Abstract: Alzheimer's disease, a prevalent form of dementia, progressively impairs cognition, behavior, and memory, affecting daily functioning due to structural brain changes. While it constitutes a substantial majority of dementia cases, other treatable conditions, such as thyroid issues and vitamin deficiencies, can manifest similar symptoms. This paper presents a machine learning system that employs logistic regression and support vector machines to develop a predictive model for early Alzheimer's disease detection. Using diverse datasets, the model's effectiveness is evaluated using accuracy, sensitivity, and specificity as performance metrics.
The project aims to contribute to early detection, enabling timely interventions and improving affected individuals' quality of life. Moreover, the findings may provide insights into Alzheimer's disease mechanisms, facilitating targeted treatments. By emphasizing the significance of diverse datasets and advanced machine learning techniques, this research seeks to enhance Alzheimer's disease understanding and detection, ultimately leading to improved healthcare outcomes.
Keywords: Alzheimer's disease, machine learning, support vector, logistic regression.
|
DOI:
10.17148/IARJSET.2023.10788