The brain disorder known as Alzheimer’s disease (AD) impacts millions of people globally. Accurate and early detection of this condition is of the utmost importance for improving patient outcomes through prompt medical management. Here, we propose a novel approach to searching magnetic resonance images of the brain for signs of Alzheimer’s disease. The primary objective of this research is to develop a trustworthy method for early Alzheimer’s disease detection using magnetic resonance imaging (MRI) of the brain. Faster intervention and better patient care are made possible by the proposed methodology’s use of machine learning algorithms to increase diagnosis accuracy. The dataset, which was donated by Kaggle, consisted of 2179 brain MR images, providing a comprehensive and diverse set for study. To forecast the onset of Alzheimer’s disease, an ensemble machine learning approach is employed, combining many classifiers like decision tree, linear support vector machine, k-NN, and Gaussian support vector machine. In the end, the ensemble that best fits the brain MR pictures is decided by a simple majority vote. With a precision of $\mathbf{9 9. 3 \%}$, the results of this study show tremendous potential for enhancing the diagnosis and treatment of Alzheimer’s disease. Better outcomes for patients and healthcare efficiency are contributed to by the elapsed time of 0.257534 seconds.
Brain Image Analysis for Alzheimer’s Disease Detection using Ensemble Machine Learning
06.11.2024
637669 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch