Review on Quantum AI-Based Parkinson’s Disease Diagnosis Optimiser

Quantum AI optimisers for Parkinson’s disease diagnosis are an active research area. The eight studies reviewed here show progress in accuracy, feature selection, and in some cases interpretability when quantum or hybrid layers complement classical deep learning. Voice and gait remain the most accessible biomarkers; multimodal fusion offers the highest ceiling if data collection can be standardised. No reviewed system is ready for unsupervised clinical deployment. Noise on current quantum hardware, hospital IT integration, and ethics of recording vulnerable patients need further work. With patient-independent validation and neurologist-led pilots, quantum-enhanced screening could support earlier PD care without replacing expert clinical judgement.

[1]  P. G. Arepalli, K. Maneesha, M. Srija, and T. Likhitha, "A Novel Technique in Early Parkinson's Disease Diagnosis using Quantum LSTM Model," in Proc. ICICNIS, IEEE, 2024. [2]  S. R. Swarna, A. Kumar, and P. Dixit, "Hybrid Quantum-Classical AI Framework for Parkinson's Disease Prediction," in Proc. IEMECON, IEEE, 2025. [3]   S. Alden Jenish et al., "A Quantum-Classical Dual-Track Deep Learning Network for Explainable Parkinson's Disease Classification," Front. Artif. Intell., vol. 9, Art. 1807209, 2026. [4] D. Vatsavai, A. Iyer, and A. A. Nair, "A Quantum-Inspired Machine Learning Approach for Multimodal Parkinson's Disease Screening," Sci. Rep., vol. 15, no. 1, 2025. [5]  R. F. Mansour, "QMFOFS-HCNN: Quantum Mayfly Optimization with Hybrid CNN for PD Detection," Neural Comput. Appl., 2024. [6] S. K. Batra et al., "Quantum Neural Network for Early PD Detection using Voice Signals," in Proc. ICCCIS, IEEE, 2023. [7]  M. Hashmi et al., "Quantum Machine Learning for PD Detection from Gait Analysis," in Proc. IEEE BIBM, IEEE, 2024. [8]  R. Kumar et al., "Hybrid Quantum-Classical Deep Learning Model for PD Diagnosis," Expert Syst. Appl., vol. 210, Art. 118432, 2025.