Alzheimerâs disease (AD), the most common cause of dementia, is a neurodegenerative disorder which leads to loss of intellectual ability and eventually resulting in death. Early detection of AD is seen as important because treatment may be most efficacious if introduced at its nascent stage. In practice, a diagnosis is largely based on clinical history and examination supported by neuropsychological evidence of the pattern of cognitive impairment. However, the reality is that only about half of those with probable dementia are actually recognized in the primary care setting. Microarrays are at the core of a biotechnology, which assists researchers to analyze the expressions of thousands of genes under different samples (conditions) at the same time. However, researchers face challenge in analyzing the microarray data due to its high dimensionality, noise and complexity in the gene expression dataset, which are characteristic of diseases such as Alzheimerâs. Therefore, it is important to find salient features from the Alzheimerâs disease gene expression dataset, which can assist in providing additional information in differentiating sub types of the disease along with the underlying biological phenomenon. Mining such data poses a critical problem with an aim to find out patterns and knowledge from these huge amounts of gene expression data. Therefore there is a need to develop an automatic system, which has the ability to classify the Alzheimerâs disease and improve the precision and accuracy of the diagnosis. This paper presents a data adaptive partitioning schema, which finds efficient partitions in every gene using gradient-based histogram partitioning approach. These partitions assist in finding the relationship and patterns among different genes in gene expression dataset in the form of rules, which helps in classifying new samples into their respective sub types of Alzheimer disease. Below are the outlines of various related research in the Alzheimer disease classification. (Data Adaptive Rule-based Classification System for Alzheimer Classification, Mohit Jain)
Last date updated on July, 2014
