Data-driven models of dominantly-inherited Alzheimer's disease progression

Disease progression modeling with temporal realignment: An emerging approach to deepen knowledge on chronic diseases

The recent development of the first disease-modifying drug for Alzheimer's disease represents a major advancement in dementia treatment. Behind this breakthrough is a quarter century of research efforts to understand the disease not by a particular symptom at a given moment, but by long-term sequential changes in multiple biomarkers. Disease progression modeling with temporal realignment (DPM-TR) is an emerging computational approach proposed with this biomarker-based disease concept. By integrating short-term clinical observations of multiple disease biomarkers in a data-driven manner, DPM-TR provides a way to understand the progression of chronic diseases over decades and predict individual disease stages more accurately. DPM-TR has been developed primarily in the area of neurodegenerative diseases but has recently been extended to non-neurodegenerative diseases, including chronic obstructive pulmonary, autoimmune, and ophthalmologic diseases. This review focuses on opportunities for DPM-TR in clinical practice and drug development and discusses its current status and challenges.

Understanding the Temporal Dynamics of Accelerated Brain Aging and Resilient Brain Aging: Insights from Discriminative Event-Based Analysis of UK Biobank Data

The intricate dynamics of brain aging, especially the neurodegenerative mechanisms driving accelerated (ABA) and resilient brain aging (RBA), are pivotal in neuroscience. Understanding the temporal dynamics of these phenotypes is crucial for identifying vulnerabilities to cognitive decline and neurodegenerative diseases. Currently, there is a lack of comprehensive understanding of the temporal dynamics and neuroimaging biomarkers linked to ABA and RBA. This study addressed this gap by utilizing a large-scale UK Biobank (UKB) cohort, with the aim to elucidate brain aging heterogeneity and establish the foundation for targeted interventions. Employing Lasso regression on multimodal neuroimaging data, structural MRI (sMRI), diffusion MRI (dMRI), and resting-state functional MRI (rsfMRI), we predicted the brain age and classified individuals into ABA and RBA cohorts. Our findings identified 1949 subjects (6.2%) as representative of the ABA subpopulation and 3203 subjects (10.1%) as representative of the RBA subpopulation. Additionally, the Discriminative Event-Based Model (DEBM) was applied to estimate the sequence of biomarker changes across aging trajectories. Our analysis unveiled distinct central ordering patterns between the ABA and RBA cohorts, with profound implications for understanding cognitive decline and vulnerability to neurodegenerative disorders. Specifically, the ABA cohort exhibited early degeneration in four functional networks and two cognitive domains, with cortical thinning initially observed in the right hemisphere, followed by the temporal lobe. In contrast, the RBA cohort demonstrated initial degeneration in the three functional networks, with cortical thinning predominantly in the left hemisphere and white matter microstructural degeneration occurring at more advanced stages. The detailed aging progression timeline constructed through our DEBM analysis positioned subjects according to their estimated stage of aging, offering a nuanced view of the aging brain's alterations. This study holds promise for the development of targeted interventions aimed at mitigating age-related cognitive decline.

Multimodal subtypes identified in Alzheimer's Disease Neuroimaging Initiative participants by missing-data-enabled subtype and stage inference

Alzheimer's disease is a highly heterogeneous disease in which different biomarkers are dynamic over different windows of the decades-long pathophysiological processes, and potentially have distinct involvement in different subgroups. Subtype and Stage Inference is an unsupervised learning algorithm that disentangles the phenotypic heterogeneity and temporal progression of disease biomarkers, providing disease insight and quantitative estimates of individual subtype and stage. However, a key limitation of Subtype and Stage Inference is that it requires a complete set of biomarkers for each subject, reducing the number of datapoints available for model fitting and limiting applications of Subtype and Stage Inference to modalities that are widely collected, e.g. volumetric biomarkers derived from structural MRI. In this study, we adapted the Subtype and Stage Inference algorithm to handle missing data, enabling the application of Subtype and Stage Inference to multimodal data (magnetic resonance imaging, positron emission tomography, cerebrospinal fluid and cognitive tests) from 789 participants in the Alzheimer's Disease Neuroimaging Initiative. Missing-data Subtype and Stage Inference identified five subtypes having distinct progression patterns, which we describe by the earliest unique abnormality as 'Typical AD with Early Tau', 'Typical AD with Late Tau', 'Cortical', 'Cognitive' and 'Subcortical'. These new multimodal subtypes were differentially associated with age, years of education, Apolipoprotein E (APOE4) status, white matter hyperintensity burden and the rate of conversion from mild cognitive impairment to Alzheimer's disease, with the 'Cognitive' subtype showing the fastest clinical progression, and the 'Subcortical' subtype the slowest. Overall, we demonstrate that missing-data Subtype and Stage Inference reveals a finer landscape of Alzheimer's disease subtypes, each of which are associated with different risk factors. Missing-data Subtype and Stage Inference has broad utility, enabling the prediction of progression in a much wider set of individuals, rather than being restricted to those with complete data.

A review of neuroimaging-based data-driven approach for Alzheimer's disease heterogeneity analysis

Alzheimer's disease (AD) is a complex form of dementia and due to its high phenotypic variability, its diagnosis and monitoring can be quite challenging. Biomarkers play a crucial role in AD diagnosis and monitoring, but interpreting these biomarkers can be problematic due to their spatial and temporal heterogeneity. Therefore, researchers are increasingly turning to imaging-based biomarkers that employ data-driven computational approaches to examine the heterogeneity of AD. In this comprehensive review article, we aim to provide health professionals with a comprehensive view of past applications of data-driven computational approaches in studying AD heterogeneity and planning future research directions. We first define and offer basic insights into different categories of heterogeneity analysis, including spatial heterogeneity, temporal heterogeneity, and spatial-temporal heterogeneity. Then, we scrutinize 22 articles relating to spatial heterogeneity, 14 articles relating to temporal heterogeneity, and five articles relating to spatial-temporal heterogeneity, highlighting the strengths and limitations of these strategies. Furthermore, we discuss the importance of understanding spatial heterogeneity in AD subtypes and their clinical manifestations, biomarkers for abnormal orderings and AD stages, the recent advancements in spatial-temporal heterogeneity analysis for AD, and the emerging role of omics data integration in advancing personalized diagnosis and treatment for AD patients. By emphasizing the significance of understanding AD heterogeneity, we hope to stimulate further research in this field to facilitate the development of personalized interventions for AD patients.

Biomarker Changes during 20 Years Preceding Alzheimer's Disease

BACKGROUND

Biomarker changes that occur in the period between normal cognition and the diagnosis of sporadic Alzheimer's disease have not been extensively investigated in longitudinal studies.

METHODS

We conducted a multicenter, nested case-control study of Alzheimer's disease biomarkers in cognitively normal participants who were enrolled in the China Cognition and Aging Study from January 2000 through December 2020. A subgroup of these participants underwent testing of cerebrospinal fluid (CSF), cognitive assessments, and brain imaging at 2-year-to-3-year intervals. A total of 648 participants in whom Alzheimer's disease developed were matched with 648 participants who had normal cognition, and the temporal trajectories of CSF biochemical marker concentrations, cognitive testing, and imaging were analyzed in the two groups.

RESULTS

The median follow-up was 19.9 years (interquartile range, 19.5 to 20.2). CSF and imaging biomarkers in the Alzheimer's disease group diverged from those in the cognitively normal group at the following estimated number of years before diagnosis: amyloid-beta (Aβ)42, 18 years; the ratio of Aβ42 to Aβ40, 14 years; phosphorylated tau 181, 11 years; total tau, 10 years; neurofilament light chain, 9 years; hippocampal volume, 8 years; and cognitive decline, 6 years. As cognitive impairment progressed, the changes in CSF biomarker levels in the Alzheimer's disease group initially accelerated and then slowed.

CONCLUSIONS

In this study involving Chinese participants during the 20 years preceding clinical diagnosis of sporadic Alzheimer's disease, we observed the time courses of CSF biomarkers, the times before diagnosis at which they diverged from the biomarkers from a matched group of participants who remained cognitively normal, and the temporal order in which the biomarkers became abnormal. (Funded by the Key Project of the National Natural Science Foundation of China and others; ClinicalTrials.gov number, NCT03653156.).

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.

A rat model established by simulating genetic-environmental interactions recapitulates human Alzheimer's disease pathology

BACKGROUND

In humans, Alzheimer's disease (AD) is typically sporadic in nature, and its pathology is usually influenced by extensive factors. The study established a rat model based on the genetic-environmental interaction.

