An approach to preprocess data in the diagnosis of Alzheimer's disease

Abstract

The number of people surviving in older age is more. This is mainly due to the developments that have taken place in the field of medicine. Theseold people are prone to many age related diseases. There are numerous neuro degenerative brain related diseases. Dementia is one among them. The people affected by Dementia will have lapse of memory. Alzheimer's disease is one of the types of dementia. Diagnosis of the disease is a time consuming task. To reduce the time needed for diagnosis the medical practitioners use system based approach. To help the practitioners researchers have developed various tools and techniques. In this paper the authors focus on classifications of subjects as diseased or not. Before doing classification the data has to be preprocessed. Preprocessing of data is done by applying techniques such as preparation of data, selection of attributes, balancing data, model evaluation and feature selection etc.The authors have collected the data of 466 subjects. The preprocessing techniques are applied on the data set. The subjects are classified using Naïve bayes and J48. The accuracy of the classifications are compared and Naïve bayes is found better.