Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2604.24597

Quantum Kernel Advantage over Classical Collapse in Medical Foundation Model Embeddings

Sebastian Cajas Ordóñez, Felipe Ocampo Osorio, Dax Enshan Koh, Rafi Al Attrach, Aldo Marzullo, Ariel Guerra-Adames, J. Alejandro Andrade, Siong Thye Goh, Chi-Yu Chen, Rahul Gorijavolu, Xue Yang, Noah Dane Hebdon, Leo Anthony Celi

quant-phcs.AISubmitted Apr 27, 2026• Announced Apr 28, 2026• 1 citation
arXivHTMLPDF

Abstract

We provide evidence of quantum kernel advantage under noiseless simulation in binary insurance classification on MIMIC-CXR chest radiographs using quantum support vector machines (QSVM) with frozen embeddings from three medical foundation models (MedSigLIP-448, RAD-DINO, ViT-patch32). We propose a two-tier fair comparison framework in which both classifiers receive identical PCA-q features. At Tier 1 (untuned QSVM vs. untuned linear SVM, C = 1 both sides), QSVM wins minority-class F1 in all 18 tested configurations (17 at p < 0.001, 1 at p < 0.01). The classical linear kernel collapses to majority-class prediction on 90-100% of seeds at every qubit count, while QSVM maintains non-trivial recall. At q = 11 (MedSigLIP-448 plateau center), QSVM achieves mean F1 = 0.343 vs. classical F1 = 0.050 (F1 gain = +0.293, p < 0.001) without hyperparameter tuning. Under Tier 2 (untuned QSVM vs. C-tuned RBF SVM), QSVM wins all seven tested configurations (mean gain +0.068, max +0.112). Eigenspectrum analysis reveals quantum kernel effective rank reaches 69.80 at q = 11, far exceeding linear kernel rank, while classical collapse remains C-invariant. A full qubit sweep reveals architecture-dependent concentration onset across models. Code: https://github.com/sebasmos/qml-medimage

Related papers

Do Quantum Kernels Improve Medical Image Classification? A Leakage-Controlled Benchmark Against Classical RBF-SVM

Dr. M. Usman Hashmi, M. Adnan Hashmi, Muazzam Ali +1 more

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.

Journal of Imaging Informatics in Medicine•Sep 21, 2026•0 citations

Matched but Not Better: An Equivalence-Tested Benchmark of Quantum Machine Learning on Six Clinical Datasets and the QML-Health-READY Reporting Framework

Mohammed Siraj B, Gousia Habib, Ruban S

Background: Quantum machine learning (QML) is promoted for clinical prediction, but comparisons with classical models are rarely paired or tested for equivalence. Methods: We compared a quantum-kernel support vector machine (QSVM; 4 qubits, tuned bandwidth) and a variational quantum classifier (VQC) with five tuned classical models across six public clinical datasets. All models used identical four-component inputs and 25 cross-validation splits. Paired AUROC differences were assessed using a corrected resampled t-test, Holm-adjusted equivalence tests (margins: +/-0.02 and +/-0.05), and random-effects pooling. Ablation, noise, finite-shot, and implementation-fault analyses were conducted. We propose QML-Health-READY, an eight-domain reporting framework. Results: Neither quantum model significantly outperformed any classical comparator. Pooled across datasets, QSVM differed from the kernel-matched radial basis function (RBF) SVM by -0.006 AUROC (95% CI: -0.017 to +0.004), equivalent to +/-0.02. VQC differed from the best classical model by -0.007 (95% CI: -0.019 to +0.004). QSVM was equivalent to RBF SVM within +/-0.05 in four of six datasets but was significantly worse than the best classical model on NHANES 2017-18 (-0.076). A classically trivial product-state kernel performed as well as the entangling kernel. With depolarizing noise (p = 0.01) and 1,024 shots per kernel entry, QSVM AUROC decreased by 0.054 (95% CI: 0.036 to 0.071). Untuned bandwidth produced near-chance AUROC (0.48-0.59). Conclusions: Correctly configured quantum classifiers approached but did not exceed tuned classical models. Finite-shot estimation, rather than gate noise, was their main practical cost, while configuration errors could reverse conclusions. QML-Health-READY defines reporting requirements for credible claims.

arXiv:2611.05442•Nov 3, 2026•0 citations

Analysis of Quantum and Classical Support Vector Machines for Early-Stage Cancer Detection Using Gene Expression Data