METHODS

A rat model was established by transduction of an adeno-associated virus combined with acrolein treatment. Rats were assigned to the normal control (NC), acrolein group, AAV (-) group, AAV-APP group, and AAV-APP/acrolein group. The success of model construction was verified in multiple ways, including by assessing cognitive function, examining microstructural changes in the brain in vivo, and performing immunohistochemistry. The contribution of genetic (APP mutation) and environmental (acrolein) factors to AD-like phenotypes in the model was explored by factorial analysis.

RESULTS

1) The AAV-APP/acrolein group showed a decline in cognitive function, as indicated by a reduced gray matter volume in key cognition-related brain areas, lower FA values in the hippocampus and internal olfactory cortex, and Aβ deposition in the cortex and hippocampus. 2) The AAV-APP group also showed a decline in cognitive function, although the group exhibited atypical brain atrophy in the gray matter and insignificant Aβ deposition. 3) The acrolein group did not show any significant changes in Aβ levels, gray matter volume, or cognitive function. 4) The genetic factor (APP mutation) explained 39.74% of the AD-like phenotypes in the model factors, and the environmental factor (acrolein exposure) explained 33.3%.

CONCLUSIONS

The genetic-environmental interaction rat model exhibited a phenotype that resembled the features of human AD and will be useful for research on AD.

Novel data-driven subtypes and stages of brain atrophy in the ALS-FTD spectrum

BACKGROUND

TDP-43 proteinopathies represent a spectrum of neurological disorders, anchored clinically on either end by amyotrophic lateral sclerosis (ALS) and frontotemporal degeneration (FTD). The ALS-FTD spectrum exhibits a diverse range of clinical presentations with overlapping phenotypes, highlighting its heterogeneity. This study was aimed to use disease progression modeling to identify novel data-driven spatial and temporal subtypes of brain atrophy and its progression in the ALS-FTD spectrum.

METHODS

We used a data-driven procedure to identify 13 anatomic clusters of brain volume for 57 behavioral variant FTD (bvFTD; with either autopsy-confirmed TDP-43 or TDP-43 proteinopathy-associated genetic variants), 103 ALS, and 47 ALS-FTD patients with likely TDP-43. A Subtype and Stage Inference (SuStaIn) model was trained to identify subtypes of individuals along the ALS-FTD spectrum with distinct brain atrophy patterns, and we related subtypes and stages to clinical, genetic, and neuropathological features of disease.

RESULTS

SuStaIn identified three novel subtypes: two disease subtypes with predominant brain atrophy in either prefrontal/somatomotor regions or limbic-related regions, and a normal-appearing group without obvious brain atrophy. The limbic-predominant subtype tended to present with more impaired cognition, higher frequencies of pathogenic variants in TBK1 and TARDBP genes, and a higher proportion of TDP-43 types B, E and C. In contrast, the prefrontal/somatomotor-predominant subtype had higher frequencies of pathogenic variants in C9orf72 and GRN genes and higher proportion of TDP-43 type A. The normal-appearing brain group showed higher frequency of ALS relative to ALS-FTD and bvFTD patients, higher cognitive capacity, higher proportion of lower motor neuron onset, milder motor symptoms, and lower frequencies of genetic pathogenic variants. The overall SuStaIn stages also correlated with evidence for clinical progression including longer disease duration, higher King's stage, and cognitive decline. Additionally, SuStaIn stages differed across clinical phenotypes, genotypes and types of TDP-43 pathology.

CONCLUSIONS

Our findings suggest distinct neurodegenerative subtypes of disease along the ALS-FTD spectrum that can be identified in vivo, each with distinct brain atrophy, clinical, genetic and pathological patterns.

Tipping points in neurodegeneration

In Alzheimer's disease (AD), Aβ deposits form slowly, several decades before further pathological events trigger neurodegeneration and dementia. However, a substantial proportion of affected individuals remains non-demented despite AD pathology, raising questions about the underlying factors that determine the transition to clinical disease. Here, we emphasize the critical function of resilience and resistance factors, which we extend beyond the concept of cognitive reserve to include the glial, immune, and vascular system. We review the evidence and use the metaphor of "tipping points" to illustrate how gradually forming AD neuropathology in the preclinical stage can transition to dementia once adaptive functions of the glial, immune, and vascular system are lost and self-reinforcing pathological cascades are unleashed. Thus, we propose an expanded framework for pathomechanistic research that focuses on tipping points and non-neuronal resilience mechanisms, which may represent previously untapped therapeutic targets in preclinical AD.

Novel data-driven subtypes and stages of brain atrophy in the ALS-FTD spectrum

Background

TDP-43 proteinopathies represents a spectrum of neurological disorders, anchored clinically on either end by amyotrophic lateral sclerosis (ALS) and frontotemporal degeneration (FTD). The ALS-FTD spectrum exhibits a diverse range of clinical presentations with overlapping phenotypes, highlighting its heterogeneity. This study aimed to use disease progression modeling to identify novel data-driven spatial and temporal subtypes of brain atrophy and its progression in the ALS-FTD spectrum.

Methods

We used a data-driven procedure to identify 13 anatomic clusters of brain volumes for 57 behavioral variant FTD (bvFTD; with either autopsy-confirmed TDP-43 or TDP-43 proteinopathy-associated genetic variants), 103 ALS, and 47 ALS-FTD patients with likely TDP-43. A Subtype and Stage Inference (SuStaIn) model was trained to identify subtypes of individuals along the ALS-FTD spectrum with distinct brain atrophy patterns, and we related subtypes and stages to clinical, genetic, and neuropathological features of disease.

Results

SuStaIn identified three novel subtypes: two disease subtypes with predominant brain atrophy either in prefrontal/somatomotor regions or limbic-related regions, and a normal-appearing group without obvious brain atrophy. The Limbic-predominant subtype tended to present with more impaired cognition, higher frequencies of pathogenic variants in TBK1 and TARDBP genes, and a higher proportion of TDP-43 type B, E and C. In contrast, the Prefrontal/Somatomotor-predominant subtype had higher frequencies of pathogenic variants in C9orf72 and GRN genes and higher proportion of TDP-43 type A. The normal-appearing brain group showed higher frequency of ALS relative to ALS-FTD and bvFTD patients, higher cognitive capacity, higher proportion of lower motor neuron onset, milder motor symptoms, and lower frequencies of genetic pathogenic variants. Overall SuStaIn stages also correlated with evidence for clinical progression including longer disease duration, higher King's stage, and cognitive decline. Additionally, SuStaIn stages differed across clinical phenotypes, genotypes and types of TDP-43 pathology.

Conclusions

Our findings suggest distinct neurodegenerative subtypes of disease along the ALS-FTD spectrum that can be identified in vivo, each with distinct brain atrophy, clinical, genetic and pathological patterns.

Genetic Phenotypes of Alzheimer's Disease: Mechanisms and Potential Therapy

Years of intensive research has brought us extensive knowledge on the genetic and molecular factors involved in Alzheimer's disease (AD). In addition to the mutations in the three main causative genes of familial AD (FAD) including presenilins and amyloid precursor protein genes, studies have identified several genes as the most plausible genes for the onset and progression of FAD, such as triggering receptor expressed on myeloid cells 2, sortilin-related receptor 1, and adenosine triphosphate-binding cassette transporter subfamily A member 7. The apolipoprotein E ε4 allele is reported to be the strongest genetic risk factor for sporadic AD (SAD), and it also plays an important role in FAD. Here, we reviewed recent developments in genetic and molecular studies that contributed to the understanding of the genetic phenotypes of FAD and compared them with SAD. We further reviewed the advancements in AD gene therapy and discussed the future perspectives based on the genetic phenotypes.

The temporal event-based model: Learning event timelines in progressive diseases

Timelines of events, such as symptom appearance or a change in biomarker value, provide powerful signatures that characterise progressive diseases. Understanding and predicting the timing of events is important for clinical trials targeting individuals early in the disease course when putative treatments are likely to have the strongest effect. However, previous models of disease progression cannot estimate the time between events and provide only an ordering in which they change. Here, we introduce the temporal event-based model (TEBM), a new probabilistic model for inferring timelines of biomarker events from sparse and irregularly sampled datasets. We demonstrate the power of the TEBM in two neurodegenerative conditions: Alzheimer's disease (AD) and Huntington's disease (HD). In both diseases, the TEBM not only recapitulates current understanding of event orderings but also provides unique new ranges of timescales between consecutive events. We reproduce and validate these findings using external datasets in both diseases. We also demonstrate that the TEBM improves over current models; provides unique stratification capabilities; and enriches simulated clinical trials to achieve a power of 80 % with less than half the cohort size compared with random selection. The application of the TEBM naturally extends to a wide range of progressive conditions.

sEBM: Scaling Event Based Models to Predict Disease Progression via Implicit Biomarker Selection and Clustering

