Early differentiation of Parkinson’s disease PD from progressive supranuclear palsy PSP , and reliable stratification of PD progression remain difficult because clinically heterogeneous measurements may carry limited class information. Quantum kernel methods are frequently proposed for biomedical classification, but their value depends on the data representation and must be established against tuned classical baselines. Methods Two tabular analyses contained in the supplied research chapters were reconstructed as an integrity preserving benchmark. The primary dataset comprised 500 records, 12 columns, no missing values, and three approximately balanced PD progression classes 154, 164, and 182 observations . Patient identifiers were excluded categorical and numerical fields were encoded and standardized an 80 20 stratified split and five fold tuning were used. Principal component analysis reduced the predictors to five components 61.10 variance , enabling five qubit fidelity kernel classifiers using ZFeatureMap, ZZFeatureMap, PauliFeatureMap, and an Ry–Rz CNOT map. Logistic regression, random forest, radial basis function SVM, and XGBoost served as classical comparators. A secondary feasibility dataset used three whole blood probes from GSE6613 after metadata resolution, retaining 22 healthy controls, 50 PD cases, and six PSP cases for classical five fold assessment. Results On the progression task, the best classical accuracy was 35.00 random forest , while the best quantum kernel accuracy was 36.00 ZZFeatureMap . ZFeatureMap achieved the highest macro AUC 0.5488 . All results were close to the 33.3 chance accuracy expected for three balanced classes the proposed Ry–Rz CNOT map achieved 33.00 accuracy and AUC 0.4868. In the secondary dataset, random forest achieved 64.10 overall accuracy but only 37.58 macro sensitivity, reflecting severe PSP imbalance. Conclusion Quantum feature map complexity did not overcome weak endpoint signal, and the study provides no evidence of quantum advantage or clinical readiness. The principal contribution is a transparent negative benchmark and a validation roadmap for future multimodal, longitudinal PD–PSP studies. Parkinson’s disease progressive supranuclear palsy quantum kernel quantum support vector classifier disease progression feature map class imbalance negative results. 35-42 Issue-5 Volume-10 Kumar Sanu | Madhuvan Dixit