pySuStaIn: a Python implementation of the Subtype and Stage Inference algorithm

Detection of individual brain tau deposition in Alzheimer's disease based on latent feature-enhanced generative adversarial network

OBJECTIVE

The conventional methods for interpreting tau PET imaging in Alzheimer's disease (AD), including visual assessment and semi-quantitative analysis of fixed hallmark regions, are insensitive to detect individual small lesions because of the spatiotemporal neuropathology's heterogeneity. In this study, we proposed a latent feature-enhanced generative adversarial network model for the automatic extraction of individual brain tau deposition regions.

METHODS

The latent feature-enhanced generative adversarial network we propose can learn the distribution characteristics of tau PET images of cognitively normal individuals and output the abnormal distribution regions of patients. This model was trained and validated using 1131 tau PET images from multiple centres (with distinct races, i.e., Caucasian and Mongoloid) with different tau PET ligands. The overall quality of synthetic imaging was evaluated using structural similarity (SSIM), peak signal to noise ratio (PSNR), and mean square error (MSE). The model was compared to the fixed templates method for diagnosing and predicting AD.

RESULTS

The reconstructed images archived good quality, with SSIM = 0.967 ± 0.008, PSNR = 31.377 ± 3.633, and MSE = 0.0011 ± 0.0007 in the independent test set. The model showed higher classification accuracy (AUC = 0.843, 95 % CI = 0.796-0.890) and stronger correlation with clinical scales (r = 0.508, P < 0.0001). The model also achieved superior predictive performance in the survival analysis of cognitive decline, with a higher hazard ratio: 3.662, P < 0.001.

INTERPRETATION

The LFGAN4Tau model presents a promising new approach for more accurate detection of individualized tau deposition. Its robustness across tracers and races makes it a potentially reliable diagnostic tool for AD in practice.

Disease staging of Alzheimer's disease using a CSF-based biomarker model

Biological staging of individuals with Alzheimer's disease (AD) may improve diagnostic and prognostic workup of dementia in clinical practice and the design of clinical trials. In this study, we used the Subtype and Stage Inference (SuStaIn) algorithm to establish a robust biological staging model for AD using cerebrospinal fluid (CSF) biomarkers. Our analysis involved 426 participants from BioFINDER-2 and was validated in 222 participants from the Knight Alzheimer Disease Research Center cohort. SuStaIn identified a singular biomarker sequence and revealed that five CSF biomarkers effectively constituted a reliable staging model (ordered: Aβ42/40, pT217/T217, pT205/T205, MTBR-tau243 and non-phosphorylated mid-region tau). The CSF stages (0-5) demonstrated a correlation with increased abnormalities in other AD-related biomarkers, such as Aβ-PET and tau-PET, and aligned with longitudinal biomarker changes reflective of AD progression. Higher CSF stages at baseline were associated with an elevated hazard ratio of clinical decline. This study highlights a common molecular pathway underlying AD pathophysiology across all patients, suggesting that a single CSF collection can accurately indicate the presence of AD pathologies and characterize the stage of disease progression. The proposed staging model has implications for enhancing diagnostic and prognostic assessments in both clinical practice and the design of clinical trials.

Longitudinal inference of multiscale markers in psychosis: from hippocampal centrality to functional outcome

