Learning Biomarker Models for Progression Estimation of Alzheimer's Disease

Beyond the usual suspects: multi-factorial computational models in the search for neurodegenerative disease mechanisms

From Alzheimer's disease to amyotrophic lateral sclerosis, the molecular cascades underlying neurodegenerative disorders remain poorly understood. The clinical view of neurodegeneration is confounded by symptomatic heterogeneity and mixed pathology in almost every patient. While the underlying physiological alterations originate, proliferate, and propagate potentially decades before symptomatic onset, the complexity and inaccessibility of the living brain limit direct observation over a patient's lifespan. Consequently, there is a critical need for robust computational methods to support the search for causal mechanisms of neurodegeneration by distinguishing pathogenic processes from consequential alterations, and inter-individual variability from intra-individual progression. Recently, promising advances have been made by data-driven spatiotemporal modeling of the brain, based on in vivo neuroimaging and biospecimen markers. These methods include disease progression models comparing the temporal evolution of various biomarkers, causal models linking interacting biological processes, network propagation models reproducing the spatial spreading of pathology, and biophysical models spanning cellular- to network-scale phenomena. In this review, we discuss various computational approaches for integrating cross-sectional, longitudinal, and multi-modal data, primarily from large observational neuroimaging studies, to understand (i) the temporal ordering of physiological alterations, i(i) their spatial relationships to the brain's molecular and cellular architecture, (iii) mechanistic interactions between biological processes, and (iv) the macroscopic effects of microscopic factors. We consider the extents to which computational models can evaluate mechanistic hypotheses, explore applications such as improving treatment selection, and discuss how model-informed insights can lay the groundwork for a pathobiological redefinition of neurodegenerative disorders.

Data-driven modelling of neurodegenerative disease progression: thinking outside the black box

Data-driven disease progression models are an emerging set of computational tools that reconstruct disease timelines for long-term chronic diseases, providing unique insights into disease processes and their underlying mechanisms. Such methods combine a priori human knowledge and assumptions with large-scale data processing and parameter estimation to infer long-term disease trajectories from short-term data. In contrast to 'black box' machine learning tools, data-driven disease progression models typically require fewer data and are inherently interpretable, thereby aiding disease understanding in addition to enabling classification, prediction and stratification. In this Review, we place the current landscape of data-driven disease progression models in a general framework and discuss their enhanced utility for constructing a disease timeline compared with wider machine learning tools that construct static disease profiles. We review the insights they have enabled across multiple neurodegenerative diseases, notably Alzheimer disease, for applications such as determining temporal trajectories of disease biomarkers, testing hypotheses about disease mechanisms and uncovering disease subtypes. We outline key areas for technological development and translation to a broader range of neuroscience and non-neuroscience applications. Finally, we discuss potential pathways and barriers to integrating disease progression models into clinical practice and trial settings.

Estimating Dementia Onset: AT(N) Profiles and Predictive Modeling in Mild Cognitive Impairment Patients

BACKGROUND

Mild Cognitive Impairment (MCI) usually precedes the symptomatic phase of dementia and constitutes a window of opportunities for preventive therapies.

OBJECTIVES

The objective of this study was to predict the time an MCI patient has left to reach dementia and obtain the most likely natural history in the progression of MCI towards dementia.

METHODS

This study was conducted on 633 MCI patients and 145 subjects with dementia through 4726 visits over 15 years from Alzheimer Disease Neuroimaging Initiative (ADNI) cohort. A combination of data from AT(N) profiles at baseline and longitudinal predictive modeling was applied. A data-driven approach was proposed for categorical diagnosis prediction and timeline estimation of cognitive decline progression, which combined supervised and unsupervised learning techniques.

RESULTS

A reduced vector of only neuropsychological measures was selected for training the models. At baseline, this approach had high performance in detecting subjects at high risk of converting from MCI to dementia in the coming years. Furthermore, a Disease Progression Model (DPM) was built and also verified using three metrics. As a result of the DPM focused on the studied population, it was inferred that amyloid pathology (A+) appears about 7 years before dementia, and tau pathology (T+) and neurodegeneration (N+) occur almost simultaneously, between 3 and 4 years before dementia. In addition, MCI-A+ subjects were shown to progress more rapidly to dementia compared to MCI-A- subjects.

CONCLUSION

Based on proposed natural histories and cross-sectional and longitudinal analysis of AD markers, the results indicated that only a single cerebrospinal fluid sample is necessary during the prodromal phase of AD. Prediction from MCI into dementia and its timeline can be achieved exclusively through neuropsychological measures.

