Comparison of Machine Learning and Quantum Machine Learning for Breast Cancer Detection

Yearly the number of breast cancer subjects are rising exponentially. In fact, breast cancer is very deadly, and all over the world the losses are increasing. It is very important to have an improved system to predict and diagnose the cancer effectively, which helps the subjects to have a better quality of life. In fact, it is crucial to have an accurate prediction system to improve the treatment and chances of survival. Moreover, earlystage detection, high accuracy of prediction and diagnosis is required at appropriate time. This paper aims to analyze the Machine Learning (ML), Deep Learning (DL) and Quantum Machine Learning (QML) techniques to diagnose the breast cancer subjects. The QML is an emerging field which transforms the input data onto the qubits and processing is performed using the quantum gates and operators. Quantum computing technology enhances the security of data transmission, hence has great application in communication and health care data processing. In this work, Logistic Regression (LR) and SVM (Linear) achieved accuracy of $\mathbf{9 7 . 9 \%}$, CNN $\mathbf{9 8 . 6 \%}$ and QSVC $\mathbf{9 3 \%}$ to classify 569 samples of normal and cancerous binary classes. Less accuracy shows noise in the quantum computing, which can be improved by optimization of rotation of specific gates.