Multiscale neuroscience conceptualizes mental illness as arising from aberrant interactions across and within multiple biopsychosocial scales. We leverage this framework to propose a multiscale disease progression model of psychosis, in which hippocampal-cortical dysconnectivity precedes impairments in episodic memory and social cognition, which lead to more severe negative symptoms and lower functional outcome. As psychosis represents a heterogeneous collection of biological and behavioral alterations that evolve over time, we further predict this disease progression for a subtype of the patient sample, with other patients showing normal-range performance on all variables. We sampled data from two cross-sectional datasets of first- and multi-episode psychosis, resulting in a sample of 163 patients and 119 non-clinical controls. To address our proposed disease progression model and evaluate potential heterogeneity, we applied a machine-learning algorithm, SuStaIn, to the patient data. SuStaIn uniquely integrates clustering and disease progression modeling and identified three patient subtypes. Subtype 0 showed normal-range performance on all variables. In comparison, Subtype 1 showed lower episodic memory, social cognition, functional outcome, and higher negative symptoms, while Subtype 2 showed lower hippocampal-cortical connectivity and episodic memory. Subtype 1 deteriorated from episodic memory to social cognition, negative symptoms, functional outcome to bilateral hippocampal-cortical dysconnectivity, while Subtype 2 deteriorated from bilateral hippocampal-cortical dysconnectivity to episodic memory and social cognition, functional outcome to negative symptoms. This first application of SuStaIn in a multiscale psychiatric model provides distinct disease trajectories of hippocampal-cortical connectivity, which might underlie the heterogeneous behavioral manifestations of psychosis.

Brain high-throughput multi-omics data reveal molecular heterogeneity in Alzheimer's disease

Unbiased data-driven omic approaches are revealing the molecular heterogeneity of Alzheimer disease. Here, we used machine learning approaches to integrate high-throughput transcriptomic, proteomic, metabolomic, and lipidomic profiles with clinical and neuropathological data from multiple human AD cohorts. We discovered 4 unique multimodal molecular profiles, one of them showing signs of poor cognitive function, a faster pace of disease progression, shorter survival with the disease, severe neurodegeneration and astrogliosis, and reduced levels of metabolomic profiles. We found this molecular profile to be present in multiple affected cortical regions associated with higher Braak tau scores and significant dysregulation of synapse-related genes, endocytosis, phagosome, and mTOR signaling pathways altered in AD early and late stages. AD cross-omics data integration with transcriptomic data from an SNCA mouse model revealed an overlapping signature. Furthermore, we leveraged single-nuclei RNA-seq data to identify distinct cell-types that most likely mediate molecular profiles. Lastly, we identified that the multimodal clusters uncovered cerebrospinal fluid biomarkers poised to monitor AD progression and possibly cognition. Our cross-omics analyses provide novel critical molecular insights into AD.

Distinct spatiotemporal atrophy patterns in corticobasal syndrome are associated with different underlying pathologies

Objective

To identify imaging subtypes of the cortico-basal syndrome (CBS) based solely on a data-driven assessment of MRI atrophy patterns, and investigate whether these subtypes provide information on the underlying pathology.

Methods

We applied Subtype and Stage Inference (SuStaIn), a machine learning algorithm that identifies groups of individuals with distinct biomarker progression patterns, to a large cohort of 135 CBS cases (52 had a pathological or biomarker defined diagnosis) and 252 controls. The model was fit using volumetric features extracted from baseline T1-weighted MRI scans and validated using follow-up MRI. We compared the clinical phenotypes of each subtype and investigated whether there were differences in associated pathology between the subtypes.

Results

SuStaIn identified two subtypes with distinct sequences of atrophy progression; four-repeat-tauopathy confirmed cases were most commonly assigned to the Subcortical subtype (83% of CBS-PSP and 75% of CBS-CBD), while CBS-AD was most commonly assigned to the Fronto-parieto-occipital subtype (81% of CBS-AD). Subtype assignment was stable at follow-up (98% of cases), and individuals consistently progressed to higher stages (100% stayed at the same stage or progressed), supporting the model's ability to stage progression.

Interpretation

By jointly modelling disease stage and subtype, we provide data-driven evidence for at least two distinct and longitudinally stable spatiotemporal subtypes of atrophy in CBS that are associated with different underlying pathologies. In the absence of sensitive and specific biomarkers, accurately subtyping and staging individuals with CBS at baseline has important implications for screening on entry into clinical trials, as well as for tracking disease progression.

