Abstract: Alzheimer's disease is a neurodegenerative disorder marked by the gradual decline of cerebral function, affecting memory, cognitive abilities, thought processes, and learning capacity.  The main catalyst for our research on Alzheimer's disease originates from statistical data released by Alzheimer's Disease International, which forecasts that 78 million individuals will be affected by it by 2030, with projections escalating to 139 million by 2050.  This alarming statistic demands prompt intervention and early diagnosis. Classical techniques are available for early diagnosis and AI-driven forecasting.  However, they require a considerable amount of high-quality data, pose risks of overfitting, entail high computational costs, complicate interpretability due to their black box nature, and demand domain expertise, among other considerations. The utilisation of quantum machine learning techniques using hybrid prediction frameworks is highly beneficial. We propose Quan-AlzhCare model, a hybrid quantum-classical framework for the early detection and prediction of Alzheimer's disease, employing a quantum generative adversarial network (QGAN) and a quantum neural network (QNN). Our analysis employing the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset was performed using quantum hardware, specifically IonQ provided by Amazon Web Services (AWS) Braket, resulting in improved performance through the transition from classical to quantum computational methods.

Keywords: Alzheimer’s disease, QGAN, Hybrid Quantum-Classical framework, QNN, ADNI, Prediction