The Event Based Model (EBM) is a probabilistic generative model to explore biomarker changes occurring as a disease progresses. Disease progression is hypothesized to occur through a sequence of biomarker dysregulation "events". The EBM estimates the biomarker dysregulation event sequence. It computes the data likelihood for a given dysregulation sequence, and subsequently evaluates the posterior distribution on the dysregulation sequence. Since the posterior distribution is intractable, Markov Chain Monte-Carlo is employed to generate samples under the posterior distribution. However, the set of possible sequences increases as N ! where N is the number of biomarkers (data dimension) and quickly becomes prohibitively large for effective sampling via MCMC. This work proposes the "scaled EBM" (sEBM) to enable event based modeling on large biomarker sets (e.g. high-dimensional data). First, sEBM implicitly selects a subset of biomarkers useful for modeling disease progression and infers the event sequence only for that subset. Second, sEBM clusters biomarkers with similar positions in the event sequence and only orders the "clusters", with each successive cluster corresponding to the next stage in disease progression. These two modifications used to construct the sEBM method provably reduces the possible space of event sequences by multiple orders of magnitude. The novel modifications are supported by theory and experiments on synthetic and real clinical data provides validation for sEBM to work in higher dimensional settings. Results on synthetic data with known ground truth shows that sEBM outperforms previous EBM variants as data dimensions increase. sEBM was successfully implemented with up to 300 biomarkers, which is a 6-fold increase over previous EBM applications. A real-world clinical application of sEBM is performed using 119 neuroimaging markers from publicly available Alzheimer's Disease Neuroimaging Initiative (ADNI) data to stratify subjects into 6 stages of disease progression. Subjects included cognitively normal (CN), mild cognitive impairment (MCI), and Alzheimer's Disease (AD). sEBM stage is differentiated for the 3 groups ( χ 2 p - v a l u e < 4.6 e - 32 ) . Increased sEBM stage is a strong predictor of conversion risk to AD ( p - v a l u e < 2.3 e - 14 ) for MCI subjects, as verified with a Cox proportional-hazards model adjusted for age, sex, education and APOE4 status. Like EBM, sEBM does not rely on apriori defined diagnostic labels and only uses cross-sectional data.

Integrated algorithm combining plasma biomarkers and cognitive assessments accurately predicts brain β-amyloid pathology

BACKGROUND

Accurate prediction of cerebral amyloidosis with easily available indicators is urgently needed for diagnosis and treatment of Alzheimer's disease (AD).

METHODS

We examined plasma Aβ42, Aβ40, T-tau, P-tau181, and NfL, with APOE genotypes, cognitive test scores and key demographics in a large Chinese cohort (N = 609, aged 40 to 84 years) covering full AD spectrum. Data-driven integrated computational models were developed to predict brain β-amyloid (Aβ) pathology.

RESULTS

Our computational models accurately predict brain Aβ positivity (area under the ROC curves (AUC) = 0.94). The results are validated in Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. Particularly, the models have the highest prediction power (AUC = 0.97) in mild cognitive impairment (MCI) participants. Three levels of models are designed with different accuracies and complexities. The model which only consists of plasma biomarkers can predict Aβ positivity in amnestic MCI (aMCI) patients with AUC = 0.89. Generally the models perform better in participants without comorbidities or family histories.

CONCLUSIONS

The innovative integrated models provide opportunity to assess Aβ pathology in a non-invasive and cost-effective way, which might facilitate AD-drug development, early screening, clinical diagnosis and prognosis evaluation.

Temporal dynamics predict symptom onset and cognitive decline in familial frontotemporal dementia

INTRODUCTION

We tested whether changes in functional networks predict cognitive decline and conversion from the presymptomatic prodrome to symptomatic disease in familial frontotemporal dementia (FTD).

METHODS

For hypothesis generation, 36 participants with behavioral variant FTD (bvFTD) and 34 controls were recruited from one site. For hypothesis testing, we studied 198 symptomatic FTD mutation carriers, 341 presymptomatic mutation carriers, and 329 family members without mutations. We compared functional network dynamics between groups, with clinical severity and with longitudinal clinical progression.

RESULTS

We identified a characteristic pattern of dynamic network changes in FTD, which correlated with neuropsychological impairment. Among presymptomatic mutation carriers, this pattern of network dynamics was found to a greater extent in those who subsequently converted to the symptomatic phase. Baseline network dynamic changes predicted future cognitive decline in symptomatic participants and older presymptomatic participants.

DISCUSSION

Dynamic network abnormalities in FTD predict cognitive decline and symptomatic conversion.

HIGHLIGHTS

We investigated brain network predictors of dementia symptom onset Frontotemporal dementia results in characteristic dynamic network patterns Alterations in network dynamics are associated with neuropsychological impairment Network dynamic changes predict symptomatic conversion in presymptomatic carriers Network dynamic changes are associated with longitudinal cognitive decline.

SUPERVISED DEEP TREE IN ALZHEIMER'S DISEASE

As a progressive neurodegenerative disorder, the pathological changes of Alzheimer's disease (AD) might begin as much as two decades before the manifestation of clinical symptoms. Since the nature of the irreversible pathology of AD, early diagnosis provides a more tractable way for disease intervention and treatment. Therefore, numerous approaches have been developed for early diagnostic purposes. Although several important biomarkers have been established, most of the existing methods show limitations in describing the continuum of AD progression. However, understanding this continuous development is essential to understand the intrinsic progression mechanism of AD. In this work, we proposed a supervised deep tree model (SDTree) to integrate AD progression and individual prediction. The proposed SDTree method models the progression of AD as a tree embedded in a latent space using nonlinear reversed graph embedding. In this way, the continuum of AD progression is encoded into the locations on the tree structure. The learned tree structure can not only represent the continuum of AD but make predictions for new subjects. We evaluated our method on the classification task and achieved promising results on Alzheimer's Disease Neuroimaging Initiative dataset.

QTC-4-MeOBnE Ameliorated Depressive-Like Behavior and Memory Impairment in 3xTg Mice

Growing evidence has associated major depressive disorder (MDD) as a risk factor or prodromal syndrome for the occurrence of Alzheimer's disease (AD). Although this dilemma remains open, it is widely shown that a lifetime history of MDD is correlated with faster progression of AD pathology. Therefore, antidepressant drugs with neuroprotective effects could be an interesting therapeutic conception to target this issue simultaneously. In this sense, 1-(7-chloroquinolin-4-yl)-N-(4-methoxybenzyl)-5-methyl-1H-1,2,3-triazole-4- carboxamide (QTC-4-MeOBnE) was initially conceived as a multi-target ligand with affinity to β-secretase (BACE), glycogen synthase kinase 3β (GSK3β), and acetylcholinesterase but has also shown secondary effects on pathways involved in neuroinflammation and neurogenesis in preclinical models of AD. Herein, we investigated the effect of QTC-4-MeOBnE (1 mg/kg) administration for 45 days on depressive-like behavior and memory impairment in 3xTg mice, before the pathology is completely established. The treatment with QTC-4-MeOBnE prevented memory impairment and depressive-like behavior assessed by the Y-Maze task and forced swimming test. This effect was associated with the modulation of plural pathways involved in the onset and progression of AD, in cerebral structures of the cortex and hippocampus. Among them, the reduction of amyloid beta (Aβ) production mediated by changes in amyloid precursor protein metabolism and hippocampal tau phosphorylation through the inhibition of kinases. Additionally, QTC-4-MeOBnE also exerted beneficial effects on neuroinflammation and synaptic integrity. Overall, our studies suggest that QTC-4-MeOBnE has a moderate effect in a transgenic model of AD, indicating that perhaps studies regarding the neuropsychiatric effects as a neuroprotective molecule are more prone to be feasible.

A multidimensional ODE-based model of Alzheimer's disease progression

Data-driven Alzheimer's disease (AD) progression models are useful for clinical prediction, disease mechanism understanding, and clinical trial design. Most dynamic models were inspired by the amyloid cascade hypothesis and described AD progression as a linear chain of pathological events. However, the heterogeneity observed in healthy and sporadic AD populations challenged the amyloid hypothesis, and there is a need for more flexible dynamical models that accompany this conceptual shift. We present a statistical model of the temporal evolution of biomarkers and cognitive tests that allows diverse biomarker paths throughout the disease. The model consists of two elements: a multivariate dynamic model of the joint evolution of biomarkers and cognitive tests; and a clinical prediction model. The dynamic model uses a system of ordinary differential equations to jointly model the rate of change of an individual's biomarkers and cognitive tests. The clinical prediction model is an ordinal logistic model of the diagnostic label. Prognosis and time-to-onset predictions are obtained by computing the clinical label probabilities throughout the forecasted biomarker trajectories. The proposed dynamical model is interpretable, free of one-dimensional progression hypotheses or disease staging paradigms, and can account for the heterogeneous dynamics observed in sporadic AD. We developed the model using longitudinal data from the Alzheimer's Disease Neuroimaging Initiative. We illustrate the patterns of biomarker rates of change and the model performance to predict the time to conversion from MCI to dementia.

