Fusion-aware quantum variational autoencoder for brain-heart signal modeling in mental health applications

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.