Quantum machine learning (QML) is an emerging research area focused on enhancing the diagnostic accuracy and interpretability of biomedical signals. In this study, we propose a Quantum Variational Autoencoder (QVAE) framework for EEG-ECG-based mental health diagnostics, integrating quantum amplitude encoding, entanglement-driven latent space transformation, and a hybrid quantum-classical attention mechanism. The proposed QVAE model leverages quantum computational techniques to enhance classification performance, signal reconstruction, and latent feature interpretability. We introduce a quantum Wasserstein-Fisher Hybrid Loss Function, which integrates Quantum Wasserstein Distance (QWD) and Quantum Fisher Information (QFI) for multimodal physiological data. Through extensive experimentation on EEG and ECG datasets from Brainwave and PhysioNet repositories, the proposed model achieved a classification accuracy of 97.8% and an error of 0.007, significantly outperforming baseline CNNs, classical variational autocoders, and classical variationals. Importantly, extensive simulations on IBM Qiskit and PennyLane quantum simulators demonstrate the feasibility of the proposed framework on quantum simulators, supporting its potential for deployment on near-term quantum hardware. This study contributes to quantum machine learning for healthcare by achieving high diagnostic accuracy and robust signal reconstruction, demonstrating its suitability for immediate clinical translation into quantum-enhanced EEG diagnostics.
Quantum machine learning (QML) is an emerging research area focused on enhancing the diagnostic accuracy and interpretability of biomedical signals. In this study, we propose a Quantum Variational Autoencoder (QVAE) framework for EEG-ECG-based mental health diagnostics, integrating quantum amplitude encoding, entanglement-driven latent space transformation, and a hybrid quantum-classical attention mechanism. The proposed QVAE model leverages quantum computational techniques to enhance classification performance, signal reconstruction, and latent feature interpretability. We introduce a quantum Wasserstein-Fisher Hybrid Loss Function, which integrates Quantum Wasserstein Distance (QWD) and Quantum Fisher Information (QFI) for multimodal physiological data. Through extensive experimentation on EEG and ECG datasets from Brainwave and PhysioNet repositories, the proposed model achieved a classification accuracy of 97.8% and an error of 0.007, significantly outperforming baseline CNNs, classical variational autocoders, and classical variationals. Importantly, extensive simulations on IBM Qiskit and PennyLane quantum simulators demonstrate the feasibility of the proposed framework on quantum simulators, supporting its potential for deployment on near-term quantum hardware. This study contributes to quantum machine learning for healthcare by achieving high diagnostic accuracy and robust signal reconstruction, demonstrating its suitability for immediate clinical translation into quantum-enhanced EEG diagnostics.
Automated epileptic seizure detection from electroencephalogram (EEG) recordings remains a challenging biomedical signal analysis task because of the nonlinear, non-stationary, and high-dimensional characteristics of neural activity. Although deep learning has substantially improved automated seizure classification, conventional architectures may exhibit limited capability in modeling complex latent feature interactions while maintaining computational efficiency in biomedical applications. This study presents an entanglement-driven hybrid quantum–classical representation learning framework that integrates Continuous Wavelet Transform (CWT)-based time–frequency analysis, EfficientNet-B0 feature extraction, quantum-compatible latent feature compression, angle-based quantum state encoding, and a customized four-qubit Variational Quantum Convolutional Neural Network (QCNN) for EEG seizure classification. The proposed shallow variational quantum architecture is designed to facilitate expressive quantum feature learning while remaining compatible with the computational constraints of near-term noisy intermediate-scale quantum (NISQ) systems. An experimental evaluation was conducted on a balanced subset of 4,000 EEG segments from the UCI Epileptic Seizure Recognition Dataset. Stratified five-fold cross-validation achieved a mean classification accuracy of 97.80% ± 1.50%, demonstrating consistent predictive performance and generalization across several data partitions. Furthermore, evaluation on an independent held-out test set yielded 99.50% accuracy, 99.03% precision, 100.00% recall, 99.51% F1-score, and an area under the ROC curve (AUC) of 1.000. To comprehensively assess the proposed framework, additional investigations, including quantum circuit expressibility, barren plateau analysis, optimization trainability, latent feature-space separability, robustness evaluation, computational scalability, and patch-level quantum attention visualization, were performed, offering complementary evidence regarding representation quality, optimization stability, and model interpretability. Although the proposed framework is currently validated using classical quantum simulation, the results demonstrate the feasibility of hybrid quantum–classical representation learning for intelligent EEG seizure analysis and establish a foundation for future deployment on emerging quantum-computing platforms.