The Molecular Effects of Environmental Enrichment on Alzheimer's Disease

Environmental enrichment (EE) is an environmental paradigm encompassing sensory, cognitive, and physical stimulation at a heightened level. Previous studies have reported the beneficial effects of EE in the brain, particularly in the hippocampus. EE improves cognitive function as well as ameliorates depressive and anxiety-like behaviors, making it a potentially effective neuroprotective strategy against neurodegenerative diseases such as Alzheimer's disease (AD). Here, we summarize the current evidence for EE as a neuroprotective strategy as well as the potential molecular pathways that can explain the effects of EE from a biochemical perspective using animal models. The effectiveness of EE in enhancing brain activity against neurodegeneration is explored with a view to differences present in early and late life EE exposure, with its potential application in human being discussed. We discuss EE as one of the non pharmacological approaches in preventing or delaying the onset of AD for future research.

Current Applications of Machine Learning in Spine: From Clinical View

STUDY DESIGN

Narrative review.

OBJECTIVES

This review aims to present current applications of machine learning (ML) in spine domain to clinicians.

METHODS

We conducted a comprehensive PubMed search of peer-reviewed articles that were published between 2006 and 2020 using terms (spine, spinal, lumbar, cervical, thoracic, machine learning) to examine ML in spine. Then exclude research of other domain, case report, review or meta-analysis, and which without available abstract or full text.

RESULTS

Total 1738 articles were retrieved from database, and 292 studies were finally included. Key findings of current applications were compiled and summarized in this review. Main clinical applications of those techniques including image processing, diagnosis, decision supporting, operative assistance, rehabilitation, surgery outcomes, complications, hospitalization and cost.

CONCLUSIONS

ML had achieved excellent performance and hold immense potential in spine. ML could help clinical staff to improve medical level, enhance work efficiency, and reduce adverse events. However more randomized controlled trials and improvement of interpretability are essential to clinicians accepting models' assistance in real work.

Temporal order of clinical and biomarker changes in familial frontotemporal dementia

Unlike familial Alzheimer's disease, we have been unable to accurately predict symptom onset in presymptomatic familial frontotemporal dementia (f-FTD) mutation carriers, which is a major hurdle to designing disease prevention trials. We developed multimodal models for f-FTD disease progression and estimated clinical trial sample sizes in C9orf72, GRN and MAPT mutation carriers. Models included longitudinal clinical and neuropsychological scores, regional brain volumes and plasma neurofilament light chain (NfL) in 796 carriers and 412 noncarrier controls. We found that the temporal ordering of clinical and biomarker progression differed by genotype. In prevention-trial simulations using model-based patient selection, atrophy and NfL were the best endpoints, whereas clinical measures were potential endpoints in early symptomatic trials. f-FTD prevention trials are feasible but will likely require global recruitment efforts. These disease progression models will facilitate the planning of f-FTD clinical trials, including the selection of optimal endpoints and enrollment criteria to maximize power to detect treatment effects.

A Computational Monte Carlo Simulation Strategy to Determine the Temporal Ordering of Abnormal Age Onset Among Biomarkers of Alzheimer's Disease

To quantitatively determining the temporal ordering of abnormal age onsets (AAO) among various biomarkers for Alzheimer's disease (AD), we introduced a computational Monte-Carlo simulation (CMCS) to statistically examine such ordering of an AAO pair or over all AAOs. The CMCS 1) simulates longitudinal data, estimates AAO for each iteration, and finally assesses the type-I error of an AAO pair or all AAO ordering. Using hippocampus volume (VHC), cerebral glucose hypometabolic convergence index (HCI), plasma neurofilament light (NfL), mini-mental state exam (MMSE), the auditory verbal learning test-long term memory (AVLT-LTM), short term memory (AVLT-STM) and clinical-dementia rating sum of box scale (CDR-SOB) from 382 mild cognitive impairment converters and non-converters, the CMCS estimated type-I error for the earlier AAO of VHC, AVLT_STM and AVLT_LTM each than MMSE was significant (p<0.002). The type-I error for the overall AAO temporal ordering of VHC ≤ AVLT_STM ≤ AVLT_LTM < HCI ≤ MMSE ≤ CDR-SOB ≤ NfL was p = 0.012. These findings showed that our CMCS is capable of providing statistical inferences for quantifying AAO ordering which has important implications in advancing our understanding of AD.

A data-driven disease progression model of fluid biomarkers in genetic frontotemporal dementia

Several CSF and blood biomarkers for genetic frontotemporal dementia have been proposed, including those reflecting neuroaxonal loss (neurofilament light chain and phosphorylated neurofilament heavy chain), synapse dysfunction [neuronal pentraxin 2 (NPTX2)], astrogliosis (glial fibrillary acidic protein) and complement activation (C1q, C3b). Determining the sequence in which biomarkers become abnormal over the course of disease could facilitate disease staging and help identify mutation carriers with prodromal or early-stage frontotemporal dementia, which is especially important as pharmaceutical trials emerge. We aimed to model the sequence of biomarker abnormalities in presymptomatic and symptomatic genetic frontotemporal dementia using cross-sectional data from the Genetic Frontotemporal dementia Initiative (GENFI), a longitudinal cohort study. Two-hundred and seventy-five presymptomatic and 127 symptomatic carriers of mutations in GRN, C9orf72 or MAPT, as well as 247 non-carriers, were selected from the GENFI cohort based on availability of one or more of the aforementioned biomarkers. Nine presymptomatic carriers developed symptoms within 18 months of sample collection ('converters'). Sequences of biomarker abnormalities were modelled for the entire group using discriminative event-based modelling (DEBM) and for each genetic subgroup using co-initialized DEBM. These models estimate probabilistic biomarker abnormalities in a data-driven way and do not rely on previous diagnostic information or biomarker cut-off points. Using cross-validation, subjects were subsequently assigned a disease stage based on their position along the disease progression timeline. CSF NPTX2 was the first biomarker to become abnormal, followed by blood and CSF neurofilament light chain, blood phosphorylated neurofilament heavy chain, blood glial fibrillary acidic protein and finally CSF C3b and C1q. Biomarker orderings did not differ significantly between genetic subgroups, but more uncertainty was noted in the C9orf72 and MAPT groups than for GRN. Estimated disease stages could distinguish symptomatic from presymptomatic carriers and non-carriers with areas under the curve of 0.84 (95% confidence interval 0.80-0.89) and 0.90 (0.86-0.94) respectively. The areas under the curve to distinguish converters from non-converting presymptomatic carriers was 0.85 (0.75-0.95). Our data-driven model of genetic frontotemporal dementia revealed that NPTX2 and neurofilament light chain are the earliest to change among the selected biomarkers. Further research should investigate their utility as candidate selection tools for pharmaceutical trials. The model's ability to accurately estimate individual disease stages could improve patient stratification and track the efficacy of therapeutic interventions.

Targeted Screening for Alzheimer's Disease Clinical Trials Using Data-Driven Disease Progression Models

Heterogeneity in Alzheimer's disease progression contributes to the ongoing failure to demonstrate efficacy of putative disease-modifying therapeutics that have been trialed over the past two decades. Any treatment effect present in a subgroup of trial participants (responders) can be diluted by non-responders who ideally should have been screened out of the trial. How to identify (screen-in) the most likely potential responders is an important question that is still without an answer. Here, we pilot a computational screening tool that leverages recent advances in data-driven disease progression modeling to improve stratification. This aims to increase the sensitivity to treatment effect by screening out non-responders, which will ultimately reduce the size, duration, and cost of a clinical trial. We demonstrate the concept of such a computational screening tool by retrospectively analyzing a completed double-blind clinical trial of donepezil in people with amnestic mild cognitive impairment (clinicaltrials.gov: NCT00000173), identifying a data-driven subgroup having more severe cognitive impairment who showed clearer treatment response than observed for the full cohort.

What contribution can genetics make to predict the risk of Alzheimer's disease?

Alzheimer's disease (AD) is the most common neurodegenerative disorder. Although its etiology remains incompletely understood, genetic variants are important contributors. The prediction of AD risk through individual genetic variants is an important topic of research that may have individual and societal consequences when preventive treatments will become available. However, the genetic substratum of AD is heterogeneous. In addition to the extremely rare and fully penetrant pathogenic variants of the PSEN1, PSEN2 or APP genes causing autosomal dominant AD, a large spectrum of risk factors have been identified in complex forms, including the common risk factor APOEɛ4, which is associated with a moderate-to-high risk, common polymorphisms associated with a modest individual risk, and a plethora of rare variants in genes like SORL1, TREM2 or ABCA7 with moderate to high-magnitude effect. Understanding how these genetic factors contribute to AD risk in a given individual, in additional to non-genetic factors, remains a challenge. Over the last 10 years, age-related penetrance curves have progressively incorporated advances in the knowledge of AD genetics, from APOE to common polygenic components and, currently, SORL1 rare variants, which represents an important step towards precision medicine in AD. In this review, we present the complex genetic architecture of AD and we expose the prediction of AD risk according to its underlying genetic component.