Akshaj Goel, Karishma Desai, Shweta Loonkar

Quantum Support Vector Machines (QSVMs) are frequently reported to outperform classical kernels on high-dimensional gene expression data, but such comparisons are sensitive to how the evaluation is constructed. This study compares a fidelity-based quantum kernel against six classical baselines — linear and RBF SVMs, random forest, gradient boosting, a multilayer perceptron and logistic regression — on two public breast cancer cohorts, GSE2034 (286 samples) and GSE2990 (125 samples), each described by 22,283 probes. Every preprocessing step, including imputation, gene selection, feature scaling and class rebalancing, is fitted within the training fold of a repeated stratified five-fold cross-validation, and comparisons are tested with a corrected paired t-test that accounts for the dependence between folds. Under this protocol the quantum kernel is statistically indistinguishable from every classical baseline in all four experimental conditions: no comparison reaches significance after correction, and the largest ROC-AUC gap to the strongest baseline is 0.036 (95% CI −0.073 to 0.002). Two implementation factors are shown to dominate the outcome. First, rebalancing or scaling before the train–test split inflates apparent quantum performance, because duplicated minority samples appear on both sides of the split. Second, encoding standardised expression values directly as rotation angles causes kernel concentration, which drives QSVM ROC-AUC to chance (0.501) on GSE2034; restricting the encoding to [0, π/2] restores discriminative performance. Probes selected by a supervised within-fold filter and ranked by permutation importance under the quantum kernel recover known breast cancer markers, including CD44 on GSE2034 and MMP10 on GSE2990. We conclude that reported quantum-kernel advantages on these cohorts are attributable to evaluation protocol and encoding choices rather than to the quantum kernel itself, and we provide the diagnostic used to detect kernel concentration.

IEEE International Conference on Advances in Computing Research on Science Engineering and Technology (ACROSET)•Sep 1, 2026•0 citations

A Noiseless-Simulation Reference Baseline for ECG Arrhythmia Classification: Quantum-Kernel SVM and Variational Quantum Classifier vs. Classical Models on MIT-BIH

Seung-Hong Oh, Ji‐Young Yeo, Sungkwan Youm

This study constructs a reproducible head-to-head comparison between two intermediate-scale quantum (NISQ) classifier families and three classical baselines for binary heartbeat classification on the MIT–BIH Arrhythmia Database, evaluated as a noiseless-simulation reference. From twenty MIT–BIH records a balanced set of three hundred Normal and premature ventricular contraction (PVC) beats is extracted with six morphological features per beat. A quantum-kernel support vector machine using a ZZFeatureMap fidelity kernel, a variational quantum classifier with an EfficientSU2 ansatz, and three classical baselines (RBF support vector machine, logistic regression, random forest) are evaluated on identical splits and then improved across six improvement rounds plus a seventh audit round, which sweep the feature map and the SVM cost, average the Gram matrices of three feature-map instances that resolve to two distinct encoders, add a projected quantum kernel and multiple-kernel learning, widen the embedding to eight qubits with two derived features and light angle-space augmentation, stack quantum and classical heads, and re-run the best recipe over five seeds. On a ninety-sample held-out test set the classical baselines reach 0.989 accuracy at millisecond wall clock, while the best quantum head at the baseline configuration trails by 22.2 accuracy points. The eight-qubit augmented kernel-sum head reaches 0.911 accuracy, and a five-seed audit of the same recipe gives 0.869±0.035, so the residual gap is stable but not closed. Per-round results, resource accounting and calibration analyses are reported in the body.

IEEE Access•Jan 1, 2026•0 citations

Comparative Analysis and Noise Robustness Study of Quantum Kernel Methods and Variational Quantum Classifiers for Financial Fraud Detection

Ionuț-Cosmin Dinuț, Rodica Constantinescu, Bogdan Alexandrescu

Quantum machine learning on near-term noisy quantum devices has generated substantial theoretical interest, but rigorous empirical comparisons under realistic noise on practically relevant data remain scarce. This paper compares two paradigmatic quantum learning models, a Quantum Support Vector Machine (QSVM) built on the ZZFeatureMap quantum kernel and a Variational Quantum Classifier (VQC) with an EfficientSU2/RealAmplitudes ansatz, against tuned classical baselines (SVM with four kernels, Random Forest, XGBoost, LightGBM and CatBoost) on the ULB Credit Card Fraud dataset (284,807 transactions, 0.17% fraud). All models share an identical 4-qubit PCA-reduced feature space, evaluated on the full unbalanced test fold over 15 fits (3 folds × 5 seeds) and reported as mean ± standard deviation with bootstrap confidence intervals, AUPRC as the primary metric. Noise robustness is assessed under depolarizing noise p∈{0,0.001,0.01,0.05}, with ranking preservation measured directly through Spearman ρ and Kendall τ between the noisy and noiseless decision scores rather than read off AUPRC, alongside the per-paradigm computational cost. At four qubits the classical baselines lead (AUPRC 0.60 to 0.74, CatBoost best), above the VQC (0.494) and the QSVM (0.240); the controlled QSVM-versus-RBF–SVM comparison puts the cost of the quantum kernel at about 0.45 AUPRC. Under noise the QSVM keeps its score ranking (ρ=0.998 at p=0.001, 0.906 at p=0.01) and an operational decision threshold (recall 0.87 to 0.89, stable calibration), while the VQC AUPRC peaks non-monotonically at p=0.01 (0.494 rising to 0.654, then easing to 0.569 at p=0.05) even as its ranking decays monotonically (ρ from 0.72 to near zero), so average precision on its own misrepresents how noise affects it. The quantum models do not surpass the tuned classical reference at four qubits; the contribution is methodological: under noise, AUPRC has to be read together with a genuine rank statistic, because the two can move in opposite directions.

