Search

The Dementias Platform UK (DPUK) Data Portal holds over 60 cohort datasets from over 3 million participants with a range of multi-modal data including neuroimaging and genomics. This has meant we have seen an increasing interest in the development of AI models with the potential for clinical implementation. However, this presents a unique challenge to disclosure control when it comes to assessing these AI models for release due to the risk of attacks such as membership inference, model inversion or even just vulnerabilities in the models like overfitting. This is why we hosted a series of workshops bringing together members of the public, expert researchers, and data owners across the UK to build a framework for allowing the safe development and release of AI models trained on sensitive healthcare data. From this, we have put together recommendations and guidelines for the use of privacy-preserving techniques in AI models to protect patient privacy, and to allow the safe deployment of these models outside of trusted research environments. We also identified the unique challenges to privacy and implementation of privacy-preserving techniques in AI models regarding the use of complex data such as neuroimaging and genomics. This framework has created a path forward for supporting safe AI model development which takes into consideration rapidly evolving ethical, legal and privacy considerations.

Abstract There is extensive synaptic loss from frontotemporal lobar degeneration, in preclinical models and human in vivo and post mortem studies. Understanding the consequences of synaptic loss for network function is important to support translational models and guide future therapeutic strategies. To examine this relationship, we recruited 55 participants with syndromes associated with frontotemporal lobar degeneration and 24 healthy controls. We measured synaptic density with positron emission tomography using the radioligand [11C]UCB-J, which binds to the presynaptic vesicle glycoprotein SV2A, neurite dispersion with diffusion magnetic resonance imaging, and network function with task-free magnetic resonance imaging functional connectivity. Synaptic density and neurite dispersion in patients was associated with reduced connectivity beyond atrophy. Functional connectivity moderated the relationship between synaptic density and clinical severity. Our findings confirm the importance of synaptic loss in frontotemporal lobar degeneration syndromes, and the resulting effect on behaviour as a function of abnormal connectivity.

Abstract The development of novel treatments for Progressive Supranuclear Palsy (PSP) is hindered by a knowledge gap of the impact of neurodegenerative neuropathology on brain structure and function. The current standard practice for measuring postmortem tau histology is semi-quantitative assessment, which is prone to inter-rater variability, time-consuming and difficult to scale. We developed and optimized a tau aggregate type-specific quantification pipeline for cortical and subcortical regions, in human brain donors with PSP. We quantified 4 tau objects (‘neurofibrillary tangles’, ‘coiled bodies’, ‘tufted astrocytes’, and ‘tau fragments’) using a probabilistic random forest machine learning classifier. The tau pipeline achieved high classification performance (F1-score > 0.90), comparable to neuropathologist inter-rater reliability in the held-out test set. Using 240 AT8 slides from 32 postmortem brains, the tau burden was correlated against the PSP pathology staging scheme using Spearman’s rank correlation. We assessed whether clinical severity (PSP rating scale, PSPRS) score reflects neuropathological severity inferred from PSP stage and tau burden using Bayesian linear mixed regression. Tufted astrocyte density in cortical regions and coiled body density in subcortical regions showed the highest correlation to PSP stage (r = 0.62 and r = 0.38, respectively). Using traditional manual staging, only PSP patients in stage 6, not earlier stages, had significantly higher clinical severity than stage 2. Cortical tau density and neurofibrillary tangle density in subcortical regions correlated with clinical severity. Overall, our data indicate the potential for highly accurate digital tau aggregate type-specific quantification for neurodegenerative tauopathies; and the importance of studying tau aggregate type-specific burden in different brain regions as opposed to overall tau, to gain insights into the pathogenesis and progression of tauopathies.

