Quantum Machine Learning for Invasive Ductal Carcinoma Classification using Quantum Kernels

This research study reviews the quantum kernel techniques and discusses about the application of a quantum machine learning model for the classification of breast cancer using Qiskit Machine learning version 0.4.0. This study applies ZZ-Feature Map to transform classical computer data into quantum states through the use of entanglement and superposition qualities characteristic of quantum mechanics. Then, a Quantum Kernel was created using the feature map and quantum instance (simulator) to compute similarity in data points in the space of a quantum state. It utilized this kernel to train QSVC - a quantum analogue of classical Support Vector Machine (SVM) with breast cancer data. With just two pivoting features for categorization, the resource limits obtained 70% overall accuracy. Preliminary Findings Using quantum kernel techniques improves the classification jobs via quantum computation.