Key points are not available for this paper at this time.
Alzheimer's disease (AD) is a neurodegenerative disorder that is commonly seen in old age people. It causes memory loss and affects the cognitive function, which makes it difficult for a person with AD to do simple tasks. Detecting AD at an early stage can help in slowing down the progression of the disease by taking appropriate medication. Traditionally AD diagnosis is done using cognitive testing, but these tests are ineffective for testing at early stages of AD. Advancements in technology has allowed for early detection of AD, with the help of artificial intelligence. Machine learning (ML) models are developed and trained which are used for classifying the severity of AD. In this paper magnetic resonance imaging (MRI) of brain is used as dataset. ML model is trained and tested against different dataset in Jupyter notebook platform. The performance of the model against different datasets are compared, the evaluation metrics used for the comparison are accuracy, precision, F1-score and recall. Experiments have yielded promising results to improve the accuracy of AD detection which help many doctors in providing proper treatment for AD based on the severity of AD.
Aravind et al. (Fri,) studied this question.