Normative models for neuroimaging markers: Impact of model selection, sample size and evaluation criteria

Modelling population reference curves or normative modelling is increasingly used with the advent of large neuroimaging studies. In this paper we assess the performance of fitting methods from the perspective of clinical applications and investigate the influence of the sample size. Further, we evaluate linear and non-linear models for percentile curve estimation and highlight how the bias-variance trade-off manifests in typical neuroimaging data. We created plausible ground truth distributions of hippocampal volumes in the age range of 45 to 80 years, as an example application. Based on these distributions we repeatedly simulated samples for sizes between 50 and 50,000 data points, and for each simulated sample we fitted a range of normative models. We compared the fitted models and their variability across repetitions to the ground truth, with specific focus on the outer percentiles (1st, 5th, 10th) as these are the most clinically relevant. Our results quantify the expected decreasing trend in variance of the volume estimates with increasing sample size. However, bias in the volume estimates only decreases a modest amount, without much improvement at large sample sizes. The uncertainty of model performance is substantial for what would often be considered large samples in a neuroimaging context and rises dramatically at the ends of the age range, where fewer data points exist. Flexible models perform better across sample sizes, especially for non-linear ground truth. Surprisingly large samples of several thousand data points are needed to accurately capture outlying percentiles across the age range for applications in research and clinical settings. Performance evaluation methods should assess both bias and variance. Furthermore, caution is needed when attempting to go near the ends of the age range captured by the source data set and, as is a well known general principle, extrapolation beyond the age range should always be avoided. To help with such evaluations of normative models we have made our code available to guide researchers developing or utilising normative models.

Categorical predictive and disease progression modeling in the early stage of Alzheimer's disease

BACKGROUND

A preclinical stage of Alzheimer's disease (AD) precedes the symptomatic phases of mild cognitive impairment (MCI) and dementia, which constitutes a window of opportunities for preventive therapies or delaying dementia onset.

NEW METHOD

We propose to use categorical predictive models based on survival analysis with longitudinal data which are capable of determining subsets of markers to classify cognitively unimpaired (CU) subjects who progress into MCI/dementia or not. Subsequently, the proposed combination of markers was used to construct disease progression models (DPMs), which reveal long-term pathological trajectories from short-term clinical data. The proposed methodology was applied to a population recruited by the ADNI.

RESULTS

A very small subset of standard MRI-based data, CSF markers and cognitive measures was used to predict CU-to-MCI/dementia progression. The longitudinal data of these selected markers were used to construct DPMs using the algorithms of growth models by alternating conditional expectation (GRACE) and the latent time joint mixed effects model (LTJMM). The results show that the natural history of the proposed cognitive decline classifies the subjects well according to the clinical groups and shows a moderate correlation between the conversion times and their estimates by the algorithms.

COMPARISON WITH EXISTING METHODS

Unlike the training of the DPM algorithms without preselection of the markers, here, it is proposed to construct and evaluate the DPMs using the subsets of markers defined by the categorical predictive models.

CONCLUSIONS

The estimates of the natural history of the proposed cognitive decline from GRACE were more robust than those using LTJMM. The transition from normal to cognitive decline is mostly associated with an increase in temporal atrophy, worsening of clinical scores and pTAU/Aβ. Furthermore, pTAU/Aβ, Everyday Cognition score and the normalized volume of the entorhinal cortex show alterations of more than 20% fifteen years before the onset of cognitive decline.

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

A key challenge for the secondary prevention of Alzheimer’s dementia is the need to identify individuals early on in the disease process through sensitive cognitive tests and biomarkers. The European Prevention of Alzheimer’s Dementia (EPAD) consortium recruited participants into a longitudinal cohort study with the aim of building a readiness cohort for a proof-of-concept clinical trial and also to generate a rich longitudinal data-set for disease modelling. Data have been collected on a wide range of measurements including cognitive outcomes, neuroimaging, cerebrospinal fluid biomarkers, genetics and other clinical and environmental risk factors, and are available for 1,828 eligible participants at baseline, 1,567 at 6 months, 1,188 at one-year follow-up, 383 at 2 years, and 89 participants at three-year follow-up visit. We novelly apply state-of-the-art longitudinal modelling and risk stratification approaches to these data in order to characterise disease progression and biological heterogeneity within the cohort. Specifically, we use longitudinal class-specific mixed effects models to characterise the different clinical disease trajectories and a semi-supervised Bayesian clustering approach to explore whether participants can be stratified into homogeneous subgroups that have different patterns of cognitive functioning evolution, while also having subgroup-specific profiles in terms of baseline biomarkers and longitudinal rate of change in biomarkers.

