Probabilistic disease progression modeling to characterize diagnostic uncertainty: Application to staging and prediction in Alzheimer's disease

• Published in: NeuroImage (Orlando, Fla.) Vol. 190; pp. 56 - 68
• Main Authors: Lorenzi, Marco, Filippone, Maurizio, Frisoni, Giovanni B., Alexander, Daniel C., Ourselin, Sebastien
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 15.04.2019; Elsevier Limited
• Subjects: Accuracy; Aged; Alzheimer Disease - diagnosis; Alzheimer Disease - metabolism; Alzheimer Disease - pathology; Alzheimer Disease - physiopathology; Alzheimer's disease; Amyloid; Atrophy; Biomarkers; Brain research; Clinical trials; Cognitive Dysfunction - diagnosis; Cognitive Dysfunction - metabolism; Cognitive Dysfunction - pathology; Cognitive Dysfunction - physiopathology; Data processing; Diagnosis; Disease Progression; Disease progression modeling; Follow-Up Studies; Gaussian process; Humans; Magnetic Resonance Imaging; Medical imaging; Models, Neurological; Neurodegenerative diseases; Pathology; Positron-Emission Tomography; Prognosis; Severity of Illness Index; Uncertainty; Clinical trials; Disease progression modeling; Gaussian process; Diagnosis; Alzheimer's disease
• ISSN: 1053-8119; 1095-9572
• DOI: 10.1016/j.neuroimage.2017.08.059

Disease progression modeling (DPM) of Alzheimer's disease (AD) aims at revealing long term pathological trajectories from short term clinical data. Along with the ability of providing a data-driven description of the natural evolution of the pathology, DPM has the potential of representing a valuable clinical instrument for automatic diagnosis, by explicitly describing the biomarker transition from normal to pathological stages along the disease time axis. In this work we reformulated DPM within a probabilistic setting to quantify the diagnostic uncertainty of individual disease severity in an hypothetical clinical scenario, with respect to missing measurements, biomarkers, and follow-up information. We show that the staging provided by the model on 582 amyloid positive testing individuals has high face validity with respect to the clinical diagnosis. Using follow-up measurements largely reduces the prediction uncertainties, while the transition from normal to pathological stages is mostly associated with the increase of brain hypo-metabolism, temporal atrophy, and worsening of clinical scores. The proposed formulation of DPM provides a statistical reference for the accurate probabilistic assessment of the pathological stage of de-novo individuals, and represents a valuable instrument for quantifying the variability and the diagnostic value of biomarkers across disease stages.