Statistical Disease Progression Modeling in Alzheimer Disease

Abstract

Background: The characterizing symptom of Alzheimer disease (AD) is cognitive deterioration. While much recent work has focused on defining AD as a biological construct, most patients are still diagnosed, staged, and treated based on their cognitive symptoms. But the cognitive capability of a patient at any time throughout this deterioration reflects not only the disease state, but also the effect of the cognitive decline on the patient's pre-disease cognitive capability. Patients with high pre-disease cognitive capabilities tend to score better on cognitive tests that are sensitive early in disease relative to patients with low pre-disease cognitive capabilities at a similar disease stage. Thus, a single assessment with a cognitive test is often not adequate for determining the stage of an AD patient. Repeated evaluation of patients' cognition over time may improve the ability to stage AD patients, and such longitudinal assessments in combinations with biomarker assessments can help elucidate the time dynamics of biomarkers. In turn, this can potentially lead to identification of markers that are predictive of disease stage and future cognitive decline, possibly before any cognitive deficit is measurable. Methods and Findings: This article presents a class of statistical disease progression models and applies them to longitudinal cognitive scores. These non-linear mixed-effects disease progression models explicitly model disease stage, baseline cognition, and the patients' individual changes in cognitive ability as latent variables. Maximum-likelihood estimation in these models induces a data-driven criterion for separating disease progression and baseline cognition. Applied to data from the Alzheimer's Disease Neuroimaging Initiative, the model estimated a timeline of cognitive decline that spans ∼15 years from the earliest subjective cognitive deficits to severe AD dementia. Subsequent analyses demonstrated how direct modeling of latent factors that modify the observed data patterns provides a scaffold for understanding disease progression, biomarkers, and treatment effects along the continuous time progression of disease. Conclusions: The presented framework enables direct interpretations of factors that modify cognitive decline. The results give new insights to the value of biomarkers for staging patients and suggest alternative explanations for previous findings related to accelerated cognitive decline among highly educated patients and patients on symptomatic treatments.

Simultaneous modeling of Alzheimer's disease progression via multiple cognitive scales

“…Resultingly, time 0 of the latent disease timescale corresponds to the average state of the cognitively normal participants at baseline. We have made both the univariate and multivariate models presented in Section 3 available in the progmod R package 20 which builds on the maximum likelihood estimation procedures in the nlme ‐package 21 . Example data and code for fitting both univariate and multivariate disease progression models are available in the package documentation.…”

“…These transformed outcomes are modeled using a linear mixed‐effects model and the identifiability of the latent time shifts is achieved by assuming that disease stage is the only consistent time‐invariant patient‐level effect across outcomes. Another recent disease progression modeling framework has been proposed by Raket 20 . This framework considers the same problem but differ in some key modeling choices.…”

Disease Modelling of Cognitive Outcomes and Biomarkers in the European Prevention of Alzheimer’s Dementia Longitudinal Cohort

“…On the whole there have been few treatment successes (and none of these are disease-modifying) despite substantive investment in pharmacological compounds for Alzheimer’s disease in symptomatic populations and early promise shown in pre-clinical studies ( Gauthier et al, 2016 ; Winblad et al, 2016 ; Anderson et al, 2017 ). There may be a number of possible explanations for the many failures including inadequate drug dosages, incorrect treatment targets and inappropriate trial populations where the disease process is too far along to be amenable to treatment ( Raket, 2020 ; Shi et al, 2020 ; Yiannopoulou and Papageorgiou, 2020 ). There is a consensus that the genesis of AD pathology occurs decades before the onset of dementia symptoms ( Braak and Braak, 1997 ; Hardy and Selkoe, 2002 ; Jack et al, 2010 ; Bateman et al, 2012 ; Braak and Del Tredici, 2012 ; Jack et al, 2013 ).…”

“…Various disease progression and sub-type approaches have been proposed and developed. These include survival and multi-state models for investigating transitions between disease states ( Hubbard and Zhou, 2011 ; Vos et al, 2013 ; van den Hout, 2016 ; Wei and Kryscio, 2016 ; Robitaille et al, 2018 ; Zhang et al, 2019 ); mixed effects models (linear, generalized, non-linear) that incorporate subject-specific random effects and can be extended to handle latent time shifts, random change points, latent factors, processes and classes, hidden states, and multiple outcomes ( Hall et al, 2000 ; Jedynak et al, 2012 ; Liu et al, 2013 ; Proust-Lima et al, 2013 ; Donohue et al, 2014 ; Samtani et al, 2014 ; Lai et al, 2016 ; Zhang et al, 2016 ; Geifman et al, 2018 ; Li et al, 2018 ; Wang et al, 2018 ; Lorenzi et al, 2019 ; Proust-Lima et al, 2019 ; Villeneuve et al, 2019 ; Younes et al, 2019 ; Bachman et al, 2020 ; Kulason et al, 2020 ; Raket, 2020 ; Segalas et al, 2020 ; Williams et al, 2020 ) and can be combined with models for event-history data ( Marioni et al, 2014 ; Blanche et al, 2015 ; Proust-Lima et al, 2016 ; Rouanet et al, 2016 ; Li et al, 2017 ; Iddi et al, 2019 ; Li and Luo, 2019 ; Wu et al, 2020 ); event-based models which attempt to model the pathological cascade of events occurring as the disease develops and progresses through disease stages ( Fonteijn et al, 2012 ; Young et al, 2014 ; Chen et al, 2016 ; Goyal et al, 2018 ; Oxtoby et al, 2018 ); and various clustering approaches for discovering risk stratification/disease progression groups and endotypes. For example, those based on hierarchical, partitioning and model-based clustering algorithms/methods ( Dong et al, 2016 ; Racine et al, 2016 ; Dong et al, 2017 ; ten Kate et al, 2018 ; Young et al, 2018 ).…”

fdata-04-676168.pdf

“…Various disease progression and sub-type approaches have been proposed and developed. These include survival and multi-state models for investigating transitions between disease states (Hubbard and Zhou, 2011;Vos et al, 2013;van den Hout, 2016;Wei and Kryscio, 2016;Robitaille et al, 2018;Zhang et al, 2019); mixed effects models (linear, generalized, non-linear) that incorporate subject-specific random effects and can be extended to handle latent time shifts, random change points, latent factors, processes and classes, hidden states, and multiple outcomes (Hall et al, 2000;Jedynak et al, 2012;Liu et al, 2013;Proust-Lima et al, 2013;Donohue et al, 2014;Samtani et al, 2014;Lai et al, 2016;Zhang et al, 2016;Geifman et al, 2018;Li et al, 2018;Wang et al, 2018;Lorenzi et al, 2019;Proust-Lima et al, 2019;Villeneuve et al, 2019;Younes et al, 2019;Bachman et al, 2020;Kulason et al, 2020;Raket, 2020;Segalas et al, 2020;Williams et al, 2020) and can be combined with models for event-history data (Marioni et al, 2014;Blanche et al, 2015;Proust-Lima et al, 2016;Rouanet et al, 2016;Li et al, 2017;Iddi et al, 2019;Li and Luo, 2019;Wu et al, 2020); event-based models which attempt to model the pathological cascade of events occurring as the disease develops and progresses through disease stages (Fonteijn et al, 2012;...…”