Pathology steered stratification network for subtype identification in Alzheimer's disease

BACKGROUND

Alzheimer's disease (AD) is a heterogeneous, multifactorial neurodegenerative disorder characterized by three neurobiological factors beta-amyloid, pathologic tau, and neurodegeneration. There are no effective treatments for AD at a late stage, urging for early detection and prevention. However, existing statistical inference approaches in neuroimaging studies of AD subtype identification do not take into account the pathological domain knowledge, which could lead to ill-posed results that are sometimes inconsistent with the essential neurological principles.

PURPOSE

Integrating systems biology modeling with machine learning, the study aims to assist clinical AD prognosis by providing a subpopulation classification in accordance with essential biological principles, neurological patterns, and cognitive symptoms.

METHODS

We propose a novel pathology steered stratification network (PSSN) that incorporates established domain knowledge in AD pathology through a reaction-diffusion model, where we consider non-linear interactions between major biomarkers and diffusion along the brain structural network. Trained on longitudinal multimodal neuroimaging data, the biological model predicts long-term evolution trajectories that capture individual characteristic progression pattern, filling in the gaps between sparse imaging data available. A deep predictive neural network is then built to exploit spatiotemporal dynamics, link neurological examinations with clinical profiles, and generate subtype assignment probability on an individual basis. We further identify an evolutionary disease graph to quantify subtype transition probabilities through extensive simulations.

RESULTS

Our stratification achieves superior performance in both inter-cluster heterogeneity and intra-cluster homogeneity of various clinical scores. Applying our approach to enriched samples of aging populations, we identify six subtypes spanning AD spectrum, where each subtype exhibits a distinctive biomarker pattern that is consistent with its clinical outcome.

CONCLUSIONS

The proposed PSSN (i) reduces neuroimage data to low-dimensional feature vectors, (ii) combines AT[N]-Net based on real pathological pathways, (iii) predicts long-term biomarker trajectories, and (iv) stratifies subjects into fine-grained subtypes with distinct neurological underpinnings. PSSN provides insights into pre-symptomatic diagnosis and practical guidance on clinical treatments, which may be further generalized to other neurodegenerative diseases.

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.

Exploring cognitive progression subtypes in the Framingham Heart Study

INTRODUCTION

Alzheimer's disease (AD) is a heterogeneous disorder characterized by complex underlying neuropathology that is not fully understood. This study aimed to identify cognitive progression subtypes and examine their correlation with clinical outcomes.

METHODS

Participants of this study were recruited from the Framingham Heart Study. The Subtype and Stage Inference (SuStaIn) method was used to identify cognitive progression subtypes based on eight cognitive domains.

RESULTS

Three cognitive progression subtypes were identified, including verbal learning (Subtype 1), abstract reasoning (Subtype 2), and visual memory (Subtype 3). These subtypes represent different domains of cognitive decline during the progression of AD. Significant differences in age of onset among the different subtypes were also observed. A higher SuStaIn stage was significantly associated with increased mortality risk.

DISCUSSION

This study provides a characterization of AD heterogeneity in cognitive progression, emphasizing the importance of developing personalized approaches for risk stratification and intervention.

Highlights

We used the Subtype and Stage Inference (SuStaIn) method to identify three cognitive progression subtypes.Different subtypes have significant variations in age of onset.Higher stages of progression are associated with increased mortality risk.

Disease progression modelling reveals heterogeneity in trajectories of Lewy-type α-synuclein pathology

Lewy body (LB) disorders, characterized by the aggregation of misfolded α-synuclein proteins, exhibit notable clinical heterogeneity. This may be due to variations in accumulation patterns of LB neuropathology. By applying data-driven disease progression modelling to regional neuropathological LB density scores from 814 brain donors, we describe three inferred trajectories of LB pathology that were characterized by differing clinicopathological presentation and longitudinal antemortem clinical progression. Most donors (81.9%) showed earliest pathology in the olfactory bulb, followed by accumulation in either limbic (60.8%) or brainstem (21.1%) regions. The remaining donors (18.1%) exhibited the first abnormalities in brainstem regions. Early limbic pathology was associated with Alzheimer's disease-associated characteristics. Meanwhile, brainstem-first pathology was associated with progressive motor impairment and substantial LB pathology outside of the brain. Our data provides evidence for heterogeneity in the temporal spread of LB pathology, possibly explaining some of the clinical disparities observed in LBDs.

