Quantum kernel methods map clinical features into exponentially large Hilbert spaces where overlapping biological markers can become more separable than in fixed-dimensional classical feature spaces, but existing work evaluates single quantum feature maps, ignores barren-plateau failure modes, and relies on single train-test splits vulnerable to data leakage. Classical diagnostics for Parkinson's disease, breast cancer, and diabetes remain limited by the Specificity-Recall trade-off that fixed-dimensional kernels impose on overlapping biomarker distributions. We propose an adaptive hybrid quantum framework routing clinical data through three distinct quantum feature maps, namely Angle, Amplitude, and ZZ-entanglement, computing fidelity-based Gram matrices for Quantum SVM and Quantum KNN classifiers. A Logistic Regression meta-learner, trained on strictly out-of-fold predictions from nested cross-validation (5-fold inner, 10-fold outer), learns which quantum kernel generalizes on each dataset and suppresses those that do not. Evaluated on Parkinson's (195 patients), Breast Cancer (569), and Diabetes (768) with 1,000-iteration bootstrapping, the ensemble raised Parkinson's Specificity from 0.585 to 0.813 ([Formula: see text]) while maintaining Recall above 0.95, matched classical RBF-SVM on Breast Cancer (all [Formula: see text]), and improved Diabetes Recall from 0.553 to 0.621 ([Formula: see text]). A standalone Variational Quantum Classifier failed on all datasets (ROC-AUC 0.51 to 0.57), confirming barren plateau limitations. Explainability via SHAP, LIME, and Permutation Importance revealed dataset-dependent kernel trust: the meta-learner suppressed QKNN Amplitude on Diabetes (coefficient [Formula: see text]) while amplifying it on Parkinson's (1.761). PCA-based feature backtracking recovered established biomarkers including Insulin and Glucose for Diabetes, vocal perturbation measures for Parkinson's, and nucleus geometry for Breast Cancer. Noise simulations confirmed graceful degradation under NISQ conditions. The framework performs data-driven kernel selection, removing the need to pre-specify an encoding strategy.
Quantum kernel methods map clinical features into exponentially large Hilbert spaces where overlapping biological markers can become more separable than in fixed-dimensional classical feature spaces, but existing work evaluates single quantum feature maps, ignores barren-plateau failure modes, and relies on single train-test splits vulnerable to data leakage. Classical diagnostics for Parkinson's disease, breast cancer, and diabetes remain limited by the Specificity-Recall trade-off that fixed-dimensional kernels impose on overlapping biomarker distributions. We propose an adaptive hybrid quantum framework routing clinical data through three distinct quantum feature maps, namely Angle, Amplitude, and ZZ-entanglement, computing fidelity-based Gram matrices for Quantum SVM and Quantum KNN classifiers. A Logistic Regression meta-learner, trained on strictly out-of-fold predictions from nested cross-validation (5-fold inner, 10-fold outer), learns which quantum kernel generalizes on each dataset and suppresses those that do not. Evaluated on Parkinson's (195 patients), Breast Cancer (569), and Diabetes (768) with 1,000-iteration bootstrapping, the ensemble raised Parkinson's Specificity from 0.585 to 0.813 ([Formula: see text]) while maintaining Recall above 0.95, matched classical RBF-SVM on Breast Cancer (all [Formula: see text]), and improved Diabetes Recall from 0.553 to 0.621 ([Formula: see text]). A standalone Variational Quantum Classifier failed on all datasets (ROC-AUC 0.51 to 0.57), confirming barren plateau limitations. Explainability via SHAP, LIME, and Permutation Importance revealed dataset-dependent kernel trust: the meta-learner suppressed QKNN Amplitude on Diabetes (coefficient [Formula: see text]) while amplifying it on Parkinson's (1.761). PCA-based feature backtracking recovered established biomarkers including Insulin and Glucose for Diabetes, vocal perturbation measures for Parkinson's, and nucleus geometry for Breast Cancer. Noise simulations confirmed graceful degradation under NISQ conditions. The framework performs data-driven kernel selection, removing the need to pre-specify an encoding strategy.
Background: Breast cancer remains a leading cause of cancer-related mortality, and reliable computational decision support is increasingly viewed as a complement to expert pathological assessment rather than a replacement for it. Variational quantum classifiers (VQCs) and Quantum Support Vector Machines (QSVMs) have recently been promoted as candidate models for medical classification, yet most published comparisons rely on internal hold-out validation alone and report only a single point estimate of discrimination, omitting calibration, decision-analytic value, and explainability—three ingredients that any clinically credible model must furnish. Methods: We assembled a complete quantum–classical machine learning pipeline and evaluated it under a deliberately stringent protocol designed to expose, rather than conceal, the limitations of current Noisy Intermediate-Scale Quantum (NISQ)-era models. The analytical hypothesis was conservative and stated in advance; in light of saturated classical baselines on this benchmark, we did not anticipate a quantum advantage in raw discrimination, and we framed the study as a methodological probe rather than as a competition. Using the Wisconsin Diagnostic Breast Cancer (WDBC) dataset (n = 569) for development and an independent Wisconsin Original (WBC) cohort (n = 683) for external validation, we benchmarked five classical learners (XGBoost, LightGBM, CatBoost, RandomForest, RBF-SVM), two quantum models (an eight-qubit VQC implemented in PennyLane and a ZZ-feature-map QSVM implemented in Qiskit), and a stacked hybrid ensemble. The evaluation framework combined Optuna-driven hyperparameter optimisation, internal–external cross-validation, and external validation on the independent WBC cohort. Robustness and interpretability were then probed through circuit depth and embedding rotation ablation, depolarising noise stress tests, learning curve and feature stability analysis, decision curve analysis, and dual SHAP-based explanations covering both a direct tree-based explanation and a quantum surrogate. Reporting followed the TRIPOD + AI guideline. Results: On the internal test partition, RBF-SVM achieved the highest discrimination (AUC = 0.998), with XGBoost, LightGBM, CatBoost, the hybrid ensemble, and the VQC clustering between 0.992 and 0.996; the QSVM with a ZZ-fidelity kernel underperformed substantially (AUC = 0.727). Pairwise tests for correlated ROC curves indicated that most differences among top models were not statistically significant. On the external WBC cohort, model rankings reorganised, as RBF-SVM (AUC = 0.986, 95% CI 0.946–0.997), RandomForest (0.985, 95% CI 0.945–0.996), VQC (0.983, 95% CI 0.942–0.995), and the hybrid ensemble (0.982, 95% CI 0.941–0.995) all retained near-ceiling discrimination with extensively overlapping confidence intervals. Ablation analysis demonstrated that the choice of embedding rotation is decisive—Z-rotation embeddings collapsed VQC performance to chance levels (AUC ≈ 0.50), whereas X- and Y-rotations preserved it. Depolarising noise up to p = 0.10 had a negligible effect on the VQC, and SHAP analyses converged on worst concave points, mean concave points, and worst area as the dominant predictors across both classical and quantum models. Decision curve analysis showed positive net benefit for both classical and hybrid models across the clinically meaningful threshold range, exceeding both the treat-all and treat-none reference strategies throughout. Conclusions: In the present regime, the principal contribution of QML is not raw discrimination—modern classical learners are already at the data ceiling—but the construction of a rigorous, reproducible, externally validated, and interpretable benchmarking framework in which quantum models can be fairly compared with their classical counterparts. Because evaluation was confined to curated benchmark datasets rather than real-world clinical populations, the interpretability and net benefit findings reported here should be read as benchmark-level evidence and not as a demonstration of readiness for clinical deployment.
Quantum kernel methods are often proposed as a route to improved medical image classification because quantum feature maps can embed data into high-dimensional Hilbert spaces. However, their practical value remains unclear when compared with strong classical kernels under leakage-controlled conditions. This study benchmarks two simulated quantum kernel support vector machines, QSVM-ZZ and QSVM-Pauli, against logistic regression, linear SVM, fixed-default RBF-SVM, and a compact multi-layer perceptron on BrainTumorMRI and BreastMNIST. All models used identical frozen ResNet18 features, train-only standardisation, PCA compression to four and eight dimensions, three random seeds, and matched classifier-training budgets where applicable. Across 24 seed-level matched comparisons, the best quantum kernel model never outperformed the best classical model. The mean quantum-minus-classical macro-F1 gap was - 0.2230, with all 24 gaps negative. Fixed pairwise comparisons confirmed that RBF-SVM exceeded both quantum kernels individually. QSVMs also required approximately 50 × to more than 220 × higher runtime. These findings show that, for compressed ResNet18 medical image features under noiseless simulation, the tested QSVM-ZZ and QSVM-Pauli kernels did not provide a practical advantage over fixed-default RBF-SVM.
Lung cancer screening with low-dose chest computed tomography reduces mortality, but its impact is limited by uptake, adherence, and management challenges. Blood-based cell-free DNA (cfDNA) biomarkers offer a complementary approach, although early detection remains difficult because of lung cancer heterogeneity and high-dimensional, nonlinear molecular signals. We evaluated quantum-classical hybrid machine learning for lung cancer detection using DNA fragmentomics and DNA methylation. After feature selection, models were trained using 20- and 40-feature subsets. Features were encoded into quantum Hilbert space using angle and dense-angle feature maps with multiple entanglement strategies. Fidelity-based quantum kernels were computed with exact statevector simulation and integrated with precomputed-kernel SVM and kernel-PCA logistic regression and compared with an SVM model trained on the original features. This framework enabled systematic evaluation of how encoding and entanglement design affect classification. Across repeated held-out evaluations, quantum-kernel models achieved competitive performance on both datasets. For fragmentomics, several 20-feature configurations improved AUC relative to a classical SVM baseline, suggesting effective capture of nonlinear cfDNA fragmentation structure. For methylation, the classical SVM achieved the highest AUC, although selected quantum models remained competitive and improved specificity in some cases. Increasing features from 20 to 40 did not consistently improve performance and often increased variability. Overall, these results support quantum kernel methods as a promising approach for cfDNA-based lung cancer detection.