Electronics•Jun 5, 2026•1 citation

Classical, Quantum, and Hybrid Quantum-Classical SVMs for Binary Medical Classification

Divyanshu Ranjan, Devendra Joshi

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.

IEEE International Symposium on Sustainable Energy, Signal Processing and Cyber Security (iSSSC)•Nov 6, 2025•2 citations
We provide evidence of quantum kernel advantage under noiseless simulation in binary insurance classification on MIMIC-CXR chest radiographs using quantum support vector machines (QSVM) with frozen embeddings from three medical foundation models (MedSigLIP-448, RAD-DINO, ViT-patch32). We propose a two-tier fair comparison framework in which both classifiers receive identical PCA-q features. At Tier 1 (untuned QSVM vs. untuned linear SVM, C = 1 both sides), QSVM wins minority-class F1 in all 18 tested configurations (17 at p < 0.001, 1 at p < 0.01). The classical linear kernel collapses to majority-class prediction on 90-100% of seeds at every qubit count, while QSVM maintains non-trivial recall. At q = 11 (MedSigLIP-448 plateau center), QSVM achieves mean F1 = 0.343 vs. classical F1 = 0.050 (F1 gain = +0.293, p < 0.001) without hyperparameter tuning. Under Tier 2 (untuned QSVM vs. C-tuned RBF SVM), QSVM wins all seven tested configurations (mean gain +0.068, max +0.112). Eigenspectrum analysis reveals quantum kernel effective rank reaches 69.80 at q = 11, far exceeding linear kernel rank, while classical collapse remains C-invariant. A full qubit sweep reveals architecture-dependent concentration onset across models. Code: https://github.com/sebasmos/qml-medimage
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.
Background: Quantum machine learning (QML) is promoted for clinical prediction, but comparisons with classical models are rarely paired or tested for equivalence. Methods: We compared a quantum-kernel support vector machine (QSVM; 4 qubits, tuned bandwidth) and a variational quantum classifier (VQC) with five tuned classical models across six public clinical datasets. All models used identical four-component inputs and 25 cross-validation splits. Paired AUROC differences were assessed using a corrected resampled t-test, Holm-adjusted equivalence tests (margins: +/-0.02 and +/-0.05), and random-effects pooling. Ablation, noise, finite-shot, and implementation-fault analyses were conducted. We propose QML-Health-READY, an eight-domain reporting framework. Results: Neither quantum model significantly outperformed any classical comparator. Pooled across datasets, QSVM differed from the kernel-matched radial basis function (RBF) SVM by -0.006 AUROC (95% CI: -0.017 to +0.004), equivalent to +/-0.02. VQC differed from the best classical model by -0.007 (95% CI: -0.019 to +0.004). QSVM was equivalent to RBF SVM within +/-0.05 in four of six datasets but was significantly worse than the best classical model on NHANES 2017-18 (-0.076). A classically trivial product-state kernel performed as well as the entangling kernel. With depolarizing noise (p = 0.01) and 1,024 shots per kernel entry, QSVM AUROC decreased by 0.054 (95% CI: 0.036 to 0.071). Untuned bandwidth produced near-chance AUROC (0.48-0.59). Conclusions: Correctly configured quantum classifiers approached but did not exceed tuned classical models. Finite-shot estimation, rather than gate noise, was their main practical cost, while configuration errors could reverse conclusions. QML-Health-READY defines reporting requirements for credible claims.
Quantum Support Vector Machines (QSVMs) are frequently reported to outperform classical kernels on high-dimensional gene expression data, but such comparisons are sensitive to how the evaluation is constructed. This study compares a fidelity-based quantum kernel against six classical baselines — linear and RBF SVMs, random forest, gradient boosting, a multilayer perceptron and logistic regression — on two public breast cancer cohorts, GSE2034 (286 samples) and GSE2990 (125 samples), each described by 22,283 probes. Every preprocessing step, including imputation, gene selection, feature scaling and class rebalancing, is fitted within the training fold of a repeated stratified five-fold cross-validation, and comparisons are tested with a corrected paired t-test that accounts for the dependence between folds. Under this protocol the quantum kernel is statistically indistinguishable from every classical baseline in all four experimental conditions: no comparison reaches significance after correction, and the largest ROC-AUC gap to the strongest baseline is 0.036 (95% CI −0.073 to 0.002). Two