Performance Evaluation of Quantum and Classical Machine-Learning Models for Breast Cancer Diagnosis

Quantum computing shows promise for transformative innovation across various fields, including machine learning and health care. This research evaluates quantum machine-learning (QML) models, specifically quantum neural networks (QNNs) and quantum support vector machines (QSVMs), alongside their classical counterparts, traditional neural networks (TNNs), and support vector machines (SVMs), using the breast cancer dataset. The dataset is widely used for cancer diagnosis, making it a crucial test case for assessing quantum computing’s capabilities in health care. The study provides a comprehensive overview of quantum computing, QNNs, QSVMs, TNNs, and SVMs, exploring their advantages and limitations. Our methodology involves implementing and comparing these models based on precision, recall, F1-score, and accuracy metrics. The research illuminates the applications of quantum computing in machine learning and health care, suggesting avenues for future research such as advanced quantum algorithms, hyperparameter optimization, and hybrid quantum-classical approaches. These directions can enhance QML’s performance, applicability, and facilitate transformative advancements in health care.