A data-driven study of Alzheimer's disease related amyloid and tau pathology progression

Amyloid-β is thought to facilitate the spread of tau throughout the neocortex in Alzheimer's disease, though how this occurs is not well understood. This is because of the spatial discordance between amyloid-β, which accumulates in the neocortex, and tau, which accumulates in the medial temporal lobe during ageing. There is evidence that in some cases amyloid-β-independent tau spreads beyond the medial temporal lobe where it may interact with neocortical amyloid-β. This suggests that there may be multiple distinct spatiotemporal subtypes of Alzheimer's-related protein aggregation, with potentially different demographic and genetic risk profiles. We investigated this hypothesis, applying data-driven disease progression subtyping models to post-mortem neuropathology and in vivo PET-based measures from two large observational studies: the Alzheimer's Disease Neuroimaging Initiative (ADNI) and the Religious Orders Study and Rush Memory and Aging Project (ROSMAP). We consistently identified 'amyloid-first' and 'tau-first' subtypes using cross-sectional information from both studies. In the amyloid-first subtype, extensive neocortical amyloid-β precedes the spread of tau beyond the medial temporal lobe, while in the tau-first subtype, mild tau accumulates in medial temporal and neocortical areas prior to interacting with amyloid-β. As expected, we found a higher prevalence of the amyloid-first subtype among apolipoprotein E (APOE) ε4 allele carriers while the tau-first subtype was more common among APOE ε4 non-carriers. Within tau-first APOE ε4 carriers, we found an increased rate of amyloid-β accumulation (via longitudinal amyloid PET), suggesting that this rare group may belong within the Alzheimer's disease continuum. We also found that tau-first APOE ε4 carriers had several fewer years of education than other groups, suggesting a role for modifiable risk factors in facilitating amyloid-β-independent tau. Tau-first APOE ε4 non-carriers, in contrast, recapitulated many of the features of primary age-related tauopathy. The rate of longitudinal amyloid-β and tau accumulation (both measured via PET) within this group did not differ from normal ageing, supporting the distinction of primary age-related tauopathy from Alzheimer's disease. We also found reduced longitudinal subtype consistency within tau-first APOE ε4 non-carriers, suggesting additional heterogeneity within this group. Our findings support the idea that amyloid-β and tau may begin as independent processes in spatially disconnected regions, with widespread neocortical tau resulting from the local interaction of amyloid-β and tau. The site of this interaction may be subtype-dependent: medial temporal lobe in amyloid-first, neocortex in tau-first. These insights into the dynamics of amyloid-β and tau may inform research and clinical trials that target these pathologies.

Uncovering distinct progression patterns of tau deposition in progressive supranuclear palsy using [18F]Florzolotau PET imaging and subtype/stage inference algorithm

BACKGROUND

Progressive supranuclear palsy (PSP) is a primary 4-repeat tauopathy with diverse clinical phenotypes. Previous post-mortem studies examined tau deposition sequences in PSP, but in vivo scrutiny is lacking.

METHODS

We conducted [18F]Florzolotau tau positron emission tomography (PET) scans on 148 patients who were clinically diagnosed with PSP and 20 healthy controls. We employed the Subtype and Stage Inference (SuStaIn) algorithm to identify PSP subtype/stage and related tau patterns, comparing clinical features across subtypes and assessing PSP stage-clinical severity association. We also evaluated functional connectivity differences among subtypes through resting-state functional magnetic resonance imaging.