Abstract Background Identifying prediagnostic neurodegenerative disease is a critical issue in neurodegenerative disease research, and Alzheimer’s disease (AD) in particular, to identify populations suitable for preventive and early disease-modifying trials. Evidence from genetic and other studies suggests the neurodegeneration of Alzheimer’s disease measured by brain atrophy starts many years before diagnosis, but it is unclear whether these changes can be used to reliably detect prediagnostic sporadic disease. Methods We trained a Bayesian machine learning neural network model to generate a neuroimaging phenotype and AD score representing the probability of AD using structural MRI data in the Alzheimer’s Disease Neuroimaging Initiative (ADNI) Cohort (cut-off 0.5, AUC 0.92, PPV 0.90, NPV 0.93). We go on to validate the model in an independent real-world dataset of the National Alzheimer’s Coordinating Centre (AUC 0.74, PPV 0.65, NPV 0.80) and demonstrate the correlation of the AD-score with cognitive scores in those with an AD-score above 0.5. We then apply the model to a healthy population in the UK Biobank study to identify a cohort at risk for Alzheimer’s disease. Results We show that the cohort with a neuroimaging Alzheimer’s phenotype has a cognitive profile in keeping with Alzheimer’s disease, with strong evidence for poorer fluid intelligence, and some evidence of poorer numeric memory, reaction time, working memory, and prospective memory. We found some evidence in the AD-score positive cohort for modifiable risk factors of hypertension and smoking. Conclusions This approach demonstrates the feasibility of using AI methods to identify a potentially prediagnostic population at high risk for developing sporadic Alzheimer’s disease.

Abstract Progress in dementia research has been limited, with substantial gaps in our knowledge of targets for prevention, mechanisms for disease progression, and disease-modifying treatments. The growing availability of multimodal data sets opens possibilities for the application of machine learning and artificial intelligence (AI) to help answer key questions in the field. We provide an overview of the state of the science, highlighting current challenges and opportunities for utilisation of AI approaches to move the field forward in the areas of genetics, experimental medicine, drug discovery and trials optimisation, imaging, and prevention. Machine learning methods can enhance results of genetic studies, help determine biological effects and facilitate the identification of drug targets based on genetic and transcriptomic information. The use of unsupervised learning for understanding disease mechanisms for drug discovery is promising, while analysis of multimodal data sets to characterise and quantify disease severity and subtype are also beginning to contribute to optimisation of clinical trial recruitment. Data-driven experimental medicine is needed to analyse data across modalities and develop novel algorithms to translate insights from animal models to human disease biology. AI methods in neuroimaging outperform traditional approaches for diagnostic classification, and although challenges around validation and translation remain, there is optimism for their meaningful integration to clinical practice in the near future. AI-based models can also clarify our understanding of the causality and commonality of dementia risk factors, informing and improving risk prediction models along with the development of preventative interventions. The complexity and heterogeneity of dementia requires an alternative approach beyond traditional design and analytical approaches. Although not yet widely used in dementia research, machine learning and AI have the potential to unlock current challenges and advance precision dementia medicine.

Background: Neurotransmitters deficits in Frontotemporal Dementia (FTD) are still poorly understood. Better knowledge of neurotransmitters impairment, especially in prodromal disease stages, might tailor symptomatic treatment approaches. Methods: In the present study, we applied JuSpace toolbox, which allowed for cross-modal correlation of Magnetic Resonance Imaging (MRI)-based measures with nuclear imaging derived estimates covering various neurotransmitter systems including dopaminergic, serotonergic, noradrenergic, GABAergic and glutamatergic neurotransmission.We included 392 mutation carriers (157 GRN, 164 C9orf72, 71 MAPT), together with 276 non-carrier cognitively healthy controls (HC). We tested if the spatial patterns of grey matter volume (GMV) alterations in mutation carriers (relative to HC) are correlated with specific neurotransmitter systems in prodromal (CDR® plus NACC FTLD = 0.5) and in symptomatic (CDR® plus NACC FTLD≥1) FTD. Results: In prodromal stages of C9orf72 disease, voxel-based brain changes were significantly associated with spatial distribution of dopamine and acetylcholine pathways; in prodromal MAPT disease with dopamine and serotonin pathways, while in prodromal GRN disease no significant findings were reported (p

