Big Data-Machine Learning Processing of Recorded Radiofrequency Physiological and Pathological Measurements to Predict the Progression of Alzheimer’s Disease

Alzheimer’s disease is expected to be the largest growing disease around the world with the increase in the ageing population. It affects the livelihood of not just patients, but those who take care of them. Currently, MRI and PET scans are used to monitor its progression. However, these systems are inconvenient for patients to use. There is a need for more intelligent and efficient methods to predict the current stage of the disease along with strategies on how to slow down its progress over time. In this paper, RF measurements were obtained from previous studies which looked at physiological and pathological changes in the brain due to Alzheimer’s disease. Big data techniques were implemented to scale the dataset to simulate measurements for 100 patients. Data was then processed in several machine learning algorithms in order to validate how well each algorithm could classify the stage of Alzheimer’s disease. Results showed that classical machine learning algorithms were accurate in classifying the different stages of Alzheimer’s disease using the combined RF dataset.