Machine Learning Models for Alzheimer’s Disease Detection Using OASIS Data

Early Prediction of Alzheimer’s disease is a challenging task for researchers to contribute. Dementia is the simplest symptom of Alzheimer’s disease. Nowadays, most researchers apply Artificial Intelligence to discover mental disorders like Alzheimer’s, which mostly affect the old age population worldwide. In Alzheimer's disease, the brain is under neurodegenerative changes. As our population ages, more people will be affected by diseases that impact memory functionalities. These repercussions will profoundly affect the person’s social and financial fronts. It is difficult to predict Alzheimer's disease in its early stages. The Medication given early in Alzheimer's disease is more effective and has fewer minor side effects than treatment given later. To find the optimum parameters for Alzheimer's disease prediction, researchers used a variety of algorithms, including Decision Trees, Random Forests, Support Vector Machines, Gradient Boosting, and Voting classifiers. Predictions of Alzheimer's disease are based on data from the Open Access Series of Imaging Studies (OASIS). The performance of machine learning models is tested using measures such as Precision, Recall, Accuracy, and F1-score. Clinicians can use the proposed classification approach to make diagnoses of these disorders. With these ML algorithms, it is extremely beneficial to reduce annual Alzheimer's disease death rates in early diagnosis. On the test data of Alzheimer’s disease, the proposed work demonstrates better results, with the best validation average accuracy of 80%.