Recent research on quantum machine learning has demonstrated that quantum computing-based models can consistently outperform classical methods. In the field of healthcare, where immediate intervention is required, this is extremely important. Chronic Kidney Disease (CKD) is a widespread and critical health issue, demanding accurate and efficient diagnostic tools. We have explored the potential of Quantum Support Vector Machine (QSVM) over classical Support Vector Machine (SVM) for CKD diagnosis in this research, utilizing quantum computing principles for computational advantage. QSVMs in healthcare prediction have gained attention in the research community. QSVMs are effective at classifying and predicting medical data. We have employed a comprehensive dataset of patient health records, including clinical and demographic attributes, as input features for both QSVM and classical SVM. The accuracy and speed of healthcare predictions can be enhanced by employing QSVM. This will eventually lead to better healthcare systems that operate more efficiently. Our Quantum Machine Learning (QML) model yields higher classification accuracy at roughly 97.50% and better speed-up compared to the Classical Machine Learning (CML) model.