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

Abstract

Heart disease remains a leading cause of mortality globally, driving interest in advanced computational methods for early prediction. This study presents a comparative analysis of classical machine learning techniques versus a Quantum Support Vector Machine (QSVM) for predicting heart disease using a specialized dataset featuring standard clinical metrics alongside a unique 'QuantumPatternFeature.' We implemented and evaluated six classical algorithms (Logistic Regression, K-Nearest Neighbors, Decision Tree, Random Forest, Naive Bayes, Gradient Boosting), employing RandomizedSearchCV for hyperparameter optimization. For the quantum approach, a QSVC utilizing Qiskit's ZZFeatureMap (reps=2) and FidelityQuantumKernel was trained and tested using a classical simulator. A classical Support Vector Classifier (SVC) with an RBF kernel served as an additional baseline. Performance was assessed on a 20% hold-out test set using accuracy, precision, recall, F1-score, and confusion matrices. Results indicate that tuned classical 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 with 89.0% accuracy. Furthermore, the QSVM exhibited substantially higher computational times for both training and prediction on the simulator compared to all classical methods. The findings suggest that for this dataset size and the specific simulated QSVM configuration, classical machine learning approaches offer superior performance and efficiency, and the 'QuantumPatternFeature' did not confer a discernible advantage within this quantum implementation framework.

Keywords

• Heart Disease Prediction
• Classical Machine Learning
• Quantum Machine Learning (QML)
• Quantum Support Vector Machine (QSVM)
• Quantum Kernel
• Performance Evaluation
• Comparative Analysis

How to cite

Abhijit Pathak, Touhidul Alam Seyam, Zarin Hadika, Arifur Rahaman, Bulbul Ahamed (2025). Comparative Performance Evaluation of Classical Machine Learning and Quantum SVM for Heart Disease Prediction using a Quantum-Featured Dataset. Sonargaon University Journal, 5(I), 89–105.

@article{pathak20253,
  title   = {Comparative Performance Evaluation of Classical Machine Learning and Quantum SVM for Heart Disease Prediction using a Quantum-Featured Dataset},
  author  = {Abhijit Pathak and Touhidul Alam Seyam and Zarin Hadika and Arifur Rahaman and Bulbul Ahamed},
  journal = {Sonargaon University Journal},
  volume  = {5},
  number  = {I},
  pages   = {89--105},
  year    = {2025},
  issn    = {2518-3125},
  url     = {https://su.edu.bd/journal/volume-5-issue-1/comparative-performance-evaluation-of-classical-machine-learning-and-quantum-svm}
}