Chen, GemaiChen, Zhenyu2023-09-082023-09-082023-08-31Chen, Z. (2023). Prediction of cognitive status of Alzheimer’s disease using machine learning methods with structural magnetic resonance imaging (Master's thesis, University of Calgary, Calgary, Canada). Retrieved from https://prism.ucalgary.ca.https://hdl.handle.net/1880/116985https://dx.doi.org/10.11575/PRISM/41829Alzheimer's disease is a progressive form of dementia. A patient diagnosed with Alzheimer's disease usually underwent three types of cognitive status: normal cognitive (NC), mild cognitive impairment (MCI), and Alzheimer's disease (AD). This thesis studies two machine learning models to predict cognitive status based on the region of interest features extracted from structural magnetic resonance imaging. The support vector machine (SVM) model uses recursive feature elimination to select the proper number of features and the multilayer perceptron (MLP) neural network model uses Bayesian optimization to tune the hyperparameters. When applied to a real data set with 1684 observations, the SVM model achieved 68.84% accuracy while the MLP model achieved 70.92% accuracy for multi-classification. We further compared the two models in three binary classifications, namely, NC vs MCI, MCI vs AD, and NC vs AD. The SVM model achieved the area under the receiver operating characteristic curves (AUCs) of 72%, 71%, 86%, while the MLP model achieved the AUCs of 68%, 73%, 88%, respectively. In general, the MLP model performs better than the SVM model. Both models can be used to assist in the early diagnosis of Alzheimer's disease.enUniversity of Calgary graduate students retain copyright ownership and moral rights for their thesis. You may use this material in any way that is permitted by the Copyright Act or through licensing that has been assigned to the document. For uses that are not allowable under copyright legislation or licensing, you are required to seek permission.Education--HealthEducation--MathematicsBiostatisticsmaster thesis