Alzheimer's disease occurs due to neurodegenerative disorder, innovative approach is needed for early detection of disease. A method combining multimodal data fusion with adaptive capabilities of Adam optimization algorithm to enhance Alzheimer's disease prediction have been proposed. The proposed multimodal fusion approach combines neuroimaging, clinical, and genetic data into a deep neural network architecture, in order to achieve better accuracy,. Utilization of multimodal data helps to capture the view of disease, from structural brain changes to clinical assessments. This approach not only enhances predictive accuracy but also provides valuable insights into the mechanisms of Alzheimer's disease prediction. Utilization of Adam's optimization algorithm helps the model to converge faster making the proposed method highly effective. Combining the strengths of multimodal fusion and Adam optimization, the proposed method can be utilized for early Alzheimer's disease diagnosis, leading to improved patient outcomes and improved accuracy in Alzheimer's disease prediction.