Abstract Hybrid quantum–classical architectures offer a promising direction for sequence modeling, yet their empirical behavior on realistic bioinformatics tasks remains insufficiently documented. Here, we present a fully simulated, reproducible benchmark for hybrid quantum machine learning applied to synthetic DNA disease-risk classification. A dataset of 5,000 sequences (200 bp) across five balanced classes was generated using motif-injection rules with controlled noise, from which 74 biological features were extracted. Baseline models (CNN, attention, classical ensemble) were compared against two quantum-hybrid models incorporating a 4-qubit ZZFeatureMap + RealAmplitudes ansatz, executed exclusively on Qiskit Aer Simulator with 1,024 shots. The attention model achieved the highest test accuracy (51.7%), while quantum-hybrid models produced comparable performance (51.1–51.3%), showing no measurable quantum advantage under these settings. The study establishes an honest, fully reproducible baseline for QML in genomics, highlighting current limitations of small-qubit encodings and motivating future work with trainable variational circuits and larger biological datasets.
Abstract Hybrid quantum–classical architectures offer a promising direction for sequence modeling, yet their empirical behavior on realistic bioinformatics tasks remains insufficiently documented. Here, we present a fully simulated, reproducible benchmark for hybrid quantum machine learning applied to synthetic DNA disease-risk classification. A dataset of 5,000 sequences (200 bp) across five balanced classes was generated using motif-injection rules with controlled noise, from which 74 biological features were extracted. Baseline models (CNN, attention, classical ensemble) were compared against two quantum-hybrid models incorporating a 4-qubit ZZFeatureMap + RealAmplitudes ansatz, executed exclusively on Qiskit Aer Simulator with 1,024 shots. The attention model achieved the highest test accuracy (51.7%), while quantum-hybrid models produced comparable performance (51.1–51.3%), showing no measurable quantum advantage under these settings. The study establishes an honest, fully reproducible baseline for QML in genomics, highlighting current limitations of small-qubit encodings and motivating future work with trainable variational circuits and larger biological datasets.
Abstract Hybrid quantum–classical architectures offer a promising direction for sequence modeling, yet their empirical behavior on realistic bioinformatics tasks remains insufficiently documented. Here, we present a fully simulated, reproducible benchmark for hybrid quantum machine learning applied to synthetic DNA disease-risk classification. A dataset of 5,000 sequences (200 bp) across five balanced classes was generated using motif-injection rules with controlled noise, from which 74 biological features were extracted. Baseline models (CNN, attention, classical ensemble) were compared against two quantum-hybrid models incorporating a 4-qubit ZZFeatureMap + RealAmplitudes ansatz, executed exclusively on Qiskit Aer Simulator with 1,024 shots. The attention model achieved the highest test accuracy (51.7%), while quantum-hybrid models produced comparable performance (51.1–51.3%), showing no measurable quantum advantage under these settings. The study establishes an honest, fully reproducible baseline for QML in genomics, highlighting current limitations of small-qubit encodings and motivating future work with trainable variational circuits and larger biological datasets.
This paper presents a systematic empirical benchmarking of quantum machine learning (QML) applications within the under-explored domain of agricultural image classification. The authors implement and evaluate four hybrid quantum-classical architectures—including variational quantum classifiers (VQC), quanvolutional neural networks (QNN), and a ResNet-50 combined with a Quantum Support Vector Machine (QSVM)—against a purely classical EfficientNet baseline. The architectures are tested on three agricultural disease datasets: potato tuber disease, jujube insect pests, and paddy leaf rust. The experimental findings reveal that the ResNet-50+QSVM hybrid model achieves the optimal balance of classification accuracy and training stability, reaching a 93.4% mean accuracy. Crucially, the hybrid QSVM demonstrates extreme sample efficiency by requiring 41% fewer labeled training samples than the classical EfficientNet baseline to cross a 90% accuracy threshold, showing the capability of quantum feature maps in low-data regimes.
Quantum Machine Learning (QML) has emerged as a promising paradigm that combines principles of quantum computation with classical learning techniques to address challenges posed by complex, high-dimensional, and non-linear datasets. This work presents a systematic experimental study of quantum-enhanced classification and clustering using hybrid quantum–classical models evaluated on synthetically generated datasets. Quantum Support Vector Machines (QSVM) and Variational Quantum Classifiers (VQC) are implemented using the Qiskit framework and benchmarked against established classical algorithms. The synthetic datasets are carefully designed to control linearity, dimensionality, class overlap, and nonlinear structure, enabling a detailed performance comparison under both ideal and noisy simulation conditions. The experimental results indicate that quantum feature representations can enhance class separability in non-linear scenarios, while also highlighting the practical limitations imposed by noise sensitivity and circuit depth constraints inherent to Noisy Intermediate-Scale Quantum (NISQ) devices .
