Chapter 12 - Medical diagnosis in Alzheimer’s disease based on supervised and semisupervised learning

Abstract

Dementia is one of the most common neurological disorders among the elderly. Identifying those who are of high risk suffering from dementia is important to the administration of early treatment to slow down the progression of dementia symptoms and help preserve some cognitive functions of the brain. To separate probably or possibly demented patients from normal persons, some medical data with features for describing symptoms are required. However, to achieve accurate classification, significant amount of subject feature information is involved and sufficient class labels are needed. Hence, identification of demented subjects can be transformed into a pattern recognition problem with high-dimensional nonlinear datasets, and conventional machine learning methods can typically be utilized for handling the problem. This chapter will discuss the applications of supervised and semisupervised learning methods on dementia diagnosis. The typical limitations of the current research are discussed in detail.