Comparison and aggregation of event sequences across ten cohorts to describe the consensus biomarker evolution in Alzheimer's disease

BACKGROUND

Previous models of Alzheimer's disease (AD) progression were primarily hypothetical or based on data originating from single cohort studies. However, cohort datasets are subject to specific inclusion and exclusion criteria that influence the signals observed in their collected data. Furthermore, each study measures only a subset of AD-relevant variables. To gain a comprehensive understanding of AD progression, the heterogeneity and robustness of estimated progression patterns must be understood, and complementary information contained in cohort datasets be leveraged.

METHODS

We compared ten event-based models that we fit to ten independent AD cohort datasets. Additionally, we designed and applied a novel rank aggregation algorithm that combines partially overlapping, individual event sequences into a meta-sequence containing the complementary information from each cohort.

RESULTS

We observed overall consistency across the ten event-based model sequences (average pairwise Kendall's tau correlation coefficient of 0.69 ± 0.28), despite variance in the positioning of mainly imaging variables. The changes described in the aggregated meta-sequence are broadly consistent with the current understanding of AD progression, starting with cerebrospinal fluid amyloid beta, followed by tauopathy, memory impairment, FDG-PET, and ultimately brain deterioration and impairment of visual memory.

CONCLUSION

Overall, the event-based models demonstrated similar and robust disease cascades across independent AD cohorts. Aggregation of data-driven results can combine complementary strengths and information of patient-level datasets. Accordingly, the derived meta-sequence draws a more complete picture of AD pathology compared to models relying on single cohorts.

Differentiating amyloid beta spread in autosomal dominant and sporadic Alzheimer's disease

Amyloid-beta deposition is one of the hallmark pathologies in both sporadic Alzheimer's disease and autosomal-dominant Alzheimer's disease, the latter of which is caused by mutations in genes involved in amyloid-beta processing. Despite amyloid-beta deposition being a centrepiece to both sporadic Alzheimer's disease and autosomal-dominant Alzheimer's disease, some differences between these Alzheimer's disease subtypes have been observed with respect to the spatial pattern of amyloid-beta. Previous work has shown that the spatial pattern of amyloid-beta in individuals spanning the sporadic Alzheimer's disease spectrum can be reproduced with high accuracy using an epidemic spreading model which simulates the diffusion of amyloid-beta across neuronal connections and is constrained by individual rates of amyloid-beta production and clearance. However, it has not been investigated whether amyloid-beta deposition in the rarer autosomal-dominant Alzheimer's disease can be modelled in the same way, and if so, how congruent the spreading patterns of amyloid-beta across sporadic Alzheimer's disease and autosomal-dominant Alzheimer's disease are. We leverage the epidemic spreading model as a data-driven approach to probe individual-level variation in the spreading patterns of amyloid-beta across three different large-scale imaging datasets (2 sporadic Alzheimer's disease, 1 autosomal-dominant Alzheimer's disease). We applied the epidemic spreading model separately to the Alzheimer's Disease Neuroimaging initiative (n = 737), the Open Access Series of Imaging Studies (n = 510) and the Dominantly Inherited Alzheimer's Network (n = 249), the latter two of which were processed using an identical pipeline. We assessed inter- and intra-individual model performance in each dataset separately and further identified the most likely subject-specific epicentre of amyloid-beta spread. Using epicentres defined in previous work in sporadic Alzheimer's disease, the epidemic spreading model provided moderate prediction of the regional pattern of amyloid-beta deposition across all three datasets. We further find that, whilst the most likely epicentre for most amyloid-beta-positive subjects overlaps with the default mode network, 13% of autosomal-dominant Alzheimer's disease individuals were best characterized by a striatal origin of amyloid-beta spread. These subjects were also distinguished by being younger than autosomal-dominant Alzheimer's disease subjects with a default mode network amyloid-beta origin, despite having a similar estimated age of symptom onset. Together, our results suggest that most autosomal-dominant Alzheimer's disease patients express amyloid-beta spreading patterns similar to those of sporadic Alzheimer's disease, but that there may be a subset of autosomal-dominant Alzheimer's disease patients with a separate, striatal phenotype.

Cerebrospinal Fluid Profile of Tau, Phosphorylated Tau, Aβ42, and Aβ40 in Probable Cerebral Amyloid Angiopathy

Background: There is no consensus regarding the diagnostic value of cerebrospinal fluid (CSF) Alzheimer’s disease (AD) biomarkers in cerebral amyloid angiopathy (CAA). Objective: To describe the CSF levels of Aβ 42, Aβ 40, total protein Tau, and phosphorylated-Tau (p-Tau) in a large series of probable CAA patients and to compare with AD patients in order to identify a specific pattern in CAA but also to look for correlations with the neuroimaging profile. Methods: We retrospectively included from 2 French centers probable CAA patients according to modified Boston criteria who underwent lumbar puncture (LP) with CSF AD biomarker quantifications. Two neurologists independently analyzed all MRI sequences. A logistic regression and Spearman’s correlation coefficient were used to identify correlation between MRI and CSF biomarkers in CAA. Results: We included 63 probable CAA and 27 AD patients. Among CAA 50.8% presented with decreased Aβ 42 level associated with elevated p-Tau and/or Tau, 34.9% with isolated decreased Aβ 42 level and 14.3% patients with normal Aβ 42 level. Compared to AD, CAA showed lower levels of Tau (p = 0.008), p-Tau (p = 0.004), and Aβ 40 (p = 0.001) but similar Aβ 42 level (p = 0.07). No correlation between Aβ 42 or Aβ 40 levels and neuroimaging was found. Conclusion: CSF biomarkers may improve the accuracy of the modified Boston criteria with altered profile in 85% of the patients fulfilling revised Boston criteria for probable CAA. Aβ 40 appears as an interesting selective biomarker in differential diagnosis.

Alzheimer’s disease – the journey of a healthy brain into organ failure

As the most common dementia, Alzheimer’s disease (AD) exacts an immense personal, societal, and economic toll. AD was first described at the neuropathological level in the early 1900s. Today, we have mechanistic insight into select aspects of AD pathogenesis and have the ability to clinically detect and diagnose AD and underlying AD pathologies in living patients. These insights demonstrate that AD is a complex, insidious, degenerative proteinopathy triggered by Aβ aggregate formation. Over time Aβ pathology drives neurofibrillary tangle (NFT) pathology, dysfunction of virtually all cell types in the brain, and ultimately, overt neurodegeneration. Yet, large gaps in our knowledge of AD pathophysiology and huge unmet medical need remain. Though we largely conceptualize AD as a disease of aging, heritable and non-heritable factors impact brain physiology, either continuously or at specific time points during the lifespan, and thereby alter risk for devolvement of AD. Herein, I describe the lifelong journey of a healthy brain from birth to death with AD, while acknowledging the many knowledge gaps that remain regarding our understanding of AD pathogenesis. To ensure the current lexicon surrounding AD changes from inevitable, incurable, and poorly manageable to a lexicon of preventable, curable, and manageable we must address these knowledge gaps, develop therapies that have a bigger impact on clinical symptoms or progression of disease and use these interventions at the appropriate stage of disease.

Temporal Progression Patterns of Brain Atrophy in Corticobasal Syndrome and Progressive Supranuclear Palsy Revealed by Subtype and Stage Inference (SuStaIn)

Differentiating corticobasal degeneration presenting with corticobasal syndrome (CBD-CBS) from progressive supranuclear palsy with Richardson's syndrome (PSP-RS), particularly in early stages, is often challenging because the neurodegenerative conditions closely overlap in terms of clinical presentation and pathology. Although volumetry using brain magnetic resonance imaging (MRI) has been studied in patients with CBS and PSP-RS, studies assessing the progression of brain atrophy are limited. Therefore, we aimed to reveal the difference in the temporal progression patterns of brain atrophy between patients with CBS and those with PSP-RS purely based on cross-sectional data using Subtype and Stage Inference (SuStaIn)—a novel, unsupervised machine learning technique that integrates clustering and disease progression modeling. We applied SuStaIn to the cross-sectional regional brain volumes of 25 patients with CBS, 39 patients with typical PSP-RS, and 50 healthy controls to estimate the two disease subtypes and trajectories of CBS and PSP-RS, which have distinct atrophy patterns. The progression model and classification accuracy of CBS and PSP-RS were compared with those of previous studies to evaluate the performance of SuStaIn. SuStaIn identified distinct temporal progression patterns of brain atrophy for CBS and PSP-RS, which were largely consistent with previous evidence, with high reproducibility (99.7%) under cross-validation. We classified these diseases with high accuracy (0.875) and sensitivity (0.680 and 1.000, respectively) based on cross-sectional structural brain MRI data; the accuracy was higher than that reported in previous studies. Moreover, SuStaIn stage correctly reflected disease severity without the label of disease stage, such as disease duration. Furthermore, SuStaIn also showed the genialized performance of differentiation and reflection for CBS and PSP-RS. Thus, SuStaIn has potential for improving our understanding of disease mechanisms, accurately stratifying patients, and providing prognoses for patients with CBS and PSP-RS.

