Precise diagnosis of alzheimer's disease using recursive feature elimination method

Gufran Ahmad Ansari ； R. Sivakani ； S. Srisakthi

《International Journal of Systematic Innovation》 7卷3期 (2022/09) Pp. 28-38

https://doi.org/10.6977/IJoSI.202209_7(3).0003

摘要

One of the prevalent diseases that the elderly tend to have patients has been Alzheimer's disease (AD). It is a neurological disease where the brain cells start to deteriorate. As the disease progresses it eventually leads to the death of the brain cells. Death in brain cells results in various problems like memory loss change in behavior patterns and many more. The most challenging problem has been in predicting an early diagnosis of AD in patients. The importance of the disease is that it is detected early. If early detection is done, the death of brain cells can be reduced. The disease is predicted based on the various features of the patient. Feature selection has been one of the important steps in predicting the disease. This paper takes the OASIS data set and implements the different algorithms and proposes a model. The proposed model identifies the salient feature by recursively considering smaller and smaller sets of the features. The classification has been done for evaluating the feature selection. The result has been compared before the feature selection method and after the feature selection method. The performance metrics show improved scores after applying the feature section concept.

關鍵字

Alzheimer ； early diagnosis ； feature selection ； recursive feature elimination (RFE)