Robust parametric modeling of Alzheimer’s disease progression

• Published in: NeuroImage (Orlando, Fla.) Vol. 225; p. 117460
• Main Authors: Mehdipour Ghazi, Mostafa, Nielsen, Mads, Pai, Akshay, Modat, Marc, Jorge Cardoso, M., Ourselin, Sébastien, Sørensen, Lauge
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 15-01-2021; Elsevier Limited; Elsevier
• Subjects: Age; Aged; Aged, 80 and over; Algorithms; Alzheimer Disease - diagnostic imaging; Alzheimer Disease - metabolism; Alzheimer Disease - physiopathology; Alzheimer's disease; Amyloid beta-Peptides - metabolism; Bayesian analysis; Bayesian classifier; Biomarkers; Brain - diagnostic imaging; Brain - metabolism; Brain - physiopathology; Brain mapping; Cerebrospinal fluid; Classification; Cognitive ability; Cognitive Dysfunction - diagnostic imaging; Cognitive Dysfunction - metabolism; Cognitive Dysfunction - physiopathology; Deep learning; Dementia; Disease Progression; Disease progression modeling; Entorhinal Cortex - diagnostic imaging; Female; Generalized logistic function; Hippocampus - diagnostic imaging; Humans; Kernel density estimation; Logistic Models; M-estimation; Magnetic Resonance Imaging; Male; Mental Status and Dementia Tests; Methods; Neurodegenerative diseases; Neuroimaging; Neuropsychological Tests; Parametric statistics; Positron emission tomography; tau Proteins - metabolism; Temporal Lobe - diagnostic imaging; Generalized logistic function; Alzheimer’s disease; Magnetic resonance imaging; M-estimation; Disease progression modeling; Cerebrospinal fluid; Kernel density estimation; Positron emission tomography; Bayesian classifier
• ISSN: 1053-8119; 1095-9572
• DOI: 10.1016/j.neuroimage.2020.117460

•A parametric disease progression modeling method is proposed based on alternating Mestimation which is robust to outliers.•A novel generalized logistic function, called modified Stannard, is proposed which better fits the AD biomarker trajectories.•An end-to-end approach is introduced that performs biomarker trajectory modeling and clinical status classification.•The proposed method is applied to model the progression of Alzheimer’s disease using volumetric MRI and PET biomarkers, CSF measures, as well as cognitive tests.•The generalizability of the proposed method is evaluated based on the prediction performance within and across cohorts.
Quantitative characterization of disease progression using longitudinal data can provide long-term predictions for the pathological stages of individuals. This work studies the robust modeling of Alzheimer’s disease progression using parametric methods. The proposed method linearly maps the individual’s age to a disease progression score (DPS) and jointly fits constrained generalized logistic functions to the longitudinal dynamics of biomarkers as functions of the DPS using M-estimation. Robustness of the estimates is quantified using bootstrapping via Monte Carlo resampling, and the estimated inflection points of the fitted functions are used to temporally order the modeled biomarkers in the disease course. Kernel density estimation is applied to the obtained DPSs for clinical status classification using a Bayesian classifier. Different M-estimators and logistic functions, including a novel type proposed in this study, called modified Stannard, are evaluated on the data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) for robust modeling of volumetric magnetic resonance imaging (MRI) and positron emission tomography (PET) biomarkers, cerebrospinal fluid (CSF) measurements, as well as cognitive tests. The results show that the modified Stannard function fitted using the logistic loss achieves the best modeling performance with an average normalized mean absolute error (NMAE) of 0.991 across all biomarkers and bootstraps. Applied to the ADNI test set, this model achieves a multiclass area under the ROC curve (AUC) of 0.934 in clinical status classification. The obtained results for the proposed model outperform almost all state-of-the-art results in predicting biomarker values and classifying clinical status. Finally, the experiments show that the proposed model, trained using abundant ADNI data, generalizes well to data from the National Alzheimer’s Coordinating Center (NACC) with an average NMAE of 1.182 and a multiclass AUC of 0.929.