Abstract We envisage the development of new Brain Health Services to achieve primary and secondary dementia prevention. These services will complement existing memory clinics by targeting cognitively unimpaired individuals, where the focus is on risk profiling and personalized risk reduction interventions rather than diagnosing and treating late-stage disease. In this article, we review key potentially modifiable risk factors and genetic risk factors and discuss assessment of risk factors as well as additional fluid and imaging biomarkers that may enhance risk profiling. We then outline multidomain measures and risk profiling and provide practical guidelines for Brain Health Services, with consideration of outstanding uncertainties and challenges. Users of Brain Health Services should undergo risk profiling tailored to their age, level of risk, and availability of local resources. Initial risk assessment should incorporate a multidomain risk profiling measure. For users aged 39–64, we recommend the Cardiovascular Risk Factors, Aging, and Incidence of Dementia (CAIDE) Dementia Risk Score, whereas for users aged 65 and older, we recommend the Brief Dementia Screening Indicator (BDSI) and the Australian National University Alzheimer’s Disease Risk Index (ANU-ADRI). The initial assessment should also include potentially modifiable risk factors including sociodemographic, lifestyle, and health factors. If resources allow, apolipoprotein E ɛ4 status testing and structural magnetic resonance imaging should be conducted. If this initial assessment indicates a low dementia risk, then low intensity interventions can be implemented. If the user has a high dementia risk, additional investigations should be considered if local resources allow. Common variant polygenic risk of late-onset AD can be tested in middle-aged or older adults. Rare variants should only be investigated in users with a family history of early-onset dementia in a first degree relative. Advanced imaging with 18-fluorodeoxyglucose positron emission tomography (FDG-PET) or amyloid PET may be informative in high risk users to clarify the nature and burden of their underlying pathologies. Cerebrospinal fluid biomarkers are not recommended for this setting, and blood-based biomarkers need further validation before clinical use. As new technologies become available, advances in artificial intelligence are likely to improve our ability to combine diverse data to further enhance risk profiling. Ultimately, Brain Health Services have the potential to reduce the future burden of dementia through risk profiling, risk communication, personalized risk reduction, and cognitive enhancement interventions.

Abstract Synaptic loss is an early and clinically relevant feature of many neurodegenerative diseases. Here we assess three adults at risk of frontotemporal dementia from C9orf72 mutation, using [11C]UCB‐J PET to quantify synaptic density in comparison with 19 healthy controls and one symptomatic patient with behavioural variant frontotemporal dementia. The three pre‐symptomatic C9orf72 carriers showed reduced synaptic density in the thalamus compared to controls, and there was an additional extensive synaptic loss in frontotemporal regions of the symptomatic patient. [11C]UCB‐J PET may facilitate early, pre‐symptomatic assessment, monitoring of disease progression and evaluation of new preventive treatment strategies for frontotemporal dementia.

Abstract Individuals with mild cognitive impairment (MCI) of different subtypes show distinct alterations in network patterns. The first aim of this study is to identify the subtypes of MCI by employing a regional radiomics similarity network (R2SN). The second aim is to characterize the abnormality patterns associated with the clinical manifestations of each subtype. An individual‐level R2SN is constructed for N = 605 normal controls (NCs), N = 766 MCI patients, and N = 283 Alzheimer's disease (AD) patients. MCI patients’ R2SN profiles are clustered into two subtypes using nonnegative matrix factorization. The patterns of brain alterations, gene expression, and the risk of cognitive decline in each subtype are evaluated. MCI patients are clustered into “similar to the pattern of NCs” (N‐CI, N = 252) and “similar to the pattern of AD” (A‐CI, N = 514) subgroups. Significant differences are observed between the subtypes with respect to the following: 1) clinical measures; 2) multimodal neuroimaging; 3) the proportion of progression to dementia (61.54% for A‐CI and 21.77% for N‐CI) within three years; 4) enriched genes for potassium‐ion transport and synaptic transmission. Stratification into the two subtypes provides new insight for risk assessment and precise early intervention for MCI patients.

Abstract Introduction Although widespread cortical asymmetries have been identified in Alzheimer's disease (AD), thalamic asymmetries and their relevance to clinical severity in AD remain unclear. Methods Lateralization indices were computed for individual thalamic subnuclei of 65 participants (33 healthy controls, 14 amyloid‐positive patients with mild cognitive impairment, and 18 patients with AD dementia). We compared lateralization indices across diagnostic groups and correlated them with clinical measures. Results Although overall asymmetry of the thalamus did not differ between groups, greater leftward lateralization of atrophy in the ventral nuclei was demonstrated in AD, compared with controls and amyloid‐positive mild cognitive impairment. Increased posterior ventrolateral and ventromedial nuclei asymmetry were associated with worse cognitive dysfunction, informant‐reported neuropsychiatric symptoms, and functional ability. Discussion Leftward ventral thalamic atrophy was associated with disease severity in AD. Our findings suggest the clinically relevant involvement of thalamic nuclei in the pathophysiology of AD.

