Machine learning techniques for AD/MCI diagnosis and prognosis

Authors

Dinggang Shen, University of North CarolinaFollow
Chong-Yaw Wee, University of North Carolina
Daoqiang Zhang, University of North Carolina
Luping Zhou, University of WollongongFollow
Pew-Thian Yap, University of North Carolina

RIS ID

86796

Publication Details

Shen, D., Wee, C., Zhang, D., Zhou, L. & Yap, P. (2014). Machine learning techniques for AD/MCI diagnosis and prognosis. In S. Dua, U. Rajendra. Acharya & P. Dua (Eds.), Machine Learning in Healthcare Informatics (pp. 147-179). New York, United States: Springer-Verlag Berlin Heidelberg.

Abstract

In the past two decades, machine learning techniques have been extensively applied for the detection of neurologic or neuropsychiatric disorders, especially Alzheimer's disease (AD) and its prodrome, mild cognitive impairment (MCI). This chapter presents some of the latest developments in the application of machine learning techniques to AD and MCI diagnosis and prognosis. We will divide our discussion into two parts: single modality and multimodality approaches. We will discuss how various biomarkers as well as connectivity networks can be extracted from the various modalities, such as structural T1-weighted imaging, diffusion-tensor imaging (DTI) and resting-state functional magnetic resonance imaging (fMRI), for effective diagnosis and prognosis. We will further demonstrate how these modalities can be fused for further performance improvement.