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.

Towards cascading genetic risk in Alzheimer's disease.

Alzheimer's disease typically progresses in stages, which have been defined by the presence of disease-specific biomarkers: amyloid (A), tau (T) and neurodegeneration (N). This progression of biomarkers has been condensed into the ATN framework, in which each of the biomarkers can be either positive (+) or negative (-). Over the past decades, genome-wide association studies have implicated ∼90 different loci involved with the development of late-onset Alzheimer's disease. Here, we investigate whether genetic risk for Alzheimer's disease contributes equally to the progression in different disease stages or whether it exhibits a stage-dependent effect. Amyloid (A) and tau (T) status was defined using a combination of available PET and CSF biomarkers in the Alzheimer's Disease Neuroimaging Initiative cohort. In 312 participants with biomarker-confirmed A-T- status, we used Cox proportional hazards models to estimate the contribution of APOE and polygenic risk scores (beyond APOE) to convert to A+T- status (65 conversions). Furthermore, we repeated the analysis in 290 participants with A+T- status and investigated the genetic contribution to conversion to A+T+ (45 conversions). Both survival analyses were adjusted for age, sex and years of education. For progression from A-T- to A+T-, APOE-e4 burden showed a significant effect [hazard ratio (HR) = 2.88; 95% confidence interval (CI): 1.70-4.89; P < 0.001], whereas polygenic risk did not (HR = 1.09; 95% CI: 0.84-1.42; P = 0.53). Conversely, for the transition from A+T- to A+T+, the contribution of APOE-e4 burden was reduced (HR = 1.62; 95% CI: 1.05-2.51; P = 0.031), whereas the polygenic risk showed an increased contribution (HR = 1.73; 95% CI: 1.27-2.36; P < 0.001). The marginal APOE effect was driven by e4 homozygotes (HR = 2.58; 95% CI: 1.05-6.35; P = 0.039) as opposed to e4 heterozygotes (HR = 1.74; 95% CI: 0.87-3.49; P = 0.12). The genetic risk for late-onset Alzheimer's disease unfolds in a disease stage-dependent fashion. A better understanding of the interplay between disease stage and genetic risk can lead to a more mechanistic understanding of the transition between ATN stages and a better understanding of the molecular processes leading to Alzheimer's disease, in addition to opening therapeutic windows for targeted interventions.

Symptom-based staging for logopenic variant primary progressive aphasia.

BACKGROUND AND PURPOSE: Logopenic variant primary progressive aphasia (lvPPA) is a major variant presentation of Alzheimer's disease (AD) that signals the importance of communication dysfunction across AD phenotypes. A clinical staging system is lacking for the evolution of AD-associated communication difficulties that could guide diagnosis and care planning. Our aim was to create a symptom-based staging scheme for lvPPA, identifying functional milestones relevant to the broader AD spectrum. METHODS: An international lvPPA caregiver cohort was surveyed on symptom development under an 'exploratory' survey (34 UK caregivers). Feedback from this survey informed the development of a 'consolidation' survey (27 UK, 10 Australian caregivers) in which caregivers were presented with six provisional clinical stages and feedback was analysed using a mixed-methods approach. RESULTS: Six clinical stages were endorsed. Early symptoms included word-finding difficulty, with loss of message comprehension and speech intelligibility signalling later-stage progression. Additionally, problems with hearing in noise, memory and route-finding were prominent early non-verbal symptoms. 'Milestone' symptoms were identified that anticipate daily-life functional transitions and care needs. CONCLUSIONS: This work introduces a new symptom-based staging scheme for lvPPA, and highlights milestone symptoms that could inform future clinical scales for anticipating and managing communication dysfunction across the AD spectrum.

Statistical considerations when estimating time-saving treatment effects in Alzheimer's disease clinical trials.

