Unraveling the heterogeneity in Alzheimer's disease progression across multiple cohorts and the implications for data‐driven disease modeling

Birkenbihl, Colin; Salimi, Yasamin; Fröhlich, Holger; Initiative, Japanese Alzheimer’s Disease Neuroimaging; Initiative, Alzheimer’s Disease Neuroimaging

doi:10.1002/alz.12387

Cited by 25 publications

(14 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This increased visibility and discoverability will promote information and data and sample exchange among researchers. EPND could be best positioned to make a large number of cohort datasets discoverable and interoperable for future research, as heterogeneity in cohort datasets, linked to the use of different data models, sampling methods, and recruitment criteria, compounds these issues and further impedes the use of data and samples for large-scale research ( 12 ). Entry into EPND's catalog – in datasets or completed case studies – will require minimal effort on the part of contributors, making it easy for researchers to add value to the community, and ensuring they have opportunities to participate in studies before they are published.…”

Section: Epnd: Opportunities To Accelerate Neurodegenerative Disease ...mentioning

confidence: 99%

Data and sample sharing as an enabler for large-scale biomarker research and development: The EPND perspective

Bose

Brookes²,

Scordis³

et al. 2022

Front. Neurol.

View full text Add to dashboard Cite

Biomarker discovery, development, and validation are reliant on large-scale analyses of high-quality samples and data. Currently, significant quantities of data and samples have been generated by European studies on Alzheimer's disease (AD) and other neurodegenerative diseases (NDD), representing a valuable resource for developing biomarkers to support early detection of disease, treatment monitoring, and patient stratification. However, discovery of, access to, and sharing of data and samples from AD and NDD research are hindered both by silos that limit collaboration, and by the array of complex requirements for secure, legal, and ethical sharing. In this Perspective article, we examine key challenges currently hampering large-scale biomarker research, and outline how the European Platform for Neurodegenerative Diseases (EPND) plans to address them. The first such challenge is a fragmented landscape filled with technical barriers that make it difficult to discover and access high-quality samples and data in one location. A second challenge is related to the complex array of legal and ethical requirements that must be navigated by researchers when sharing data and samples, to ensure compliance with data protection regulations and research ethics. Another challenge is the lack of broad-scale collaboration and opportunities to facilitate partnerships between data and sample contributors and researchers, in addition to a lack of regulatory engagement early in the research process to enable validation of potential biomarkers. A further challenge facing projects is the need to remain sustainable beyond initial funding periods, ensuring data and samples are shared and reused, thereby driving further research and innovation. In addressing these challenges, EPND will enable an environment of faster and more disruptive research on diagnostics and disease-modifying therapies for Alzheimer's disease and other neurodegenerative diseases.

show abstract

Section: Epnd: Opportunities To Accelerate Neurodegenerative Disease ...mentioning

confidence: 99%

Data and sample sharing as an enabler for large-scale biomarker research and development: The EPND perspective

Bose

Brookes²,

Scordis³

et al. 2022

Front. Neurol.

View full text Add to dashboard Cite

show abstract

“…Individual organizations, such as hospitals, pharmaceutical companies, and health insurance providers are currently limited in their ability to collect data that are fully representative of a disease population. This issue is especially pronounced in clinical studies, where patients are usually recruited based on predefined inclusion and exclusion criteria that introduce cohort-specific statistical biases 2 . These biases, in turn, can negatively impact the generalization ability of machine learning models, since the usual i.i.d.…”