implementation factors are shown to dominate the outcome. First, rebalancing or scaling before the train–test split inflates apparent quantum performance, because duplicated minority samples appear on both sides of the split. Second, encoding standardised expression values directly as rotation angles causes kernel concentration, which drives QSVM ROC-AUC to chance (0.501) on GSE2034; restricting the encoding to [0, π/2] restores discriminative performance. Probes selected by a supervised within-fold filter and ranked by permutation importance under the quantum kernel recover known breast cancer markers, including CD44 on GSE2034 and MMP10 on GSE2990. We conclude that reported quantum-kernel advantages on these cohorts are attributable to evaluation protocol and encoding choices rather than to the quantum kernel itself, and we provide the diagnostic used to detect kernel concentration.
This study constructs a reproducible head-to-head comparison between two intermediate-scale quantum (NISQ) classifier families and three classical baselines for binary heartbeat classification on the MIT–BIH Arrhythmia Database, evaluated as a noiseless-simulation reference. From twenty MIT–BIH records a balanced set of three hundred Normal and premature ventricular contraction (PVC) beats is extracted with six morphological features per beat. A quantum-kernel support vector machine using a ZZFeatureMap fidelity kernel, a variational quantum classifier with an EfficientSU2 ansatz, and three classical baselines (RBF support vector machine, logistic regression, random forest) are evaluated on identical splits and then improved across six improvement rounds plus a seventh audit round, which sweep the feature map and the SVM cost, average the Gram matrices of three feature-map instances that resolve to two distinct encoders, add a projected quantum kernel and multiple-kernel learning, widen the embedding to eight qubits with two derived features and light angle-space augmentation, stack quantum and classical heads, and re-run the best recipe over five seeds. On a ninety-sample held-out test set the classical baselines reach 0.989 accuracy at millisecond wall clock, while the best quantum head at the baseline configuration trails by 22.2 accuracy points. The eight-qubit augmented kernel-sum head reaches 0.911 accuracy, and a five-seed audit of the same recipe gives 0.869±0.035, so the residual gap is stable but not closed. Per-round results, resource accounting and calibration analyses are reported in the body.
Quantum machine learning on near-term noisy quantum devices has generated substantial theoretical interest, but rigorous empirical comparisons under realistic noise on practically relevant data remain scarce. This paper compares two paradigmatic quantum learning models, a Quantum Support Vector Machine (QSVM) built on the ZZFeatureMap quantum kernel and a Variational Quantum Classifier (VQC) with an EfficientSU2/RealAmplitudes ansatz, against tuned classical baselines (SVM with four kernels, Random Forest, XGBoost, LightGBM and CatBoost) on the ULB Credit Card Fraud dataset (284,807 transactions, 0.17% fraud). All models share an identical 4-qubit PCA-reduced feature space, evaluated on the full unbalanced test fold over 15 fits (3 folds × 5 seeds) and reported as mean ± standard deviation with bootstrap confidence intervals, AUPRC as the primary metric. Noise robustness is assessed under depolarizing noise p∈{0,0.001,0.01,0.05}, with ranking preservation measured directly through Spearman ρ and Kendall τ between the noisy and noiseless decision scores rather than read off AUPRC, alongside the per-paradigm computational cost. At four qubits the classical baselines lead (AUPRC 0.60 to 0.74, CatBoost best), above the VQC (0.494) and the QSVM (0.240); the controlled QSVM-versus-RBF–SVM comparison puts the cost of the quantum kernel at about 0.45 AUPRC. Under noise the QSVM keeps its score ranking (ρ=0.998 at p=0.001, 0.906 at p=0.01) and an operational decision threshold (recall 0.87 to 0.89, stable calibration), while the VQC AUPRC peaks non-monotonically at p=0.01 (0.494 rising to 0.654, then easing to 0.569 at p=0.05) even as its ranking decays monotonically (ρ from 0.72 to near zero), so average precision on its own misrepresents how noise affects it. The quantum models do not surpass the tuned classical reference at four qubits; the contribution is methodological: under noise, AUPRC has to be read together with a genuine rank statistic, because the two can move in opposite directions.
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.