Predicting Amyloid-β Levels in Amnestic Mild Cognitive Impairment Using Machine Learning Techniques
| Autor: | Ali Ezzati, Christos Davatzikos, Christian G. Habeck, Richard B. Lipton, Andrea R. Zammit, Jinshil Hyun, Charles B. Hall, Ashkan Golzar, Danielle J Harvey, Irfan A. Qureshi, Monica Truelove-Hill |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
0301 basic medicine
Male Amyloid Apolipoprotein E4 Neuroimaging Disease Neuropsychological Tests Machine learning computer.software_genre Article Machine Learning 03 medical and health sciences 0302 clinical medicine Gene Frequency mental disorders Medicine Humans Cognitive Dysfunction Cognitive impairment Alleles Aged Amyloid beta-Peptides Receiver operating characteristic business.industry General Neuroscience Neuropsychology Brain General Medicine Middle Aged Magnetic Resonance Imaging Clinical trial Psychiatry and Mental health Clinical Psychology 030104 developmental biology Positron-Emission Tomography Cohort Female Artificial intelligence Geriatrics and Gerontology business computer 030217 neurology & neurosurgery Biomarkers |
| Zdroj: | J Alzheimers Dis |
| Popis: | BACKGROUND: Amyloid-β positivity (Aβ+) based on PET imaging is part of the enrollment criteria for many of the clinical trials of Alzheimer’s disease (AD), particularly in trials for amyloid-targeted therapy. Predicting Aβ positivity prior to PET imaging can decrease unnecessary patient burden and costs of running these trials. OBJECTIVE: The aim of this study was to evaluate the performance of a machine learning model in estimating the individual risk of Aβ+ based on gold-standard of PET imaging. METHODS: We used data from an amnestic mild cognitive impairment (aMCI) subset of the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort to develop and validate the models. The predictors of Aβ status included demographic and ApoE4 status in all models plus a combination of neuropsychological tests (NP), MRI volumetrics, and cerebrospinal fluid (CSF) biomarkers. RESULTS: The models that included NP and MRI measures separately showed an area under the receiver operating characteristics (AUC) of 0.74 and 0.72, respectively. However, using NP and MRI measures jointly in the model did not improve prediction. The models including CSF biomarkers significantly outperformed other models with AUCs between 0.89 to 0.92. CONCLUSIONS: Predictive models can be effectively used to identify persons with aMCI likely to be amyloid positive on a subsequent PET scan. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|