Optimizing Machine Learning Methods to Improve Predictive Models of Alzheimer’s Disease

Article type: Research Article

Authors: Ezzati, Ali^{a; b; *} | Zammit, Andrea R.^a | Harvey, Danielle J.^c | Habeck, Christian^d | Hall, Charles B.^e | Lipton, Richard B.^{a; b; e} | for the Alzheimer’s Disease Neuroimaging Initiative¹

Affiliations: [a] Department of Neurology, Albert Einstein College of Medicine, Bronx, NY, USA | [b] Department of Neurology, Montefiore Medical Center, Bronx, NY, USA | [c] Department of Public Health Sciences, University of California-Davis, Davis, CA, USA | [d] Department of Neurology, Cognitive Neuroscience Division, Columbia University, New York, NY, USA | [e] Department of Epidemiology and Population Health, Albert Einstein College of Medicine, Bronx, NY, USA

Correspondence: [*] Correspondence to: Ali Ezzati, MD, Albert Einstein College of Medicine, 1225 Morris Park Avenue, Bronx, NY 10461, USA. Tel.: +1 718 430 3885; Fax: +1 718 430 3870; E-mail: ali.ezzati@einstein.yu.edu.

Note: [1] Data used in preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database (http://adni.loni.usc.edu). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing of ADNI investigators can be found at https://adni.loni.usc.edu/wp-content/uploads/how_to_apply/ADNI_Acknowledgement_List.pdf.

Abstract: Background:Predicting clinical course of cognitive decline can boost clinical trials’ power and improve our clinical decision-making. Machine learning (ML) algorithms are specifically designed for the purpose of prediction; however. identifying optimal features or algorithms is still a challenge. Objective:To investigate the accuracy of different ML methods and different features to classify cognitively normal (CN) individuals from Alzheimer’s disease (AD) and to predict longitudinal outcome in participants with mild cognitive impairment (MCI). Methods:A total of 1,329 participants from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) were included: 424 CN, 656 MCI, and 249 AD individuals. Four feature-sets at baseline (hippocampal volume and volume of 47 cortical and subcortical regions with and without demographics and APOE4) and six machine learning methods (decision trees, support vector machines, K-nearest neighbor, ensemble linear discriminant, boosted trees, and random forests) were used to classify participants with normal cognition from participants with AD. Subsequently the model with best classification performance was used for predicting clinical outcome of MCI participants. Results:Ensemble linear discriminant models using demographics and all volumetric magnetic resonance imaging measures as feature-set showed the best performance in classification of CN versus AD participants (accuracy = 92.8%, sensitivity = 95.8%, and specificity = 88.3%). Prediction accuracy of future conversion from MCI to AD for this ensemble linear discriminant at 6, 12, 24, 36, and 48 months was 63.8% (sensitivity = 74.4, specificity = 63.1), 68.9% (sensitivity = 75.9, specificity = 67.8), 74.9% (sensitivity = 71.5, specificity = 76.3), 75.3%, (sensitivity = 65.2, specificity = 79.7), and 77.0% (sensitivity = 59.6, specificity = 86.1), respectively. Conclusions:Machine learning models trained for classification of CN versus AD can improve our prediction ability of MCI conversion to AD.

Keywords: Alzheimer’s disease, classification, early diagnosis, machine learning, magnetic resonance imaging, mild cognitive impairment, predictive analytics

DOI: 10.3233/JAD-190262

Journal: Journal of Alzheimer's Disease, vol. 71, no. 3, pp. 1027-1036, 2019