FINDINGS

We identified two distinct subtypes of PSP: Subtype1 and Subtype2. Subtype1 typically exhibits a sequential progression of the disease, starting from subcortical and gradually moving to cortical regions. Conversely, Subtype2 is characterized by an early, simultaneous onset in both regions. Interestingly, once the disease is initiated, Subtype1 tends to spread more rapidly within each region compared to Subtype2. Individuals categorized as Subtype2 are generally older and exhibit less severe dysfunctions in areas such as cognition, bulbar, limb motor, and general motor functions compared to those with Subtype1. Moreover, they have a more favorable prognosis in terms of limb motor function. We found significant correlations between several clinical variables and the identified PSP SuStaIn stages. Furthermore, Subtype2 displayed a remarkable reduction in functional connectivity compared to Subtype1.

INTERPRETATION

We present the evidence of distinct in vivo spatiotemporal tau trajectories in PSP. Our findings can contribute to precision medicine advancements for PSP.

FUNDING

This work was supported by grants from the National Natural Science Foundation of China (number 82272039, 81971641, 82021002, and 92249302); Swiss National Science Foundation (number 188350); the STI2030-Major Project of China (number 2022ZD0211600); the Clinical Research Plan of Shanghai Hospital Development Center of China (number SHDC2020CR1038B); and the National Key R&D Program of China (number 2022YFC2009902, 2022YFC2009900), the China Scholarship Council (number 202006100181); the Deutsche Forschungsgemeinschaft (DFG) under Germany's Excellence Strategy within the framework of the Munich Cluster for Systems Neurology (EXC 2145 SyNergy, ID 390857198).

The Spectrum of Cognitive Dysfunction in Amyotrophic Lateral Sclerosis: An Update

Cognitive dysfunction is an important non-motor symptom in amyotrophic lateral sclerosis (ALS) that has a negative impact on survival and caregiver burden. It shows a wide spectrum ranging from subjective cognitive decline to frontotemporal dementia (FTD) and covers various cognitive domains, mainly executive/attention, language and verbal memory deficits. The frequency of cognitive impairment across the different ALS phenotypes ranges from 30% to 75%, with up to 45% fulfilling the criteria of FTD. Significant genetic, clinical, and pathological heterogeneity reflects deficits in various cognitive domains. Modern neuroimaging studies revealed frontotemporal degeneration and widespread involvement of limbic and white matter systems, with hypometabolism of the relevant areas. Morphological substrates are frontotemporal and hippocampal atrophy with synaptic loss, associated with TDP-43 and other co-pathologies, including tau deposition. Widespread functional disruptions of motor and extramotor networks, as well as of frontoparietal, frontostriatal and other connectivities, are markers for cognitive deficits in ALS. Cognitive reserve may moderate the effect of brain damage but is not protective against cognitive decline. The natural history of cognitive dysfunction in ALS and its relationship to FTD are not fully understood, although there is an overlap between the ALS variants and ALS-related frontotemporal syndromes, suggesting a differential vulnerability of motor and non-motor networks. An assessment of risks or the early detection of brain connectivity signatures before structural changes may be helpful in investigating the pathophysiological mechanisms of cognitive impairment in ALS, which might even serve as novel targets for effective disease-modifying therapies.

Novel CSF tau biomarkers can be used for disease staging of sporadic Alzheimer's disease

