NORMA eResearch @NCI Library

Alzheimer Disease Detection and Prognosis from Clinical Data using Machine Learning Techniques

Mohammed, Mubeen Ali (2020) Alzheimer Disease Detection and Prognosis from Clinical Data using Machine Learning Techniques. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (2MB) | Preview


Alzheimer’s disease is the fifth most leading cause of death as per WHO impacting millions globally, 131 million cases projected in 2050. No cure has been found for Alzheimer’s disease implying early diagnosing of Alzheimer’s stages Normal Cognition (NC), Mild Cognitive Impairment (MCI), and Alzheimer disease (AD) in patients is cost-effective, reduce suffering among the community. In this paper, Machine learning algorithms like ElasticNET, Gradient Boosting, Deep Neural Net, Support Vector Machines, and LSTM networks are used for the prediction of continuous cognitive variables MMSE, ADAS13, Ventricle and categorical classification of 3 AD stages. These predictions are performed on ADNI Clinical data. The evaluation metrics proposed are R2 , RMSE, Accuracy, Precision, Recall, F1-score. Gradient boosted regressor is a robust model compared to other algorithms achieving R2 of 90% and lowest RMSE scores. Dynamic LSTM obtained an accuracy of 78% outperforming other classifiers showing promising results by detecting Alzheimer patients empowering medical supervisors to initiate appropriate treatment. The model is better at predicting Alzheimer’s stages however model accuracy can be enhanced by using a multi-modal, ensemble approach along with other state-of-the art methods.
Keywords : Alzheimer disease, Elastic Net, Gradient Boosting, Neural Network, LSTM Network, Support Vector Machines, BioMedical data

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
R Medicine > Healthcare Industry
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 20 Jan 2021 17:38
Last Modified: 20 Jan 2021 17:38

Actions (login required)

View Item View Item