Purpose This study investigates the integration of quantum-enhanced machine learning (QML) into medical image analysis, focusing on classification and feature extraction tasks. It aims to evaluate whether hybrid quantum-classical models can overcome the limitations of traditional machine learning in handling high-dimensional, clinically relevant imaging data. Design/methodology/approach Hybrid architectures combining classical preprocessing with quantum components, specifically variational quantum circuits (VQCs) and quantum kernel methods, were developed and implemented in simulated quantum environments using Qiskit and PennyLane on Google Colab. Publicly available datasets (ChestX-ray14, Brain Tumor MRI and CT Hemorrhage) were preprocessed and encoded into quantum states. Model performance was evaluated against classical baselines (MLP and CNN) using accuracy, precision, recall, F1-score, convergence speed and trainable parameters. Findings Quantum-enhanced models achieved competitive or superior performance compared to classical models with significantly fewer trainable parameters and faster convergence. The Quantum Kernel SVM demonstrated the highest precision (89.1%) and F1-score (88.5%) using only 8 parameters, while VQC models converged up to 2× faster than classical baselines. These results highlight the potential of QML to improve efficiency, robustness and scalability in diagnostic imaging workflows, particularly in resource-constrained or data-limited settings. Research limitations/implications The study relies on simulated quantum environments, which do not capture hardware noise or qubit limitations. Future work will extend to real quantum devices, multimodal data integration and interpretability strategies. Practical implications Quantum kernel methods and lightweight VQC architectures enable faster, resource-efficient diagnostic modeling, making them suitable for clinical environments with limited computational capacity or time-sensitive decision-making needs. Social implications Improving the efficiency and accessibility of medical image analysis has the potential to support faster diagnosis and enhance healthcare delivery, particularly in underserved or resource-limited regions. Originality/value This study provides a practical evaluation of hybrid quantum-classical models applied to multiple real medical imaging datasets in a reproducible simulated environment. It offers an early-stage framework demonstrating how QML techniques can be integrated into existing machine learning pipelines for medical image analysis.
Quantum machine learning (QML) presents a promising avenue for addressing complex classification challenges, yet its application in medical imaging remains largely unexplored. This work introduces a hybrid quantum classical framework designed to classify skin diseases—Chickenpox, Measles, Monkeypox, and Normal—using a 4 qubit quantum system. The framework integrates a Quantum Convolutional Neural Network (QCNN) for feature extraction and a Variational Quantum Classifier (VQC) for classification, processing a dataset of 770 images with significant class imbalance. To address this imbalance, we employ a class weighted loss function with weightswyi= [3.0, 3.5, 0.6, 0.4], ensuring balanced representation across all classes. The model is optimized using Simultaneous Perturbation Stochastic Approximation (SPSA) over 150 iterations, achieving a test accuracy of 70.13% on a subset of 154 images, which represents 20% of the dataset. This marks a substantial improvement over both a random baseline of 25% and a prior run that achieved 37.66% accuracy, which was skewed toward the majority class. Principal Component Analysis (PCA) reduces image features to a 4 dimensional representation, enabling compatibility with the quantum system. The QCNN extracts these features, while the VQC performs classification based on measurements from 1024 shots on the QASM simulator. To ensure practical reusability, the trained model—including quantum circuits, optimized parameters, and PCA transformations—is saved for future deployment. Validation on a separate set of 24 samples (6 per class) yields 70.83% accuracy (17 out of 24 correct predictions), demonstrating the model’s generalization capabilities. While the performance falls short of classical benchmarks, this study establishes the feasibility of QML with minimal qubits, paving the way for quantum driven diagnostics in resource constrained environments.
Near-term quantum machine learning (QML) models operate in environments wherein noise is unavoidable, arising from both imperfect classical data acquisition and the limitations of noisy intermediate-scale quantum (NISQ) hardware. Although most existing studies have focused primarily on quantum circuit noise in isolation, the combined influence of corrupted classical inputs and quantum hardware noise has received comparatively little attention.
In this work, we present a systematic experimental study of the robustness of a variational quantum classifier under realistic multi-level noise conditions. Using the Titanic dataset as a benchmark, a range of dataset-level noise models-including speckle noise, impulse noise, quantization noise, and feature dropout are applied to classical features prior to quantum encoding using a ZZ feature map. In parallel, hardware-inspired quantum noise channels such as depolarizing noise, amplitude damping, phase damping, Pauli errors, and readout errors are incorporated at the circuit level using the Qiskit Aer simulator.
The experimental results indicate that noise in classical input data can significantly intensify the effects of quantum decoherence, resulting in less stable training and noticeably lower classification accuracy. Together, these observations emphasize the importance of designing and evaluating quantum machine learning pipelines with noise in mind, and highlight the need to consider classical and quantum noise simultaneously when assessing QML performance in the NISQ era