A data-driven model of brain volume changes in progressive supranuclear palsy

The most common clinical phenotype of progressive supranuclear palsy is Richardson syndrome, characterized by levodopa unresponsive symmetric parkinsonism, with a vertical supranuclear gaze palsy, early falls and cognitive impairment. There is currently no detailed understanding of the full sequence of disease pathophysiology in progressive supranuclear palsy. Determining the sequence of brain atrophy in progressive supranuclear palsy could provide important insights into the mechanisms of disease progression, as well as guide patient stratification and monitoring for clinical trials. We used a probabilistic event-based model applied to cross-sectional structural MRI scans in a large international cohort, to determine the sequence of brain atrophy in clinically diagnosed progressive supranuclear palsy Richardson syndrome. A total of 341 people with Richardson syndrome (of whom 255 had 12-month follow-up imaging) and 260 controls were included in the study. We used a combination of 12-month follow-up MRI scans, and a validated clinical rating score (progressive supranuclear palsy rating scale) to demonstrate the longitudinal consistency and utility of the event-based model's staging system. The event-based model estimated that the earliest atrophy occurs in the brainstem and subcortical regions followed by progression caudally into the superior cerebellar peduncle and deep cerebellar nuclei, and rostrally to the cortex. The sequence of cortical atrophy progresses in an anterior to posterior direction, beginning in the insula and then the frontal lobe before spreading to the temporal, parietal and finally the occipital lobe. This in vivo ordering accords with the post-mortem neuropathological staging of progressive supranuclear palsy and was robust under cross-validation. Using longitudinal information from 12-month follow-up scans, we demonstrate that subjects consistently move to later stages over this time interval, supporting the validity of the model. In addition, both clinical severity (progressive supranuclear palsy rating scale) and disease duration were significantly correlated with the predicted subject event-based model stage (P < 0.01). Our results provide new insights into the sequence of atrophy progression in progressive supranuclear palsy and offer potential utility to stratify people with this disease on entry into clinical trials based on disease stage, as well as track disease progression.

Beyond the average patient: how neuroimaging models can address heterogeneity in dementia

Dementia is a highly heterogeneous condition, with pronounced individual differences in age of onset, clinical presentation, progression rates and neuropathological hallmarks, even within a specific diagnostic group. However, the most common statistical designs used in dementia research studies and clinical trials overlook this heterogeneity, instead relying on comparisons of group average differences (e.g. patient versus control or treatment versus placebo), implicitly assuming within-group homogeneity. This one-size-fits-all approach potentially limits our understanding of dementia aetiology, hindering the identification of effective treatments. Neuroimaging has enabled the characterization of the average neuroanatomical substrates of dementias; however, the increasing availability of large open neuroimaging datasets provides the opportunity to examine patterns of neuroanatomical variability in individual patients. In this update, we outline the causes and consequences of heterogeneity in dementia and discuss recent research that aims to tackle heterogeneity directly, rather than assuming that dementia affects everyone in the same way. We introduce spatial normative modelling as an emerging data-driven technique, which can be applied to dementia data to model neuroanatomical variation, capturing individualized neurobiological 'fingerprints'. Such methods have the potential to detect clinically relevant subtypes, track an individual's disease progression or evaluate treatment responses, with the goal of moving towards precision medicine for dementia.

Degenerative adversarial neuroimage nets for brain scan simulations: Application in ageing and dementia

•

We implemented a new deep learning framework capable of synthesising realistic and accurate 4D brain MRI in ageing and Alzheimer’s disease.

•

We proposed a sequence of memory-efficient techniques designed to improve model stability, reduce artefacts, and improve individualization.

•

Synthesised T1w MRI scans contain only minor structural differences with real data, and have minimal noise/texture artefacts.

•

Synthesised MRI scans were diagnostically indistinguishable from real scans.

•

Synthetic MRI can be used for: i) data augmentation, ii) model validation and iii) understanding biological/disease mechanisms in the brain.

Accurate and realistic simulation of high-dimensional medical images has become an important research area relevant to many AI-enabled healthcare applications. However, current state-of-the-art approaches lack the ability to produce satisfactory high-resolution and accurate subject-specific images. In this work, we present a deep learning framework, namely 4D-Degenerative Adversarial NeuroImage Net (4D-DANI-Net), to generate high-resolution, longitudinal MRI scans that mimic subject-specific neurodegeneration in ageing and dementia. 4D-DANI-Net is a modular framework based on adversarial training and a set of novel spatiotemporal, biologically-informed constraints. To ensure efficient training and overcome memory limitations affecting such high-dimensional problems, we rely on three key technological advances: i) a new 3D training consistency mechanism called Profile Weight Functions (PWFs), ii) a 3D super-resolution module and iii) a transfer learning strategy to fine-tune the system for a given individual. To evaluate our approach, we trained the framework on 9852 T1-weighted MRI scans from 876 participants in the Alzheimer’s Disease Neuroimaging Initiative dataset and held out a separate test set of 1283 MRI scans from 170 participants for quantitative and qualitative assessment of the personalised time series of synthetic images. We performed three evaluations: i) image quality assessment; ii) quantifying the accuracy of regional brain volumes over and above benchmark models; and iii) quantifying visual perception of the synthetic images by medical experts. Overall, both quantitative and qualitative results show that 4D-DANI-Net produces realistic, low-artefact, personalised time series of synthetic T1 MRI that outperforms benchmark models.

Revealing the Timeline of Structural MRI Changes in Premanifest to Manifest Huntington Disease

BACKGROUND AND OBJECTIVES

Longitudinal measurements of brain atrophy using structural MRI (sMRI) can provide powerful markers for tracking disease progression in neurodegenerative diseases. In this study, we use a disease progression model to learn individual-level disease times and hence reveal a new timeline of sMRI changes in Huntington disease (HD).

METHODS

We use data from the 2 largest cohort imaging studies in HD-284 participants from TRACK-HD (100 control, 104 premanifest, and 80 manifest) and 159 participants from PREDICT-HD (36 control and 128 premanifest)-to train and test the model. We longitudinally register T1-weighted sMRI scans from 3 consecutive time points to reduce intraindividual variability and calculate regional brain volumes using an automated segmentation tool with rigorous manual quality control.

RESULTS

Our model reveals, for the first time, the relative magnitude and timescale of subcortical and cortical atrophy changes in HD. We find that the largest (∼20% average change in magnitude) and earliest (∼2 years before average abnormality) changes occur in the subcortex (pallidum, putamen, and caudate), followed by a cascade of changes across other subcortical and cortical regions over a period of ∼11 years. We also show that sMRI, when combined with our disease progression model, provides improved prediction of onset over the current best method (root mean square error = 4.5 years and maximum error = 7.9 years vs root mean square error = 6.6 years and maximum error = 18.2 years).

DISCUSSION

Our findings support the use of disease progression modeling to reveal new information from sMRI, which can potentially inform imaging marker selection for clinical trials.

Dynamic Changes in the Levels of Amyloid-β42 Species in the Brain and Periphery of APP/PS1 Mice and Their Significance for Alzheimer's Disease

Although amyloid-β₄₂ (Aβ₄₂) has been used as one of the core biomarkers for Alzheimer’s disease (AD) diagnosis, the dynamic changes of its different forms in the brain, blood, and even intestines and its correlation with the progression of AD disease remain obscure. Herein, we screened Aβ₄₂-specific preferred antibody pairs 1F12/1F12 and 1F12/2C6 to accurately detect Aβ₄₂ types using sandwich ELISA, including total Aβ₄₂, Aβ₄₂ oligomers (Aβ₄₂Os), and Aβ₄₂ monomers (Aβ₄₂Ms). The levels of Aβ₄₂ species in the brain, blood, and intestines of different aged APP/PS1 mice were quantified to study their correlation with AD progression. Total Aβ₄₂ levels in the blood were not correlated with AD progression, but Aβ₄₂Ms level in the blood of 9-month-old APP/PS1 mice was significantly reduced, and Aβ₄₂Os level in the brain was significantly elevated compared to 3-month-old APP/PS1, demonstrating that the levels of Aβ₄₂Ms and Aβ₄₂Os in the blood and brain were correlated with AD progression. Interestingly, in 9-month-old APP/PS1 mice, the level of Aβ₄₂ in the intestine was higher than that in 3-month-old APP/PS1 mice, indicating that the increased level of Aβ₄₂ in the gastrointestinal organs may also be related to the progression of AD. Meanwhile, changes in the gut microbiota composition of APP/PS1 mice with age were also observed. Therefore, the increase in Aβ derived from intestinal tissues and changes in microbiome composition can be used as a potential early diagnosis tool for AD, and further used as an indicator of drug intervention to reduce brain amyloid.