Identifying relevant outcomes in the progression of Alzheimer's disease; what do patients and care partners want to know about prognosis?

BACKGROUND

Prognostic studies in the context of Alzheimer's disease (AD) mainly predicted time to dementia. However, it is questionable whether onset of dementia is the most relevant outcome along the AD disease trajectory from the perspective of patients and their care partners. Therefore, we aimed to identify the most relevant outcomes from the viewpoint of patients and care partners.

METHODS

We used a two-step, mixed-methods approach. As a first step we conducted four focus groups in the Netherlands to elicit a comprehensive list of outcomes considered important by patients (n = 12) and care partners (n = 14) in the prognosis of AD. The focus groups resulted in a list of 59 items, divided into five categories. Next, in an online European survey, we asked participants (n = 232; 99 patients, 133 care partners) to rate the importance of all 59 items (5-point Likert scale). As participants were likely to rate a large number of outcomes as "important" (4) or "very important" (5), we subsequently asked them to select the three items they considered most important.

RESULTS

The top-10 lists of items most frequently mentioned as "most important" by patients and care partners were merged into one core outcome list, comprising 13 items. Both patients and care partners selected outcomes from the category "cognition" most often, followed by items in the categories "functioning and dependency" and "physical health." No items from the category "behavior and neuropsychiatry" and "social environment" ended up in our core list of relevant outcomes.

CONCLUSION

We identified a core list of outcomes relevant to patients and care partner, and found that prognostic information related to cognitive decline, dependency, and physical health are considered most relevant by both patients and their care partners.

Longitudinal survival analysis and two-group comparison for predicting the progression of mild cognitive impairment to Alzheimer's disease

BACKGROUND

Longitudinal studies using structural magnetic resonance imaging (MRI) and neuropsychological measurements (NMs) allow a noninvasive means of following the subtle anatomical changes occurring during the evolution of AD.

NEW METHOD

This paper compared two approaches for the construction of longitudinal predictive models: a) two-group comparison between converter and nonconverter MCI subjects and b) longitudinal survival analysis. Predictive models combined MRI-based markers with NMs and included demographic and clinical information as covariates. Both approaches employed linear mixed effects modeling to capture the longitudinal trajectories of the markers. The two-group comparison approaches used linear discriminant analysis and the survival analysis used risk ratios obtained from the extended Cox model and logistic regression.

RESULTS

The proposed approaches were developed and evaluated using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with a total of 1330 visits from 321 subjects. With both approaches, a very small number of features were selected. These markers are easily interpretable, generating robust, verifiable and reliable predictive models. Our best models predicted conversion with 78% accuracy at baseline (AUC = 0.860, 79% sensitivity, 76% specificity). As more visits were made, longitudinal predictive models improved their predictions with 85% accuracy (AUC = 0.944, 86% sensitivity, 85% specificity).

COMPARISON WITH EXISTING METHOD

Unlike the recently published models, there was also an improvement in the prediction accuracy of the conversion to AD when considering the longitudinal trajectory of the patients.

CONCLUSIONS

The survival-based predictive models showed a better balance between sensitivity and specificity with respect to the models based on the two-group comparison approach.

Disease progression timeline estimation for Alzheimer's disease using discriminative event based modeling

Alzheimer's Disease (AD) is characterized by a cascade of biomarkers becoming abnormal, the pathophysiology of which is very complex and largely unknown. Event-based modeling (EBM) is a data-driven technique to estimate the sequence in which biomarkers for a disease become abnormal based on cross-sectional data. It can help in understanding the dynamics of disease progression and facilitate early diagnosis and prognosis by staging patients. In this work we propose a novel discriminative approach to EBM, which is shown to be more accurate than existing state-of-the-art EBM methods. The method first estimates for each subject an approximate ordering of events. Subsequently, the central ordering over all subjects is estimated by fitting a generalized Mallows model to these approximate subject-specific orderings based on a novel probabilistic Kendall's Tau distance. We also introduce the concept of relative distance between events which helps in creating a disease progression timeline. Subsequently, we propose a method to stage subjects by placing them on the estimated disease progression timeline. We evaluated the proposed method on Alzheimer's Disease Neuroimaging Initiative (ADNI) data and compared the results with existing state-of-the-art EBM methods. We also performed extensive experiments on synthetic data simulating the progression of Alzheimer's disease. The event orderings obtained on ADNI data seem plausible and are in agreement with the current understanding of progression of AD. The proposed patient staging algorithm performed consistently better than that of state-of-the-art EBM methods. Event orderings obtained in simulation experiments were more accurate than those of other EBM methods and the estimated disease progression timeline was observed to correlate with the timeline of actual disease progression. The results of these experiments are encouraging and suggest that discriminative EBM is a promising approach to disease progression modeling.

