul 2, 20242 citations

A Comparative Analysis of Classical and Quantum Approaches for Heart Attack Prediction

Rohan Landge, Shreni Bandgar, Rohit Salke +3 more

Heart diseases are a set of heart and blood-vessel-related disorders, arising from a variety of lifestyle, environmental, and genetic factors. Even with advancements in medical technology, accurately forecasting heart attack risk remains challenging, as today’s diagnosis methods fail to catch the nonlinearity and complexity in clinical data. Classical machine learning algorithms, such as k-nearest neighbors and support vector machine, when mixed with synthetic minority oversampling technique, show promise for heart attack risk prediction. These models for real-world scenarios struggle with high-dimensional, imbalanced, nonlinear datasets, which limits the effectiveness of models. Quantum machine learning offers a computational approach and takes benefit of concepts like superposition and entanglement to uncover insightful patterns. In this work, we compare classical and quantum models for heart attack risk prediction using a heart attack prediction dataset with 14 clinical features and 1888 patient records. The outcomes demonstrate that the classical support vector machine, when combined with synthetic minority oversampling technique, achieves the highest predictive accuracy of 92.00%, with minimal run time. k-nearest neighbors also works well, with an accuracy of 83.33%. Among quantum methods, quantum support vector machine with quantum Fourier transform achieves a 74.00% accuracy, while quantum clustering reaches 67.20%. However, both approaches required higher computational power. The quantum Fourier transform–based approach improves quantum model performance, particularly in recognizing cyclic trends in clinical data. However, classical approaches remain superior with respect to accuracy and efficiency on current hardware. This work demonstrates the strength of quantum machine learning in handling complex data while also recognizing the present challenges with quantum hardware and simulators. It suggests that upcoming research should focus on testing these models on actual quantum devices. Adopting standardized performance metrics can improve both classical and quantum-based decision support systems for heart disease risk prediction.

Auerbach Publications eBooksFeb 24, 20260 citations

A Comparative Analysis of Quantum and Classical Algorithms for Heart Disease Prediction

Sathya S, Ramasamy Madhumathi

Quantum Computing (QC) works based on the principle of quantum mechanics, which is different from traditional computers. Heart disease remains the leading cause of mortality worldwide and the development of advanced predictive models for early diagnosis is necessary. In this paper, the Support Vector Machine (SVM), Quantum Support Vector Machine (QSVM), and Variational Quantum Classifier (VQC) are used to predict heart disease. Among these algorithms, QSVM and VQC are used for heart disease prediction using QC principles. The SVM and QSVM achieves the accuracy of 80% and 69% and VQC achieves the highest accuracy of 86% with ZFeatureMap and RealAmplitude in 100 iterations. The FeatureMap and Ansatz are used for turning data into quantum states. The VQC employs a parameterized quantum circuit to minimize the classification error and optimization is done using gradient-free COBYLA. In addition to ZFeatureMap, other FeatureMaps like ZZFeatureMap and PauliFeatureMap are also performed in VQC.

International Conference on Distributed Systems, Computer Networks and Cybersecurity (ICDSCNC)Sep 20, 20240 citations

Cloud-Integrated Hybrid Quantum Machine Learning Framework for Enhanced Cardiovascular Disease Prediction, Clinical Decision Support

Snehal Rahul Rathi, Vikas Balasaheb Maral, Aryan Dongare +3 more

Heart disease remains one of the most critical global health concerns, creating a strong need for intelligent and accurate prediction systems. Even while conventional machine learning (ML) has shown promise, handling large and complex medical datasets often reduces the efficiency of traditional machine learning systems. Using a cloud-supported quantum framework, we present a hybrid diagnostic framework that compares three quantum architectures—QSVM, VQC, and QCNN—with five classical algorithms: Random Forest, SVM, KNN, Logistic Regression, and Gradient Boosting. The framework includes a cloud-managed preprocessing stage that uses PCA to map high-impact features, like blood pressure and cholesterol, onto an optimized qubit space in order to overcome the resource limitations of existing NISQ devices. To test the models, the Heart-Disease data set was applied, where classical algorithms demonstrated exceptional performance ranging between 70% to 75%. Specifically, because of the high precision of 0.81, VQC proved to possess remarkable performance on optimized data sets.

Advances in computational intelligence and robotics book seriesAug 19, 20260 citations

Heart Disease Prediction Analysis Using Quantum-Enhanced Features with Classical and Quantum Machine Learning Models

Kukatlapalli Pradeep Kumar, Kumar S. Babu, Delna Liz Denny +2 more

Heart disease continues to be among the top causes of death globally, and thus precise and timely detection mechanisms are necessary for successful clinical intervention. This chapter introduces a sophisticated predictive model integrating quantum-enhanced feature extraction with classical and quantum machine learning (QML) models to enhance prediction accuracy and reliability of heart disease. Quantum models like quantum random forest (QRF), quantum k-nearest neighbor (QKNN), and quantum gradient boosting classifier (QGBC) are used in conjunction with traditional models like XGBoost and SVM to investigate hybrid computational synergies. The method utilizes quantum feature mapping and entanglement-based encoding to identify intricate nonlinear patterns present in cardiovascular data. A thorough performance comparison based on the UCI Heart Disease dataset shows that quantum-augmented models exhibit better predictive accuracy, precision, and F1-scores than conventional models. The findings support the potential of quantum computing to speed up healthcare analytics and make more accurate disease diagnosis possible. This work discusses the pioneering merger of quantum computing and machine learning as a revolutionary strategy for data-driven intelligent medical decision support systems.

Auerbach Publications eBooksFeb 24, 20260 citations