Quantum-Enhanced Neuromorphic Framework for Early Detection of Wilson's Disease Using SNN-QSVM Hybrid Modeling
S. Priyanga, G. Nithila, S. Baghavathi Priya +1 more
Neurological disorders often cause progressive cognitive and motor impairments, with autosomal recessive diseases presenting diagnostic challenges due to overlapping symptoms and gradual onset. Wilson's Disease (WD), caused by ATP7B gene mutations, leads to toxic copper accumulation in the liver and brain, resulting in hepatic, neurological, and psychiatric dysfunction. Conventional diagnostic methods, such as serum ceruloplasmin tests, copper assays, and liver biopsies, are invasive and inconsistent in early detection. To address these limitations, this work proposes a hybrid Spiking Neural Network–Quantum Support Vector Machine (SNN-QSVM) framework for WD classification. The model uses neuromorphic learning and quantum-enhanced classification on demographic, clinical, symptomatic, genetic, and lifestyle features from a 60,000-sample dataset. Evaluated using accuracy, precision, recall, F1-score, and AUC-ROC, the framework achieved 94% accuracy, demonstrating strong diagnostic capability. Future work includes multimodal clinical integration and scalable quantum deployment.
Advances in computational intelligence and robotics book series•Jun 24, 2026•0 citations