Characterizing heterogeneity in the progression of Alzheimer's disease using longitudinal clinical and neuroimaging biomarkers

INTRODUCTION

Models characterizing intermediate disease stages of Alzheimer's disease (AD) are needed to inform clinical care and prognosis. Current models, however, use only a small subset of available biomarkers, capturing only coarse changes along the complete spectrum of disease progression. We propose the use of machine learning techniques and clinical, biochemical, and neuroimaging biomarkers to characterize progression to AD.

METHODS

We used a large multimodal longitudinal data set of biomarkers and demographic and genotype information from 1624 participants from the Alzheimer's Disease Neuroimaging Initiative. Using hidden Markov models, we characterized intermediate disease stages. We validated inferred disease trajectories by comparing time to first clinical AD diagnosis. We trained an L2-regularized logistic regression model to predict disease trajectory and evaluated its discriminative performance on a test set.

RESULTS

We identified 12 distinct disease states. Progression to AD occurred most often through one of two possible paths through these states. Paths differed in terms of rate of disease progression (by 5.44 years on average), amyloid and total-tau (t-tau) burden (by 10% and 69%, respectively), and hippocampal neurodegeneration (P < .001). On the test set, the predictive model achieved an area under the receiver operating characteristic curve of 0.85.

DISCUSSION

Progression to AD, in terms of biomarker trajectories, can be predicted based on participant-specific factors. Such disease staging tools could help in targeting high-risk patients for therapeutic intervention trials. As longitudinal data with richer features are collected, such models will help increase our understanding of the factors that drive the different trajectories of AD.

Structural brain imaging in Alzheimer's disease and mild cognitive impairment: biomarker analysis and shared morphometry database

Magnetic resonance (MR) imaging is a powerful technique for non-invasive in-vivo imaging of the human brain. We employed a recently validated method for robust cross-sectional and longitudinal segmentation of MR brain images from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort. Specifically, we segmented 5074 MR brain images into 138 anatomical regions and extracted time-point specific structural volumes and volume change during follow-up intervals of 12 or 24 months. We assessed the extracted biomarkers by determining their power to predict diagnostic classification and by comparing atrophy rates to published meta-studies. The approach enables comprehensive analysis of structural changes within the whole brain. The discriminative power of individual biomarkers (volumes/atrophy rates) is on par with results published by other groups. We publish all quality-checked brain masks, structural segmentations, and extracted biomarkers along with this article. We further share the methodology for brain extraction (pincram) and segmentation (MALPEM, MALPEM4D) as open source projects with the community. The identified biomarkers hold great potential for deeper analysis, and the validated methodology can readily be applied to other imaging cohorts.

Personalized Gaussian Processes for Forecasting of Alzheimer's Disease Assessment Scale-Cognition Sub-Scale (ADAS-Cog13)

In this paper, we introduce the use of a personalized Gaussian Process pGP model to predict per-patient changes in ADAS-Cog13-a significant predictor of Alzheimer's Disease (AD) in the cognitive domain - using data from each patient's previous visits, and testing on future (held-out) data. We start by learning a population-level model using multi- modal data from previously seen patients using a base Gaussian Process (GP) regression. The pGP is then formed by adapting the base GP sequentially over time to a new (target) patient using domain adaptive GPs [1]. We extend this personalized approach to predict the values of ADAS-Cog13 over the future 6, 12, 18, and 24 months. We compare this approach to a GP model trained only on past data of the target patients tGP, as well as to a new approach that combines pGP with tGP. We find that this new approach (pGP+tGP) leads to significant improvements in accurately forecasting future ADAS-Cog13 scores.

An image-based model of brain volume biomarker changes in Huntington's disease

Objective

Determining the sequence in which Huntington's disease biomarkers become abnormal can provide important insights into the disease progression and a quantitative tool for patient stratification. Here, we construct and present a uniquely fine‐grained model of temporal progression of Huntington's disease from premanifest through to manifest stages.

