Development of Gaussian Learning Algorithms for Early Detection of Alzheimer's Disease

Authors

Chen Fang, Florida International UniversityFollow

Document Type

Dissertation

Degree

Doctor of Philosophy (PhD)

Major/Program

Electrical Engineering

First Advisor's Name

Malek Adjouadi

First Advisor's Committee Title

Committee Chair

Second Advisor's Name

Mercedes Cabrerizo

Second Advisor's Committee Title

Committee Member

Third Advisor's Name

Armando Barreto

Third Advisor's Committee Title

Committee Member

Fourth Advisor's Name

Jean Andrian

Fourth Advisor's Committee Title

Committee Member

Fifth Advisor's Name

Naphtali Rishe

Fifth Advisor's Committee Title

Committee Member

Keywords

Alzheimer’s disease, computer-aided diagnosis, dimensionality reduction, mild cognitive impairment (MCI), natural language processing (NLP), multiclass classification, multimodal analysis

Date of Defense

3-26-2020

Abstract

Alzheimer’s disease (AD) is the most common form of dementia affecting 10% of the population over the age of 65 and the growing costs in managing AD are estimated to be $259 billion, according to data reported in the 2017 by the Alzheimer's Association. Moreover, with cognitive decline, daily life of the affected persons and their families are severely impacted. Taking advantage of the diagnosis of AD and its prodromal stage of mild cognitive impairment (MCI), an early treatment may help patients preserve the quality of life and slow the progression of the disease, even though the underlying disease cannot be reversed or stopped. This research aims to develop Gaussian learning algorithms, natural language processing (NLP) techniques, and mathematical models to effectively delineate the MCI participants from the cognitively normal (CN) group, and identify the most significant brain regions and patterns of changes associated with the progression of AD. The focus will be placed on the earliest manifestations of the disease (early MCI or EMCI) to plan for effective curative/therapeutic interventions and protocols.

Multiple modalities of biomarkers have been found to be significantly sensitive in assessing the progression of AD. In this work, several novel multimodal classification frameworks based on proposed Gaussian Learning algorithms are created and applied to neuroimaging data. Classification based on the combination of structural magnetic resonance imaging (MRI), positron emission tomography (PET), and cerebrospinal fluid (CSF) biomarkers is seen as the most reliable approach for high-accuracy classification.

Additionally, changes in linguistic complexity may provide complementary information for the diagnosis and prognosis of AD. For this research endeavor, an NLP-oriented neuropsychological assessment is developed to automatically analyze the distinguishing characteristics of text data in MCI group versus those in CN group. Early findings suggest significant linguistic differences between CN and MCI subjects in terms of word usage, vocabulary, recall, fragmented sentences.

In summary, the results obtained indicate a high potential of the neuroimaging-based classification and NLP-oriented assessment to be utilized as a practically computer aided diagnosis system for classification and prediction of AD and its prodromal stages. Future work will ultimately focus on early signs of AD that could help in the planning of curative and therapeutic intervention to slow the progression of the disease.

Identifier

FIDC008950

ORCID

https://orcid.org/0000-0001-9425-5626

Previously Published In

C. Fang, C. Li, M. Cabrerizo, A. Barreto, J. Andrian, N. Rishe, D. Loewenstein, R. Duara, and M. Adjouadi, “Gaussian discriminant analysis for optimal delineation of mild cognitive impairment in Alzheimer's disease,” Int J Neural Syst, vol. 28, no. 8, 1850017, May 2018.

C. Fang, C. Li, M. Cabrerizo, A. Barreto, J. Andrian, D. Loewenstein, R. Duara, and M. Adjouadi, “A novel Gaussian discriminant analysis-based computer aided diagnosis system for screening different stages of Alzheimer's disease,” in Proceedings of IEEE 17th International Conference on Bioinformatics and Bioengineering (BIBE), Oct. 23-25, 2017, Washington DC, pp. 279-284.

C. Fang, C. Li, M. Cabrerizo, A. Barreto, J. Andrian, D. Loewenstein, R. Duara, and M. Adjouadi, “A Gaussian discriminant analysis-based generative learning algorithm for the early diagnosis of mild cognitive impairment in Alzheimer's disease,” in Proceedings of IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Nov. 13-16, 2017, Kansas City, MO, pp. 538-542.

C. Fang, P. Janwattanapong, H. Martin, M. Cabrerizo, A. Barreto, D. Loewenstein, R. Duara, and M. Adjouadi, “Computerized neuropsychological assessment in mild cognitive impairment based on NLP-oriented feature extraction,” in Proceedings of IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Nov. 13-16, 2017, Kansas City, MO, pp. 543-546.

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 License.

Recommended Citation

Fang, Chen, "Development of Gaussian Learning Algorithms for Early Detection of Alzheimer's Disease" (2020). FIU Electronic Theses and Dissertations. 4398.
https://digitalcommons.fiu.edu/etd/4398