• KM. SHVETA YADAV

Abstract: Alzheimer's is an irreversible brain illness that causes thinking and memory problems, a shrinking of the total mind, and ultimately leads to death. The development of more effective treatments for AD depends on early detection. Artificial intelligence's machine learning (ML) field uses a range of probabilistic and optimisation methods that enable PCs to benefit from large and intricate datasets. Consequently, scientists concentrate on applying machine learning often to diagnose AD in its early phases. This study reviews, analyses, and critically assesses recent research on the use of ML approaches for early AD identification. Although a number of approaches demonstrated encouraging prediction accuracy, it was challenging to conduct a fair comparison between them because they were assessed on various pathologically untested data sets from various imaging modalities. Additionally, a lot of other elements including pre-processing, the quantity of significant characteristics for feature selection and class imbalance have a noticeable impact on how well the prediction is assessed. In order to get over these restrictions, a model is put forth that consists of an initial pre-processing stage, imperative attribute selection, and association rule mining for classification. Additionally, this suggested model-based method has the ability to differentiate AD from healthy controls and points research in the correct direction for early AD diagnosis.

Keywords: Alzheimer’s Disease, Machine Learning, Computer Aided Diagnosis, Pathologically Proven Data, Early Diagnosis, Class Imbalance.

""Machine Learning Advancements and Challenges in Early Alzheimer’s Disease Diagnosis: A Comprehensive Review"", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 3, page no.a184-a190, March-2024, Available :http://www.jetir.org/papers/JETIR2403025.pdf

""Machine Learning Advancements and Challenges in Early Alzheimer’s Disease Diagnosis: A Comprehensive Review"", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 3, page no. ppa184-a190, March-2024, Available at : http://www.jetir.org/papers/JETIR2403025.pdf