Deep recurrent model for individualized prediction of Alzheimer’s disease progression

• Published in: NeuroImage (Orlando, Fla.) Vol. 237; p. 118143
• Main Authors: Jung, Wonsik, Jun, Eunji, Suk, Heung-Il
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 15.08.2021; Elsevier Limited; Elsevier
• Subjects: Alzheimer's disease; Biomarkers; Cognitive ability; Cognitive tests; Computer applications; Conversion-Time Prediction; Data analysis; Deep Learning; Dementia; Dementia disorders; Discriminant analysis; Disease Progression Modeling; Longitudinal Data; Magnetic resonance imaging; Medical imaging; Medical prognosis; Mild Cognitive Impairment; Missing Value Imputation; Neurodegenerative diseases; Prediction models; Recurrent Neural Networks; Survival analysis; Missing Value Imputation; Alzheimer’s Disease; Longitudinal Data; Recurrent Neural Networks; Disease Progression Modeling; Mild Cognitive Impairment; Conversion-Time Prediction; Cognitive tests; Deep Learning
• ISSN: 1053-8119; 1095-9572; 1095-9572
• DOI: 10.1016/j.neuroimage.2021.118143

•A novel computational framework that can predict the phenotypic measurement of MRI biomarkers and trajectories of clinical status along with cognitive scores at multiple future time points.•Our proposed framework also tackles a secondary problem of estimating missing values in observations by taking account of temporal and multivariate relations inherent in time series data.•We performed exhaustive experiments on the ADNI dataset and showed its superiority in various metrics to the comparative methods considered in our experiments.•Our proposed method successfully predicted individual trajectories of MRI biomarkers, clinical scores, and clinical statuses over time by showing high correlation with the ground truths. Preprint [Display omitted] Alzheimer’s disease (AD) is known as one of the major causes of dementia and is characterized by slow progression over several years, with no treatments or available medicines. In this regard, there have been efforts to identify the risk of developing AD in its earliest time. While many of the previous works considered cross-sectional analysis, more recent studies have focused on the diagnosis and prognosis of AD with longitudinal or time series data in a way of disease progression modeling. Under the same problem settings, in this work, we propose a novel computational framework that can predict the phenotypic measurements of MRI biomarkers and trajectories of clinical status along with cognitive scores at multiple future time points. However, in handling time series data, it generally faces many unexpected missing observations. In regard to such an unfavorable situation, we define a secondary problem of estimating those missing values and tackle it in a systematic way by taking account of temporal and multivariate relations inherent in time series data. Concretely, we propose a deep recurrent network that jointly tackles the four problems of (i) missing value imputation, (ii) phenotypic measurements forecasting, (iii) trajectory estimation of a cognitive score, and (iv) clinical status prediction of a subject based on his/her longitudinal imaging biomarkers. Notably, the learnable parameters of all the modules in our predictive models are trained in an end-to-end manner by taking the morphological features and cognitive scores as input, with our circumspectly defined loss function. In our experiments over The Alzheimers Disease Prediction Of Longitudinal Evolution (TADPOLE) challenge cohort, we measured performance for various metrics and compared our method to competing methods in the literature. Exhaustive analyses and ablation studies were also conducted to better confirm the effectiveness of our method.