Modeling autosomal dominant Alzheimer's disease with machine learning.
Alzheimers Dement
; 17(6): 1005-1016, 2021 06.
Article
em En
| MEDLINE
| ID: mdl-33480178
ABSTRACT
INTRODUCTION:
Machine learning models were used to discover novel disease trajectories for autosomal dominant Alzheimer's disease.METHODS:
Longitudinal structural magnetic resonance imaging, amyloid positron emission tomography (PET), and fluorodeoxyglucose PET were acquired in 131 mutation carriers and 74 non-carriers from the Dominantly Inherited Alzheimer Network; the groups were matched for age, education, sex, and apolipoprotein ε4 (APOE ε4). A deep neural network was trained to predict disease progression for each modality. Relief algorithms identified the strongest predictors of mutation status.RESULTS:
The Relief algorithm identified the caudate, cingulate, and precuneus as the strongest predictors among all modalities. The model yielded accurate results for predicting future Pittsburgh compound B (R2 = 0.95), fluorodeoxyglucose (R2 = 0.93), and atrophy (R2 = 0.95) in mutation carriers compared to non-carriers.DISCUSSION:
Results suggest a sigmoidal trajectory for amyloid, a biphasic response for metabolism, and a gradual decrease in volume, with disease progression primarily in subcortical, middle frontal, and posterior parietal regions.Palavras-chave
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Imageamento por Ressonância Magnética
/
Tomografia por Emissão de Pósitrons
/
Doença de Alzheimer
/
Aprendizado de Máquina
Tipo de estudo:
Prognostic_studies
Limite:
Adult
/
Female
/
Humans
/
Male
Idioma:
En
Revista:
Alzheimers Dement
Ano de publicação:
2021
Tipo de documento:
Article
País de afiliação:
Estados Unidos