INTRODUCTION: Estimating treatment effects as time savings in disease progression may be more easily interpretable than assessing the absolute difference or a percentage reduction. In this study, we investigate the statistical considerations of the existing method for estimating time savings and propose alternative complementary methods. METHODS: We propose five alternative methods to estimate the time savings from different perspectives. These methods are applied to simulated clinical trial data that mimic or modify the Clinical Dementia Rating Sum of Boxes progression trajectories observed in the Clarity AD lecanemab trial. RESULTS: Our study demonstrates that the proposed methods can generate more precise estimates by considering two crucial factors: (1) the absolute difference between treatment arms, and (2) the observed progression rate in the treatment arm. DISCUSSION: Quantifying treatment effects as time savings in disease progression offers distinct advantages. To provide comprehensive estimations, it is important to use various methods. HIGHLIGHTS: We explore the statistical considerations of the current method for estimating time savings. We proposed alternative methods that provide time savings estimations based on the observed absolute differences. By using various methods, a more comprehensive estimation of time savings can be achieved.

Crop filling: A pipeline for repairing memory clinic MRI corrupted by partial brain coverage.

Data-driven solutions offer great promise for improving healthcare. However, standard clinical neuroimaging data is subject to real-world imaging artefacts that can render the data unusable for computational research and quantitative neuroradiology. T1 weighted structural MRI is used in dementia research to obtain volumetric measurements from cortical and subcortical brain regions. However, clinical radiologists often prioritise T2 weighted or FLAIR scans for visual assessment. As such, T1 weighted scans are often acquired but may not be a priority, resulting in artefacts such as partial brain coverage being systematically present in memory clinic data. Here we present "MRI Crop Filling", a pipeline to replace the missing T1 data with synthetic data generated from the T2 scan, making real-world clinical T1 data usable for computational research including the latest AI innovations. Our method consists of the following steps:•Register scans: T2 and (cropped) T1.•Synthesise a new T1 using an open source deep learning tool.•Replace missing (cropped) T1 data in original T1 scan and super-resolve to improve image quality.

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.

Combining multimodal connectivity information improves modelling of pathology spread in Alzheimer's disease.

Cortical atrophy and aggregates of misfolded tau proteins are key hallmarks of Alzheimer's disease. Computational models that simulate the propagation of pathogens between connected brain regions have been used to elucidate mechanistic information about the spread of these disease biomarkers, such as disease epicentres and spreading rates. However, the connectomes that are used as substrates for these models are known to contain modality-specific false positive and false negative connections, influenced by the biases inherent to the different methods for estimating connections in the brain. In this work, we compare five types of connectomes for modelling both tau and atrophy patterns with the network diffusion model, which are validated against tau PET and structural MRI data from individuals with either mild cognitive impairment or dementia. We then test the hypothesis that a joint connectome, with combined information from different modalities, provides an improved substrate for the model. We find that a combination of multimodal information helps the model to capture observed patterns of tau deposition and atrophy better than any single modality. This is validated with data from independent datasets. Overall, our findings suggest that combining connectivity measures into a single connectome can mitigate some of the biases inherent to each modality and facilitate more accurate models of pathology spread, thus aiding our ability to understand disease mechanisms, and providing insight into the complementary information contained in different measures of brain connectivity.

Expectation maximisation pseudo labels.

In this paper, we study pseudo-labelling. Pseudo-labelling employs raw inferences on unlabelled data as pseudo-labels for self-training. We elucidate the empirical successes of pseudo-labelling by establishing a link between this technique and the Expectation Maximisation algorithm. Through this, we realise that the original pseudo-labelling serves as an empirical estimation of its more comprehensive underlying formulation. Following this insight, we present a full generalisation of pseudo-labels under Bayes' theorem, termed Bayesian Pseudo Labels. Subsequently, we introduce a variational approach to generate these Bayesian Pseudo Labels, involving the learning of a threshold to automatically select high-quality pseudo labels. In the remainder of the paper, we showcase the applications of pseudo-labelling and its generalised form, Bayesian Pseudo-Labelling, in the semi-supervised segmentation of medical images. Specifically, we focus on: (1) 3D binary segmentation of lung vessels from CT volumes; (2) 2D multi-class segmentation of brain tumours from MRI volumes; (3) 3D binary segmentation of whole brain tumours from MRI volumes; and (4) 3D binary segmentation of prostate from MRI volumes. We further demonstrate that pseudo-labels can enhance the robustness of the learned representations. The code is released in the following GitHub repository: https://github.com/moucheng2017/EMSSL.