Chronic Kidney Disease is one of the serious global health issue worldwide as it has high mortality rate and yet most of the population is unaware of this disease. Therefore early detection and treatment of the chronic kidney disease is necessary to avoid its harsh effects on patients’ health. Various classical machine learning techniques and algorithms have been implemented for classification of chronic kidney disease. Quantum machine learning is an emerging field which uses superposition and entanglement of qubits, and thus has higher computation power than classical machine learning algorithms improving the performance and computation speed. This study aims to explore quantum machine learning for successful classification of chronic kidney disease. Hence, Quantum support vector machine is implemented and compared with classical support vector machine on UCI chronic kidney disease dataset. Quantum support vector machine is implemented and simulated by two approaches, first using PennyLane library, and second using Qiskitlibrary. PennyLane approach involves generation of quantum kernel which is then fed to support vector classifier. Whereas Qiskit involves generation of quantum kernel which is then fed to quantum support vector classifier. The results of both these approaches are at par with the classical support vector ma chine. The model using angle embedding in PennyLane achieves highest accuracy of 100% and f1 score of 100% which is equivalent to the classical implementation. The model trained using YZ PauliFeatureMap with 3 repetitions achieves both accuracy and f1 score of 99.00%.