Mutations in the granulin gene (GRN) cause familial frontotemporal dementia. Understanding the structural brain changes in presymptomatic GRN carriers would enforce the use of neuroimaging biomarkers for early diagnosis and monitoring. We studied 100 presymptomatic GRN mutation carriers and 94 noncarriers from the Genetic Frontotemporal dementia initiative (GENFI), with MRI structural images. We analyzed 3T MRI structural images using the FreeSurfer pipeline to calculate the whole brain cortical thickness (CTh) for each subject. We also perform a vertex-wise general linear model to assess differences between groups in the relationship between CTh and diverse covariables as gender, age, the estimated years to onset and education. We also explored differences according to TMEM106B genotype, a possible disease modifier. Whole brain CTh did not differ between carriers and noncarriers. Both groups showed age-related cortical thinning. The group-by-age interaction analysis showed that this age-related cortical thinning was significantly greater in GRN carriers in the left superior frontal cortex. TMEM106B did not significantly influence the age-related cortical thinning. Our results validate and expand previous findings suggesting an increased CTh loss associated with age and estimated proximity to symptoms onset in GRN carriers, even before the disease onset.

Abstract Introduction The deposition of neurofibrillary tangles in neurodegenerative disorders is associated with neuronal loss on autopsy; however, their in vivo associations with atrophy across the continuum of Alzheimer's disease (AD) remain unclear. Methods We estimated cortical thickness, tau ([18F]‐AV‐1451), and amyloid β (Aβ) status ([11C]‐PiB) in 47 subjects who were stratified into Aβ− (14 healthy controls and six mild cognitive impairment–Aβ−) and Aβ+ (14 mild cognitive impairment–Aβ+ and 13 AD) groups. Results Compared with the Aβ− group, tau was increased in widespread regions whereas cortical thinning was restricted to the temporal cortices. Increased tau binding was associated with cortical thinning in each Aβ group. Locally, regional tau was associated with temporoparietal atrophy. Discussion These findings position tau as a promising therapeutic target. Further studies are needed to elucidate the casual relationships between tau pathology and trajectories of atrophy in AD.

This paper summarises the current status of two novel short cognitive tests (SCT), known as Test Your Memory (TYM) and Test Your Memory for Mild Cognitive Impairment (TYM-MCI). The history of and recent research on the TYM and TYM-MCI are summarised in applications for Alzheimer’s and non-Alzheimer’s dementia and mild cognitive impairment. The TYM test can be used in a general neurology clinic and can help distinguish patients with Alzheimer’s disease (AD) from those with no neurological cause for their memory complaints. An adapted tele-TYM test administered by telephone to patients produces scores which correlate strongly with the clinic-administered Addenbrookes Cognitive Examination revised (ACE-R) test and can identify patients with dementia. Patients with AD decline on the TYM test at a rate of 3.6–4.1 points/year.

Cognitive problems are a major factor determining quality of life of patients with Parkinson's disease. These include deficits in inhibitory control, ranging from subclinical alterations in decision-making to severe impulse control disorders. Based on preclinical studies, we proposed that Parkinson's disease does not cause a unified disorder of inhibitory control, but rather a set of impulsivity factors with distinct psychological profiles, anatomy and pharmacology. We assessed a broad set of measures of the cognitive, behavioural and temperamental/trait aspects of impulsivity. Sixty adults, including 30 idiopathic Parkinson's disease patients (Hoehn and Yahr stage I-III) and 30 healthy controls, completed a neuropsychological battery, objective behavioural measures and self-report questionnaires. Univariate analyses of variance confirmed group differences in nine out of eleven metrics. We then used factor analysis (principal components method) to identify the structure of impulsivity in Parkinson's disease. Four principal factors were identified, consistent with four different mechanisms of impulsivity, explaining 60% of variance. The factors were related to (1) tests of response conflict, interference and self assessment of impulsive behaviours on the Barrett Impulsivity Scale, (2) tests of motor inhibitory control, and the self-report behavioural approach system, (3) time estimation and delay aversion, and (4) reflection in hypothetical scenarios including temporal discounting. The different test profiles of these four factors were consistent with human and comparative studies of the pharmacology and functional anatomy of impulsivity. Relationships between each factor and clinical and demographic features were examined by regression against factor loadings. Levodopa dose equivalent was associated only with factors (2) and (3). The results confirm that impulsivity is common in Parkinson's disease, even in the absence of impulse control disorders, and that it is not a unitary phenomenon. A better understanding of the structure of impulsivity in Parkinson's disease will support more evidence-based and effective strategies to treat impulsivity.