Biological staging of individuals with Alzheimer's disease (AD) may improve diagnostic and prognostic work-up of dementia in clinical practice and the design of clinical trials. Here, we created a staging model using the Subtype and Stage Inference (SuStaIn) algorithm by evaluating cerebrospinal fluid (CSF) amyloid-β (Aβ) and tau biomarkers in 426 participants from BioFINDER-2, that represent the entire spectrum of AD. The model composition and main analyses were replicated in 222 participants from the Knight ADRC cohort. SuStaIn revealed in the two cohorts that the data was best explained by a single biomarker sequence (one subtype), and that five CSF biomarkers (ordered: Aβ42/40, tau phosphorylation occupancies at the residues 217 and 205 [pT217/T217 and pT205/T205], microtubule-binding region of tau containing the residue 243 [MTBR-tau243], and total tau) were sufficient to create an accurate disease staging model. Increasing CSF stages (0-5) were associated with increased abnormality in other AD-related biomarkers, such as Aβ- and tau-PET, and aligned with different phases of longitudinal biomarker changes consistent with current models of AD progression. Higher CSF stages at baseline were associated with higher hazard ratio of clinical decline. Our findings indicate that a common pathophysiologic molecular pathway develops across all AD patients, and that a single CSF collection is sufficient to reliably indicate the presence of both AD pathologies and the degree and stage of disease progression.

Two distinct trajectories of clinical and neurodegeneration events in Parkinson's disease

Increasing evidence suggests that Parkinson's disease (PD) exhibits disparate spatial and temporal patterns of progression. Here we used a machine-learning technique-Subtype and Stage Inference (SuStaIn) - to uncover PD subtypes with distinct trajectories of clinical and neurodegeneration events. We enrolled 228 PD patients and 119 healthy controls with comprehensive assessments of olfactory, autonomic, cognitive, sleep, and emotional function. The integrity of substantia nigra (SN), locus coeruleus (LC), amygdala, hippocampus, entorhinal cortex, and basal forebrain were assessed using diffusion and neuromelanin-sensitive MRI. SuStaIn model with above clinical and neuroimaging variables as input was conducted to identify PD subtypes. An independent dataset consisting of 153 PD patients and 67 healthy controls was utilized to validate our findings. We identified two distinct PD subtypes: subtype 1 with rapid eye movement sleep behavior disorder (RBD), autonomic dysfunction, and degeneration of the SN and LC as early manifestations, and cognitive impairment and limbic degeneration as advanced manifestations, while subtype 2 with hyposmia, cognitive impairment, and limbic degeneration as early manifestations, followed later by RBD and degeneration of the LC in advanced disease. Similar subtypes were shown in the validation dataset. Moreover, we found that subtype 1 had weaker levodopa response, more GBA mutations, and poorer prognosis than subtype 2. These findings provide new insights into the underlying disease biology and might be useful for personalized treatment for patients based on their subtype.

Data-driven neuropathological staging and subtyping of TDP-43 proteinopathies

TAR DNA-binding protein-43 (TDP-43) accumulation is the primary pathology underlying several neurodegenerative diseases. Charting the progression and heterogeneity of TDP-43 accumulation is necessary to better characterize TDP-43 proteinopathies, but current TDP-43 staging systems are heuristic and assume each syndrome is homogeneous. Here, we use data-driven disease progression modelling to derive a fine-grained empirical staging system for the classification and differentiation of frontotemporal lobar degeneration due to TDP-43 (FTLD-TDP, n = 126), amyotrophic lateral sclerosis (ALS, n = 141) and limbic-predominant age-related TDP-43 encephalopathy neuropathologic change (LATE-NC) with and without Alzheimer's disease (n = 304). The data-driven staging of ALS and FTLD-TDP complement and extend previously described human-defined staging schema for ALS and behavioural variant frontotemporal dementia. In LATE-NC individuals, progression along data-driven stages was positively associated with age, but negatively associated with age in individuals with FTLD-TDP. Using only regional TDP-43 severity, our data driven model distinguished individuals diagnosed with ALS, FTLD-TDP or LATE-NC with a cross-validated accuracy of 85.9%, with misclassifications associated with mixed pathological diagnosis, age and genetic mutations. Adding age and SuStaIn stage to this model increased accuracy to 92.3%. Our model differentiates LATE-NC from FTLD-TDP, though some overlap was observed between late-stage LATE-NC and early-stage FTLD-TDP. We further tested for the presence of subtypes with distinct regional TDP-43 progression patterns within each diagnostic group, identifying two distinct cortical-predominant and brainstem-predominant subtypes within FTLD-TDP and a further two subcortical-predominant and corticolimbic-predominant subtypes within ALS. The FTLD-TDP subtypes exhibited differing proportions of TDP-43 type, while there was a trend for age differing between ALS subtypes. Interestingly, a negative relationship between age and SuStaIn stage was seen in the brainstem/subcortical-predominant subtype of each proteinopathy. No subtypes were observed for the LATE-NC group, despite aggregating individuals with and without Alzheimer's disease and a larger sample size for this group. Overall, we provide an empirical pathological TDP-43 staging system for ALS, FTLD-TDP and LATE-NC, which yielded accurate classification. We further demonstrate that there is substantial heterogeneity amongst ALS and FTLD-TDP progression patterns that warrants further investigation in larger cross-cohort studies.