Brain imaging is a critical tool in mental health diagnostics, particularly for detecting anomalies associated with behavioral disorders, anxiety, depression, and neuropsychiatric conditions. Traditional deep learning approaches, such as Convolutional Neural Networks (CNNs), have shown promise in analyzing functional Magnetic Resonance Imaging (fMRI), but they often suffer from computational limitations, feature extraction inefficiencies, and generalization issues. Quantum Machine Learning (QML) offers a transformative solution by enhancing feature representation, improving classification accuracy, and exploiting the power of quantum computation for large-scale medical imaging datasets. In this paper, we explored the potential of quantum models for detecting anomalies in brain imaging. Using the UCLA Consortium for Neuropsychiatric Phenomics dataset, we compared quantum models, including the Variational Quantum Classifier (VQC), Quantum Convolutional Neural Network (QCNN), and Quantum Support Vector Machine (QSVM), with classical models like CNNs and the Support Vector Machine (SVM). Our results revealed that QSVM and VQC outperformed classical models, both achieving 92% accuracy and perfect recall (100%), making them highly effective at identifying positive cases-a critical requirement in clinical diagnostics. QCNN, while less accurate at 74%, still showed strong precision (90%) and an F1score of 85%, highlighting its potential where avoiding false positives is key. Classical models, in comparison, performed moderately well: SVM reached 87% accuracy and CNN achieved 83%, but both had lower precision and F 1 -scores, suggesting less consistent performance. These findings suggest that quantum models, especially VQC and QSVM, offer a promising advantage in neuroimaging-based mental health diagnostics.
With the growing interest in hybrid quantumclassical intelligence, Quantum Machine Learning (QML) offers a new frontier for learning complex, highdimensional data like EEG signals. Most current QML methodologies, however, are plagued by instability against noisy quantum states, low fidelity, and poor feature encoding mechanisms. To overcome these drawbacks, this study introduces a new framework named “Enhancing Quantum Machine Learning Models with Error-Tolerant Superposition-Based Feature Extraction and State Fidelity Boosting”. The approach combines angle-based quantum superposition embedding with fidelity-based quantum autoencoder for retaining the integrity of quantum states during training. Classification is performed using a Variational Quantum Circuit (VQC) with fidelity loss minimization included in training to eliminate decoherence effects. The model is deployed with Pennylane and Qiskit on Python, and tested on a publicly shared EEG dataset from Kaggle on emotion classification. The model has a classification accuracy of 93.5%, a 4.3% increase compared to the bestperforming current QML method. The fidelity score was also enhanced to 0.95, which ensures that robust state is well-preserved. The work unfolds tremendous potential to employ QML in actual bio-signal applications. The fidelity-aware filtering and superposition encoding pipeline of the proposed method can be trivially generalized to other high-noise, high-dimensional quantum learning problems.
The rapid expansion of clinical data in modern healthcare requires analytical systems capable of uncovering intricate patterns and supporting accurate diagnostic decisions. Quantum machine learning (QML) offers significant potential for modeling higher-order feature interactions and accelerating computation beyond classical approaches. This paper introduces an improved hybrid architecture that fuses an inception-based attentional VGG (IAV) network with a quantum variational classifier (QVC) constructed using parameterized quantum circuits (PQCs). The framework begins with min-max normalization to stabilize heterogeneous clinical attributes and enhance training convergence. Deep discriminative features are then extracted through the IAV model, followed by quantum-driven classification using variational layers optimized by classical routines. The MIMIC-III clinical dataset is employed to validate the proposed system on large-scale healthcare records. Performance is measured using accuracy, precision, recall, and F1-score. The enhanced hybrid model achieves 97.28% accuracy, 97.16% precision, 96.65% recall, and a 97.38% F1-score, surpassing established methods including support vector machine (SVM) (89.23%), quantum support vector machine (QSVM) (90.13%), and QVKSVM (97.34%). The findings confirm that integrating deep learning with quantum variational optimization strengthens scalability, reduces computational overhead, and establishes a powerful foundation for next-generation healthcare analytics.
Multi-omics integration has become a cornerstone of personalized medicine, enabling researchers to connect genomic, transcriptomic, proteomic, metabolomic, and epigenomic data to reveal complex biological mechanisms and individualized disease signatures. However, the extreme dimensionality, heterogeneity, and nonlinear interactions across omics layers challenge even the most advanced classical machine learning methods. Quantum Machine Learning (QML) offers a powerful alternative by exploiting quantum superposition, entanglement, and high-dimensional feature embeddings to model multi-omics interactions more efficiently. This study proposes a hybrid quantum–classical framework that combines quantum kernel estimation, variational quantum classifiers, and quantum-enhanced feature fusion networks to generate integrative biological signatures for precision diagnostics. Simulation results using benchmark multi-omics datasets demonstrate improved classification accuracy, enhanced sensitivity to weak biological signals, and reduced computational overhead compared to classical baselines. These findings highlight the potential of QML to accelerate multi-omics insights and pave the way toward truly personalized, predictive healthcare.
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.