Parkinson’s disease (PD) is a progressive neurodegenerative disorder affecting millions worldwide, where early and accurate diagnosis plays a critical role in improving patient outcomes. While classical machine learning methods have shown strong performance in PD classification using clinical and acoustic data, they remain limited in capturing complex nonlinear feature interactions in high-dimensional spaces. This study explores the application of quantum machine learning (QML) techniques for PD prediction, focusing on Variational Quantum Classifiers (VQC) and Quantum Support Vector Machines (QSVM), and compares their performance with strong classical baselines including Logistic Regression, SVM, Random Forest, Grid Search–optimized models, and XGBoost. Experiments were conducted using stratified train–test splits and validated through cross-validation and statistical testing. Results show that classical models achieve competitive performance, with XGBoost reaching 91.9% accuracy. However, quantum models demonstrate slightly improved performance, with the VQC using EfficientSU2 achieving the highest accuracy of 93.1%, followed by the Real Amplitudes VQC (92.6%) and QSVM (92.2%). These improvements are consistent across evaluation metrics including F1-score and recall. Statistical analysis using 10-fold cross-validation indicates that the VQC (EfficientSU2) shows a significant improvement over classical baselines ( p = 0.031), while other quantum models do not achieve statistical significance over XGBoost ( p > 0.05). McNemar’s test on the independent test set confirms no significant difference in final prediction distributions between quantum and classical models. Overall, the findings suggest that quantum machine learning models are competitive with state-of-the-art classical approaches, offering marginal but consistent performance gains. This study highlights the potential of quantum-enhanced learning frameworks for biomedical classification tasks, while also emphasizing that their advantages remain incremental rather than definitive under current simulation-based implementations.
Early diagnosis of chronic diseases is paramount to improving patient survival rates, optimizing treatment trajectories, and mitigating escalating healthcare expenditures. While the recent explosion of heterogeneous healthcare data presents robust opportunities for predictive modeling, it simultaneously introduces severe computational bottlenecks regarding data dimensionality and non-linear complexity. This paper proposes a novel, high-performance hybrid prediction framework that seamlessly fuses classical machine learning topologies with Variational Quantum Circuits (VQCs) within a Quantum Machine Learning (QML) paradigm. The proposed architecture targets the multi-classification and risk profiling of five high-prevalence chronic conditions: diabetes, cardiovascular disease, breast cancer, chronic liver disease, and chronic kidney disease This project introduces “Quantum Health,” a Quantum Machine Learning (QML)-based multi disease prediction system that integrates classical and quantum computing to enhance diagnostic performance. It employs five quantum-enhanced models: Quantum Random Forest for breast cancer, Quantum Neural Network for diabetes, Quantum k-Nearest Neighbors (QkNN) for heart disease, Quantum AdaBoost for liver disease, and Quantum Naive Bayes for kidney disease. The models are evaluated using both classical methods and PennyLane simulations, enabling direct comparison of performance. The system is deployed as a Flask-based web application featuring a user-friendly dashboard, disease-specific prediction modules, prediction history with CSV export, and an analytics dashboard comparing classical and quantum accuracies. Each module provides predictions, confidence scores, and feature importance insights. Unlike monolithic classical models, our approach incorporates a parameterized quantum layer that maps low-dimensional classical medical vectors into high-dimensional Hilbert spaces, capturing intricate, non-linear correlations that evade classical kernels. Experimental evaluations executed on simulated quantum backends demonstrate that the proposed Quantum Hybrid Model drastically outperforms conventional baselines, achieving an overall classification accuracy of 96.8% and an Area Under the Curve (AUC) of 98.4%. The findings establish that integrating quantum circuit state vectors with ensemble classical architectures provides a scalable, computationally efficient, and highly generalizable paradigm for next-generation clinical decision support systems.
This paper presents an empirical comparison of pure quantum, hybrid quantum-classical, and classical support vector machines (SVMs) for binary medical classification on the Breast Cancer Wisconsin dataset. Taking advantage of uniform data preprocessing and feature selection, our hybrid QSVM with quantum kernel mapping coupled with classical optimization achieves accuracy of 98.25% compared with the classical SVM (94.74%) and pure quantum SVM (93.86%). In-depth benchmarking incorporates accuracy, recall, F1-score, and training time, exposing accuracy/computational cost trade-offs. We discuss how dimensionality of features and kernel selection influence model scalability and performance. Albeit constrained to a single dataset and simulation, this work enhances knowledge about hybrid quantum SVM benefits and real-world implications. Future efforts will seek to expand benchmarking to other datasets, include real quantum hardware assessment, and create explanation methods to improve interpretability and clinical usability.