Revolutionizing Lung Cancer Prognosis using a Quantum Approach for Uncertain Medical Data

Traditional machine learning methods does not always work faster enough to identify lung cancer in patient because of the limited availability of clinical data. This study proposed a Quantum SVM based approach for lung cancer prediction using a publicly available dataset containing 1158 patients records with 14 clinical features and also comparing both traditional SVM and Quan-tum SVM performance. The 8-qubit QSVM gained the highest accuracy of 88.57%, while the classical SVM achieved 88.35% results in lung cancer prediction. This research shows the efficacy of the Quantum Support Vector Machine (QSVM) in overcoming the limitations of addressing the uncertain-ty issue while working with medical data and also shows how quantum approach is better than the classical SVM.