Section: Introductionmentioning

confidence: 99%

Generation of realistic synthetic data using Multimodal Neural Ordinary Differential Equations

et al. 2022

Self Cite

View full text Add to dashboard Cite

Individual organizations, such as hospitals, pharmaceutical companies, and health insurance providers, are currently limited in their ability to collect data that are fully representative of a disease population. This can, in turn, negatively impact the generalization ability of statistical models and scientific insights. However, sharing data across different organizations is highly restricted by legal regulations. While federated data access concepts exist, they are technically and organizationally difficult to realize. An alternative approach would be to exchange synthetic patient data instead. In this work, we introduce the Multimodal Neural Ordinary Differential Equations (MultiNODEs), a hybrid, multimodal AI approach, which allows for generating highly realistic synthetic patient trajectories on a continuous time scale, hence enabling smooth interpolation and extrapolation of clinical studies. Our proposed method can integrate both static and longitudinal data, and implicitly handles missing values. We demonstrate the capabilities of MultiNODEs by applying them to real patient-level data from two independent clinical studies and simulated epidemiological data of an infectious disease.

show abstract

“…With the disproportional increase of the elderly population, the prevalence of AD will approach around 132 million worldwide by 2050, and, thus, has become a tremendous public health and socioeconomic challenge of the twenty-first century (Alzheimer's-Association 2021). The scientific approach to AD suffers from mismatches between clinical, pathological and technological data, and from heterogeneity in cohort datasets impeding the reproducibility of results (Birkenbihl et al 2021) and causing difficulties in conceiving diagnostic gold standards and creating models for drug discovery and screening (Ferrari and Sorbi 2021). As available treatments only target symptoms and neither slow nor reverse the progression of the disease, the development of disease-modifying therapies is urgent (Long and Holtzman 2019).…”

Section: Introductionmentioning

confidence: 99%

Recent update on the heterogeneity of the Alzheimer’s disease spectrum

Jellinger¹

2021

J Neural Transm

View full text Add to dashboard Cite

Alzheimer's disease (AD), the most common form of dementia worldwide, is a mixed proteinopathy (β-amyloid, tau and other proteins). Classically defined as a clinicopathological entity, AD is a heterogeneous, multifactorial disorder with various pathobiological subtypes showing different forms of cognitive presentation, currently referred to as the Alzheimer spectrum or continuum. Its morphological hallmarks are extracellular β-amyloid (amyloid plaques) and intraneuronal tau aggregates forming neurofibrillary tangles and neurites, vascular amyloid deposits (cerebral amyloid angiopathy), synapse and neuronal loss as well as neuroinflammation and reactive astrogliosis, leading to cerebral atrophy and progressive mental/cognitive impairment (dementia). In addition to "classical" AD, several subtypes with characteristic regional patterns of tau pathology have been segregated that are characterized by distinct clinical features, differences in age, sex distribution, disease duration, cognitive status, APOE genotype, and biomarker levels. In addition to four major subtypes based on the distribution of tau pathology and brain atrophy (typical, limbic predominant, hippocampal sparing, and minimal atrophy), several other clinical variants (non-amnestic, corticobasal, behavioral/dysexecutive, posterior cortical variants, etc.) have been identified. These heterogeneous AD variants are characterized by different patterns of key neuronal network destructions, in particular the default-mode network that is responsible for cognitive decline. Other frequent age-related co-pathologies, e.g., cerebrovascular lesions, Lewy and TDP-43 pathologies, hippocampal sclerosis, or argyrophilic grain disease, essentially influence the clinical picture and course of AD, and can challenge our understanding of this disorder including the threshold and causal relevance of each individual pathology. Unravelling the clinico-morphological heterogeneity among the AD spectrum entities is important for better elucidation of the pathogenic mechanisms affecting the aging brain that may enable a broader diagnostic coverage of AD as a basis for implementing precision medicine approaches and for developing preventive and ultimately disease-modifying therapies for this devastating disorder.

show abstract

Unraveling the heterogeneity in Alzheimer's disease progression across multiple cohorts and the implications for data‐driven disease modeling

Cited by 25 publications

References 33 publications

Data and sample sharing as an enabler for large-scale biomarker research and development: The EPND perspective

Data and sample sharing as an enabler for large-scale biomarker research and development: The EPND perspective

Generation of realistic synthetic data using Multimodal Neural Ordinary Differential Equations

Recent update on the heterogeneity of the Alzheimer’s disease spectrum

Contact Info

Product

Resources

About