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.

Association of Apolipoprotein E ɛ4 Allele With Clinical and Multimodal Biomarker Changes of Alzheimer Disease in Adults With Down Syndrome

Importance

Alzheimer disease (AD) is the leading cause of death in individuals with Down syndrome (DS). Previous studies have suggested that the APOE ɛ4 allele plays a role in the risk and age at onset of dementia in DS; however, data on in vivo biomarkers remain scarce.

Objective

To investigate the association of the APOE ɛ4 allele with clinical and multimodal biomarkers of AD in adults with DS.

Design, Setting, and Participants

This dual-center cohort study recruited adults with DS in Barcelona, Spain, and in Cambridge, UK, between June 1, 2009, and February 28, 2020. Included individuals had been genotyped for APOE and had at least 1 clinical or AD biomarker measurement; 2 individuals were excluded because of the absence of trisomy 21. Participants were either APOE ɛ4 allele carriers or noncarriers.

Main Outcomes and Measures

Participants underwent a neurological and neuropsychological assessment. A subset of participants had biomarker measurements: Aβ1-42, Aβ1-40, phosphorylated tau 181 (pTau181) and neurofilament light chain (NfL) in cerebrospinal fluid (CSF), pTau181, and NfL in plasma; amyloid positron emission tomography (PET); fluorine 18-labeled-fluorodeoxyglucose PET; and/or magnetic resonance imaging. Age at symptom onset was compared between APOE ɛ4 allele carriers and noncarriers, and within-group local regression models were used to compare the association of biomarkers with age. Voxelwise analyses were performed to assess topographical differences in gray matter metabolism and volume.

Results

Of the 464 adults with DS included in the study, 97 (20.9%) were APOE ɛ4 allele carriers and 367 (79.1%) were noncarriers. No differences between the 2 groups were found by age (median [interquartile range], 45.9 [36.4-50.2] years vs 43.7 [34.9-50.2] years; P = .56) or sex (51 male carriers [52.6%] vs 199 male noncarriers [54.2%]). APOE ɛ4 allele carriers compared with noncarriers presented with AD symptoms at a younger age (mean [SD] age, 50.7 [4.4] years vs 52.7 [5.8] years; P = .02) and showed earlier cognitive decline. Locally estimated scatterplot smoothing curves further showed between-group differences in biomarker trajectories with age as reflected by nonoverlapping CIs. Specifically, carriers showed lower levels of the CSF Aβ1-42 to Aβ1-40 ratio until age 40 years, earlier increases in amyloid PET and plasma pTau181, and earlier loss of cortical metabolism and hippocampal volume. No differences were found in NfL biomarkers or CSF total tau and pTau181. Voxelwise analyses showed lower metabolism in subcortical and parieto-occipital structures and lower medial temporal volume in APOE ɛ4 allele carriers.

Conclusions and Relevance

In this study, the APOE ɛ4 allele was associated with earlier clinical and biomarker changes of AD in DS. These results provide insights into the mechanisms by which APOE increases the risk of AD, emphasizing the importance of APOE genotype for future clinical trials in DS.

Profiling of Serum Exosome MiRNA Reveals the Potential of a MiRNA Panel as Diagnostic Biomarker for Alzheimer's Disease

Alzheimer's disease (AD) is the most common neurodegenerative disease in the older adults. Although much effort has been made in the analyses of diagnostic biomarkers, such as amyloid-β, tau, and neurofilament light chain, identifying peripheral blood-based biomarkers is in extremely urgent need for their minimal invasiveness and more convenience. Here we characterized the miRNA profile by RNA sequencing in human serum exosomes from AD patients and healthy controls (HC) to investigate its potential for AD diagnosis. Subsequently, Gene Ontology analysis and pathway analysis were performed for the targeted genes from the differentially expressed miRNAs. These basic functions were differentially enriched, including cell adhesion, regulation of transcription, and the ubiquitin system. Functional network analysis highlighted the pathways of proteoglycans in cancer, viral carcinogenesis, signaling pathways regulating pluripotency of stem cells, and cellular senescence in AD. A total of 24 miRNAs showed significantly differential expression between AD and HC with more than ± 2.0-fold change at p value < 0.05 and at least 50 reads for each sample. Logistic regression analysis established a model for AD prediction by serum exosomal miR-30b-5p, miR-22-3p, and miR-378a-3p. Sequencing results were validated using quantitative reverse transcription PCR. The data showed that miR-30b-5p, miR-22-3p, and miR-378a-3p were significantly deregulated in AD, with area under the curve (AUC) of 0.668, 0.637, and 0.718, respectively. The combination of the three miRs gained a better diagnostic capability with AUC of 0.880. This finding revealed a miR panel as potential biomarker in the peripheral blood to distinguish AD from HC.

Modeling autosomal dominant Alzheimer's disease with machine learning

INTRODUCTION

Machine learning models were used to discover novel disease trajectories for autosomal dominant Alzheimer's disease.

METHODS

Longitudinal structural magnetic resonance imaging, amyloid positron emission tomography (PET), and fluorodeoxyglucose PET were acquired in 131 mutation carriers and 74 non-carriers from the Dominantly Inherited Alzheimer Network; the groups were matched for age, education, sex, and apolipoprotein ε4 (APOE ε4). A deep neural network was trained to predict disease progression for each modality. Relief algorithms identified the strongest predictors of mutation status.

RESULTS

The Relief algorithm identified the caudate, cingulate, and precuneus as the strongest predictors among all modalities. The model yielded accurate results for predicting future Pittsburgh compound B (R2  = 0.95), fluorodeoxyglucose (R2  = 0.93), and atrophy (R2  = 0.95) in mutation carriers compared to non-carriers.

DISCUSSION

Results suggest a sigmoidal trajectory for amyloid, a biphasic response for metabolism, and a gradual decrease in volume, with disease progression primarily in subcortical, middle frontal, and posterior parietal regions.

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

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.

Simulating the outcome of amyloid treatments in Alzheimer's disease from imaging and clinical data

In this study, we investigate SimulAD, a novel quantitative instrument for the development of intervention strategies for disease-modifying drugs in Alzheimer's disease. SimulAD is based on the modeling of the spatio-temporal dynamics governing the joint evolution of imaging and clinical biomarkers along the history of the disease, and allows the simulation of the effect of intervention time and drug dosage on the biomarkers' progression. When applied to multi-modal imaging and clinical data from the Alzheimer's Disease Neuroimaging Initiative the method enables to generate hypothetical scenarios of amyloid lowering interventions. The results quantify the crucial role of intervention time, and provide a theoretical justification for testing amyloid modifying drugs in the pre-clinical stage. Our experimental simulations are compatible with the outcomes observed in past clinical trials, and suggest that anti-amyloid treatments should be administered at least 7 years earlier than what is currently being done in order to obtain statistically powered improvement of clinical endpoints.

Dynamics of Cortical Degeneration Over a Decade in Huntington's Disease

BACKGROUND

Characterizing changing brain structure in neurodegeneration is fundamental to understanding long-term effects of pathology and ultimately providing therapeutic targets. It is well established that Huntington's disease (HD) gene carriers undergo progressive brain changes during the course of disease, yet the long-term trajectory of cortical atrophy is not well defined. Given that genetic therapies currently tested in HD are primarily expected to target the cortex, understanding atrophy across this region is essential.

METHODS

Capitalizing on a unique longitudinal dataset with a minimum of 3 and maximum of 7 brain scans from 49 HD gene carriers and 49 age-matched control subjects, we implemented a novel dynamical systems approach to infer patterns of regional neurodegeneration over 10 years. We use Bayesian hierarchical modeling to map participant- and group-level trajectories of atrophy spatially and temporally, additionally relating atrophy to the genetic marker of HD (CAG-repeat length) and motor and cognitive symptoms.

RESULTS

We show, for the first time, that neurodegenerative changes exhibit complex temporal dynamics with substantial regional variation around the point of clinical diagnosis. Although widespread group differences were seen across the cortex, the occipital and parietal regions undergo the greatest rate of cortical atrophy. We have established links between atrophy and genetic markers of HD while demonstrating that specific cortical changes predict decline in motor and cognitive performance.