Gray matter hypoperfusion is a late pathological event in the course of Alzheimer's disease

Several studies have shown decreased cerebral blood flow (CBF) in Alzheimer's disease (AD). However, the role of hypoperfusion in the disease pathogenesis remains unclear. Combining arterial spin labeling MRI, PET, and CSF biomarkers, we investigated the associations between gray matter (GM)-CBF and the key mechanisms in AD including amyloid-β (Aβ) and tau pathology, synaptic and axonal degeneration. Further, we applied a disease progression modeling to characterize the temporal sequence of different AD biomarkers. Lower perfusion was observed in temporo-occipito-parietal cortex in the Aβ-positive cognitively impaired compared to both Aβ-negative and Aβ-positive cognitively unimpaired individuals. In participants along the AD spectrum, GM-CBF was associated with tau, synaptic and axonal dysfunction, but not Aβ in similar cortical regions. Axonal degeneration was further associated with hypoperfusion in cognitively unimpaired individuals. Disease progression modeling revealed that GM-CBF disruption Followed the abnormality of biomarkers of Aβ, tau and brain atrophy. These findings indicate that tau tangles and neurodegeneration are more closely connected with GM-CBF changes than Aβ pathology. Although subjected to the sensitivity of the employed neuroimaging techniques and the modeling approach, these findings suggest that hypoperfusion might not be an early event associated with the build-up of Aβ in preclinical phase of AD.

Uncovering spatiotemporal patterns of atrophy in progressive supranuclear palsy using unsupervised machine learning

To better understand the pathological and phenotypic heterogeneity of progressive supranuclear palsy and the links between the two, we applied a novel unsupervised machine learning algorithm (Subtype and Stage Inference) to the largest MRI data set to date of people with clinically diagnosed progressive supranuclear palsy (including progressive supranuclear palsy-Richardson and variant progressive supranuclear palsy syndromes). Our cohort is comprised of 426 progressive supranuclear palsy cases, of which 367 had at least one follow-up scan, and 290 controls. Of the progressive supranuclear palsy cases, 357 were clinically diagnosed with progressive supranuclear palsy-Richardson, 52 with a progressive supranuclear palsy-cortical variant (progressive supranuclear palsy-frontal, progressive supranuclear palsy-speech/language, or progressive supranuclear palsy-corticobasal), and 17 with a progressive supranuclear palsy-subcortical variant (progressive supranuclear palsy-parkinsonism or progressive supranuclear palsy-progressive gait freezing). Subtype and Stage Inference was applied to volumetric MRI features extracted from baseline structural (T1-weighted) MRI scans and then used to subtype and stage follow-up scans. The subtypes and stages at follow-up were used to validate the longitudinal consistency of subtype and stage assignments. We further compared the clinical phenotypes of each subtype to gain insight into the relationship between progressive supranuclear palsy pathology, atrophy patterns, and clinical presentation. The data supported two subtypes, each with a distinct progression of atrophy: a 'subcortical' subtype, in which early atrophy was most prominent in the brainstem, ventral diencephalon, superior cerebellar peduncles, and the dentate nucleus, and a 'cortical' subtype, in which there was early atrophy in the frontal lobes and the insula alongside brainstem atrophy. There was a strong association between clinical diagnosis and the Subtype and Stage Inference subtype with 82% of progressive supranuclear palsy-subcortical cases and 81% of progressive supranuclear palsy-Richardson cases assigned to the subcortical subtype and 82% of progressive supranuclear palsy-cortical cases assigned to the cortical subtype. The increasing stage was associated with worsening clinical scores, whilst the 'subcortical' subtype was associated with worse clinical severity scores compared to the 'cortical subtype' (progressive supranuclear palsy rating scale and Unified Parkinson's Disease Rating Scale). Validation experiments showed that subtype assignment was longitudinally stable (95% of scans were assigned to the same subtype at follow-up) and individual staging was longitudinally consistent with 90% remaining at the same stage or progressing to a later stage at follow-up. In summary, we applied Subtype and Stage Inference to structural MRI data and empirically identified two distinct subtypes of spatiotemporal atrophy in progressive supranuclear palsy. These image-based subtypes were differentially enriched for progressive supranuclear palsy clinical syndromes and showed different clinical characteristics. Being able to accurately subtype and stage progressive supranuclear palsy patients at baseline has important implications for screening patients on entry to clinical trials, as well as tracking disease progression.

