International Journal of Medical Discoveries

Alzheimer’s disease is a progressive neurodegenerative disease, which has implications for the health of people and is the key to targeted treatment. Interventions are the timely detection of the potential risk factors at the population level. The paper utilized big data analytics for self-reported BFRSS data for evaluating cognitive decline predictors in Alzheimer’s disease. Software such as Apache was used to implement machine learning models, such as linear for scaling processed data. These include the regression, random forest, and clustering for identifying the higher-risk groups. The random Forest model displayed moderate predictive power (R 2 = 0.4697, RMSE = 17.35), outperforming Linear Regression. Clustering resulted in the identification of populations with mental health burden and geographic differences. Results emphasize the importance of mental health, socioeconomic status, and regional differences as risk factors for Alzheimer. Big data frameworks for population health analytics and supports targeted public health interventions.