Methods

We employ a probabilistic event‐based model to determine the sequence of appearance of atrophy in brain volumes, learned from structural MRI in the Track‐HD study, as well as to estimate the uncertainty in the ordering. We use longitudinal and phenotypic data to demonstrate the utility of the patient staging system that the resulting model provides.

Results

The model recovers the following order of detectable changes in brain region volumes: putamen, caudate, pallidum, insula white matter, nonventricular cerebrospinal fluid, amygdala, optic chiasm, third ventricle, posterior insula, and basal forebrain. This ordering is mostly preserved even under cross‐validation of the uncertainty in the event sequence. Longitudinal analysis performed using 6 years of follow‐up data from baseline confirms efficacy of the model, as subjects consistently move to later stages with time, and significant correlations are observed between the estimated stages and nonimaging phenotypic markers.

Interpretation

We used a data‐driven method to provide new insight into Huntington's disease progression as well as new power to stage and predict conversion. Our results highlight the potential of disease progression models, such as the event‐based model, to provide new insight into Huntington's disease progression and to support fine‐grained patient stratification for future precision medicine in Huntington's disease.

Simulating Longitudinal Brain MRIs with Known Volume Changes and Realistic Variations in Image Intensity

This paper presents a simulator tool that can simulate large databases of visually realistic longitudinal MRIs with known volume changes. The simulator is based on a previously proposed biophysical model of brain deformation due to atrophy in AD. In this work, we propose a novel way of reproducing realistic intensity variation in longitudinal brain MRIs, which is inspired by an approach used for the generation of synthetic cardiac sequence images. This approach combines a deformation field obtained from the biophysical model with a deformation field obtained by a non-rigid registration of two images. The combined deformation field is then used to simulate a new image with specified atrophy from the first image, but with the intensity characteristics of the second image. This allows to generate the realistic variations present in real longitudinal time-series of images, such as the independence of noise between two acquisitions and the potential presence of variable acquisition artifacts. Various options available in the simulator software are briefly explained in this paper. In addition, the software is released as an open-source repository. The availability of the software allows researchers to produce tailored databases of images with ground truth volume changes; we believe this will help developing more robust brain morphometry tools. Additionally, we believe that the scientific community can also use the software to further experiment with the proposed model, and add more complex models of brain deformation and atrophy generation.

Instantiated mixed effects modeling of Alzheimer's disease markers

The assessment and prediction of a subject's current and future risk of developing neurodegenerative diseases like Alzheimer's disease are of great interest in both the design of clinical trials as well as in clinical decision making. Exploring the longitudinal trajectory of markers related to neurodegeneration is an important task when selecting subjects for treatment in trials and the clinic, in the evaluation of early disease indicators and the monitoring of disease progression. Given that there is substantial intersubject variability, models that attempt to describe marker trajectories for a whole population will likely lack specificity for the representation of individual patients. Therefore, we argue here that individualized models provide a more accurate alternative that can be used for tasks such as population stratification and a subject-specific prognosis. In the work presented here, mixed effects modeling is used to derive global and individual marker trajectories for a training population. Test subject (new patient) specific models are then instantiated using a stratified "marker signature" that defines a subpopulation of similar cases within the training database. From this subpopulation, personalized models of the expected trajectory of several markers are subsequently estimated for unseen patients. These patient specific models of markers are shown to provide better predictions of time-to-conversion to Alzheimer's disease than population based models.

Precision Imaging: more descriptive, predictive and integrative imaging

Medical image analysis has grown into a matured field challenged by progress made across all medical imaging technologies and more recent breakthroughs in biological imaging. The cross-fertilisation between medical image analysis, biomedical imaging physics and technology, and domain knowledge from medicine and biology has spurred a truly interdisciplinary effort that stretched outside the original boundaries of the disciplines that gave birth to this field and created stimulating and enriching synergies. Consideration on how the field has evolved and the experience of the work carried out over the last 15 years in our centre, has led us to envision a future emphasis of medical imaging in Precision Imaging. Precision Imaging is not a new discipline but rather a distinct emphasis in medical imaging borne at the cross-roads between, and unifying the efforts behind mechanistic and phenomenological model-based imaging. It captures three main directions in the effort to deal with the information deluge in imaging sciences, and thus achieve wisdom from data, information, and knowledge. Precision Imaging is finally characterised by being descriptive, predictive and integrative about the imaged object. This paper provides a brief and personal perspective on how the field has evolved, summarises and formalises our vision of Precision Imaging for Precision Medicine, and highlights some connections with past research and current trends in the field.