Data-driven neuropathological staging and subtyping of TDP-43 proteinopathies

TAR DNA-binding protein-43 (TDP-43) accumulation is the primary pathology underlying several neurodegenerative diseases. Charting the progression and heterogeneity of TDP-43 accumulation is necessary to better characterise TDP-43 proteinopathies, but current TDP-43 staging systems are heuristic and assume each syndrome is homogeneous. Here, we use data-driven disease progression modelling to derive a fine-grained empirical staging system for the classification and differentiation of frontotemporal lobar degeneration due to TDP-43 (FTLD-TDP, n=126), amyotrophic lateral sclerosis (ALS, n=141) and limbic-predominant age-related TDP-43 encephalopathy neuropathologic change (LATE-NC) with and without Alzheimer’s disease (n=304). The data-driven staging of ALS and FTLD-TDP complement and extend previously described human-defined staging schema for ALS and behavioural variant frontotemporal dementia. In LATE-NC individuals, progression along data-driven stages was positively associated with age, but negatively associated with age in individuals with FTLD-TDP. Using only regional TDP-43 severity, our data driven model distinguished individuals diagnosed with ALS, FTLD-TDP or LATE-NC with a cross-validated accuracy of 85.9%, with misclassifications associated with mixed pathological diagnosis, age and genetic mutations. Adding age and SuStaIn stage to this model increased accuracy to 92.3%. Our model differentiates LATE-NC from FTLD-TDP, though some overlap was observed between late-stage LATE-NC and early-stage FTLD-TDP. We further tested for the presence of subtypes with distinct regional TDP-43 progression patterns within each diagnostic group, identifying two distinct cortical-predominant and brainstem-predominant subtypes within FTLD-TDP and a further two subcortical-predominant and corticolimbic-predominant subtypes within ALS. The FTLD-TDP subtypes exhibited differing proportions of TDP-43 type, while there was a trend for age differing between ALS subtypes. Interestingly, a negative relationship between age and SuStaIn stage was seen in the brainstem/subcortical-predominant subtype of each proteinopathy. No subtypes were observed for the LATE-NC group, despite aggregating AD+ and AD-individuals and a larger sample size for this group. Overall, we provide an empirical pathological TDP-43 staging system for ALS, FTLD-TDP and LATE-NC, which yielded accurate classification. We further demonstrate that there is substantial heterogeneity amongst ALS and FTLD-TDP progression patterns that warrants further investigation in larger cross-cohort studies.