CONCLUSIONS

HD gene carriers display regional variability in the spatial pattern of cortical atrophy, which relates to genetic factors and motor and cognitive symptoms. Our findings indicate a complex pattern of neuronal loss, which enables greater characterization of HD progression.

Sequence of clinical and neurodegeneration events in Parkinson's disease progression

Dementia is one of the most debilitating aspects of Parkinson's disease. There are no validated biomarkers that can track Parkinson's disease progression, nor accurately identify patients who will develop dementia and when. Understanding the sequence of observable changes in Parkinson's disease in people at elevated risk for developing dementia could provide an integrated biomarker for identifying and managing individuals who will develop Parkinson's dementia. We aimed to estimate the sequence of clinical and neurodegeneration events, and variability in this sequence, using data-driven statistical modelling in two separate Parkinson's cohorts, focusing on patients at elevated risk for dementia due to their age at symptom onset. We updated a novel version of an event-based model that has only recently been extended to cope naturally with clinical data, enabling its application in Parkinson's disease for the first time. The observational cohorts included healthy control subjects and patients with Parkinson's disease, of whom those diagnosed at age 65 or older were classified as having high risk of dementia. The model estimates that Parkinson's progression in patients at elevated risk for dementia starts with classic prodromal features of Parkinson's disease (olfaction, sleep), followed by early deficits in visual cognition and increased brain iron content, followed later by a less certain ordering of neurodegeneration in the substantia nigra and cortex, neuropsychological cognitive deficits, retinal thinning in dopamine layers, and further deficits in visual cognition. Importantly, we also characterize variation in the sequence. We found consistent, cross-validated results within cohorts, and agreement between cohorts on the subset of features available in both cohorts. Our sequencing results add powerful support to the increasing body of evidence suggesting that visual processing specifically is affected early in patients with Parkinson's disease at elevated risk of dementia. This opens a route to earlier and more precise detection, as well as a more detailed understanding of the pathological mechanisms underpinning Parkinson's dementia.

Recent Advances in Imaging of Preclinical, Sporadic, and Autosomal Dominant Alzheimer's Disease

Observing Alzheimer's disease (AD) pathological changes in vivo with neuroimaging provides invaluable opportunities to understand and predict the course of disease. Neuroimaging AD biomarkers also allow for real-time tracking of disease-modifying treatment in clinical trials. With recent neuroimaging advances, along with the burgeoning availability of longitudinal neuroimaging data and big-data harmonization approaches, a more comprehensive evaluation of the disease has shed light on the topographical staging and temporal sequencing of the disease. Multimodal imaging approaches have also promoted the development of data-driven models of AD-associated pathological propagation of tau proteinopathies. Studies of autosomal dominant, early sporadic, and late sporadic courses of the disease have shed unique insights into the AD pathological cascade, particularly with regard to genetic vulnerabilities and the identification of potential drug targets. Further, neuroimaging markers of b-amyloid, tau, and neurodegeneration have provided a powerful tool for validation of novel fluid cerebrospinal and plasma markers. This review highlights some of the latest advances in the field of human neuroimaging in AD across these topics, particularly with respect to positron emission tomography and structural and functional magnetic resonance imaging.

Hippocampal transcriptome-wide association study and neurobiological pathway analysis for Alzheimer's disease

Genome-wide association studies (GWASs) have identified multiple susceptibility loci for Alzheimer’s disease (AD), which is characterized by early and progressive damage to the hippocampus. However, the association of hippocampal gene expression with AD and the underlying neurobiological pathways remain largely unknown. Based on the genomic and transcriptomic data of 111 hippocampal samples and the summary data of two large-scale meta-analyses of GWASs, a transcriptome-wide association study (TWAS) was performed to identify genes with significant associations between hippocampal expression and AD. We identified 54 significantly associated genes using an AD-GWAS meta-analysis of 455,258 individuals; 36 of the genes were confirmed in another AD-GWAS meta-analysis of 63,926 individuals. Fine-mapping models further prioritized 24 AD-related genes whose effects on AD were mediated by hippocampal expression, including APOE and two novel genes (PTPN9 and PCDHA4). These genes are functionally related to amyloid-beta formation, phosphorylation/dephosphorylation, neuronal apoptosis, neurogenesis and telomerase-related processes. By integrating the predicted hippocampal expression and neuroimaging data, we found that the hippocampal expression of QPCTL and ERCC2 showed significant difference between AD patients and cognitively normal elderly individuals as well as correlated with hippocampal volume. Mediation analysis further demonstrated that hippocampal volume mediated the effect of hippocampal gene expression (QPCTL and ERCC2) on AD. This study identifies two novel genes associated with AD by integrating hippocampal gene expression and genome-wide association data and reveals candidate hippocampus-mediated neurobiological pathways from gene expression to AD.

The hippocampus is a potential neuroimaging endophenotype for Alzheimer’s disease (AD). This study identifies genes whose expression in hippocampal tissue is associated with AD and establishes the pathways from hippocampal gene expression to hippocampal volume to AD. We demonstrate that 24 genes are associated with AD in hippocampal tissue, and these genes are enriched for AD-related biological processes of amyloid-beta formation, phosphorylation/dephosphorylation, neuronal apoptosis, neurogenesis and telomerase-related processes. We further show that hippocampal volume mediates the effects of the hippocampal gene expression of QPCTL and ERCC2 on AD. These findings improve our understanding of the genetic and neural mechanisms of AD.

Robust Bayesian Analysis of Early-Stage Parkinson's Disease Progression Using DaTscan Images

This paper proposes a mixture of linear dynamical systems model for quantifying the heterogeneous progress of Parkinson's disease from DaTscan Images. The model is fitted to longitudinal DaTscans from the Parkinson's Progression Marker Initiative. Fitting is accomplished using robust Bayesian inference with collapsed Gibbs sampling. Bayesian inference reveals three image-based progression subtypes which differ in progression speeds as well as progression trajectories. The model reveals characteristic spatial progression patterns in the brain, each pattern associated with a time constant. These patterns can serve as disease progression markers. The subtypes also have different progression rates of clinical symptoms measured by MDS-UPDRS Part III scores.

APOE interacts with tau PET to influence memory independently of amyloid PET in older adults without dementia

INTRODUCTION

Apolipoprotein E (APOE) interacts with Alzheimer's disease pathology to promote disease progression. We investigated the moderating effect of APOE on independent associations of amyloid and tau positron emission tomography (PET) with cognition.

METHODS

For 297 nondemented older adults from the Alzheimer's Disease Neuroimaging Initiative, regression equations modeled associations between cognition and (1) cortical amyloid beta (Aβ) PET levels adjusting for tau and (2) medial temporal lobe (MTL) tau PET levels adjusting for Aβ, including interactions with APOE ε4-carrier status.

RESULTS

Adjusting for tau PET, Aβ was not associated with cognition and did not interact with APOE. In contrast, adjusting for Aβ PET, MTL tau was associated with all cognitive domains. Further, there was a stronger moderating effect of APOE on MTL tau and memory associations in ε4-carriers, even among Aβ-negative individuals.

DISCUSSION

Findings suggest that APOE may interact with tau independently of Aβ and that elevated MTL tau confers negative cognitive consequences in Aβ-negative ε4 carriers.

The sequence of structural, functional and cognitive changes in multiple sclerosis

BACKGROUND

As disease progression remains poorly understood in multiple sclerosis (MS), we aim to investigate the sequence in which different disease milestones occur using a novel data-driven approach.

METHODS

We analysed a cohort of 295 relapse-onset MS patients and 96 healthy controls, and considered 28 features, capturing information on T2-lesion load, regional brain and spinal cord volumes, resting-state functional centrality ("hubness"), microstructural tissue integrity of major white matter (WM) tracts and performance on multiple cognitive tests. We used a discriminative event-based model to estimate the sequence of biomarker abnormality in MS progression in general, as well as specific models for worsening physical disability and cognitive impairment.

RESULTS

We demonstrated that grey matter (GM) atrophy of the cerebellum, thalamus, and changes in corticospinal tracts are early events in MS pathology, whereas other WM tracts as well as the cognitive domains of working memory, attention, and executive function are consistently late events. The models for disability and cognition show early functional changes of the default-mode network and earlier changes in spinal cord volume compared to the general MS population. Overall, GM atrophy seems crucial due to its early involvement in the disease course, whereas WM tract integrity appears to be affected relatively late despite the early onset of WM lesions.

CONCLUSION

Data-driven modelling revealed the relative occurrence of both imaging and non-imaging events as MS progresses, providing insights into disease propagation mechanisms, and allowing fine-grained staging of patients for monitoring purposes.