Employing Machine Learning Algorithms for the Prediction of Alzhiemer’s Disease

Alzheimer's disease is a neurological condition that progressively worsens over time and impairs thinking, memory, social skills, and behavior. Its onset is most commonly seen in the age groups above 65. The World Health Organization's survey indicates that dementia, including AD, is the sixth largest cause of death globally. For older people, this is the most frequent cause of dementia. The word dementia is used to refer to a wide range of brain disorders that are characterized by behavioural abnormalities, loss of memory and reasoning skills, and difficulty carrying out everyday tasks. In order to lower the death rate, early screening for this condition is essential. Machine learning techniques are quite useful in the identification of the relation between risk factors of Alzheimer’s disease and its incidence. This study examines the relationship between several characteristics that lower the risk of Alzheimer's disease using a benchmarking dataset of 2149 Americans. Early detection of AD and associated symptoms is more successful when classifiers such as Random Forest, Support Vector Machine, K-Nearest Neighbours, XGBoost, CatBoost, and Logistic Regression are used. Classifier performance and AD predictions are evaluated using metrics like as F1-score, Precision, Accuracy, and Recall. According to this suggested study, the Random Forest and CatBoost algorithm predicts the test data with 95.5% accuracy. This score is better than the other modern and latest algorithms.