Evaluating the Alzheimer's disease data landscape

Birkenbihl, Colin; Salimi, Yasamin; Domingo‐Fernándéz, Daniel; Lovestone, Simon; Fröhlich, Holger; Hofmann‐Apitius, Martin

doi:10.1002/trc2.12102

Cited by 30 publications

(37 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Developing robust, trustworthy AI approaches is a challenging task that requires a deep understanding of the application domain, the available data and the technical approach [ 142 , 146 , 150 ]. This marks it a highly interdisciplinary endeavour where multiple experts need to collaborate.…”

Section: Conclusion and Expert Recommendations In The Framework Of 3p Medicinementioning

confidence: 99%

Caution, “normal” BMI: health risks associated with potentially masked individual underweight—EPMA Position Paper 2021

et al. 2021

Self Cite

View full text Add to dashboard Cite

An increasing interest in a healthy lifestyle raises questions about optimal body weight. Evidently, it should be clearly discriminated between the standardised “normal” body weight and individually optimal weight. To this end, the basic principle of personalised medicine “one size does not fit all” has to be applied. Contextually, “normal” but e.g. borderline body mass index might be optimal for one person but apparently suboptimal for another one strongly depending on the individual genetic predisposition, geographic origin, cultural and nutritional habits and relevant lifestyle parameters—all included into comprehensive individual patient profile. Even if only slightly deviant, both overweight and underweight are acknowledged risk factors for a shifted metabolism which, if being not optimised, may strongly contribute to the development and progression of severe pathologies. Development of innovative screening programmes is essential to promote population health by application of health risks assessment, individualised patient profiling and multi-parametric analysis, further used for cost-effective targeted prevention and treatments tailored to the person. The following healthcare areas are considered to be potentially strongly benefiting from the above proposed measures: suboptimal health conditions, sports medicine, stress overload and associated complications, planned pregnancies, periodontal health and dentistry, sleep medicine, eye health and disorders, inflammatory disorders, healing and pain management, metabolic disorders, cardiovascular disease, cancers, psychiatric and neurologic disorders, stroke of known and unknown aetiology, improved individual and population outcomes under pandemic conditions such as COVID-19. In a long-term way, a significantly improved healthcare economy is one of benefits of the proposed paradigm shift from reactive to Predictive, Preventive and Personalised Medicine (PPPM/3PM). A tight collaboration between all stakeholders including scientific community, healthcare givers, patient organisations, policy-makers and educators is essential for the smooth implementation of 3PM concepts in daily practice.

show abstract

Section: Conclusion and Expert Recommendations In The Framework Of 3p Medicinementioning

confidence: 99%

Caution, “normal” BMI: health risks associated with potentially masked individual underweight—EPMA Position Paper 2021

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…It allows researchers to adequately understand and characterize performances measured via external validation of statistical and machine learning models developed on another cohort. In conclusion, our approach allows for better understanding of statistical differences that have previously been reported between various AD studies 13 …”

Section: Introductionmentioning

confidence: 84%

“…Overall, the discovered heterogeneity could likely stem from differences in the recruitment processes of cohort studies. Compositional shifts across sampled populations pose a critical confounder comparing cohort datasets and model performance 13 . Here, statistical matching could potentially help to identify comparable subsets.…”

Section: Discussionmentioning

confidence: 99%

“…Furthermore, cohort study participants are recruited according to specific inclusion and exclusion criteria defined based on the goals of the study (e.g., selection of specific age ranges or risk factors). These specific sampling procedures shape potentially distinct statistical distributions from which each study's participants are recruited and, in turn, inevitably introduce cohort‐specific statistical biases into the collected dataset itself 13,14 . These aspects potentially violate the fundamental assumption behind data mining and machine learning approaches that the participants of a validation dataset constitute a representative sample of the same population from which the original training data were drawn (Figure S1 in supporting information).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Birkenbihl

Salimi

Fröhlich

et al. 2021

Alzheimer's & Dementia

Self Cite

View full text Add to dashboard Cite

Introduction Given study‐specific inclusion and exclusion criteria, Alzheimer's disease (AD) cohort studies effectively sample from different statistical distributions. This heterogeneity can propagate into cohort‐specific signals and subsequently bias data‐driven investigations of disease progression patterns. Methods We built multi‐state models for six independent AD cohort datasets to statistically compare disease progression patterns across them. Additionally, we propose a novel method for clustering cohorts with regard to their progression signals. Results We identified significant differences in progression patterns across cohorts. Models trained on cohort data learned cohort‐specific effects that bias their estimations. We demonstrated how six cohorts relate to each other regarding their disease progression. Discussion Heterogeneity in cohort datasets impedes the reproducibility of data‐driven results and validation of progression models generated on single cohorts. To ensure robust scientific insights, it is advisable to externally validate results in independent cohort datasets. The proposed clustering assesses the comparability of cohorts in an unbiased, data‐driven manner.

show abstract

“…However, in a recent study, we observed that the information gained through such metadata-driven cohort assessments differs from the content that is factually shared with researchers after successful access applications [15].…”

Section: Introductionmentioning

confidence: 91%

ADataViewer: Exploring Semantically Harmonized Alzheimer’s Disease Cohort Datasets

Salimi

Domingo‐Fernándéz

Bobis-Álvarez³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

INTRODUCTION: Currently, AD cohort datasets are difficult to find, lack across-cohort interoperability, and the content of the shared datasets often only becomes clear to third-party researchers once data access has been granted. METHODS: We accessed and systematically investigated the content of 20 major AD cohort datasets on data-level. A medical professional and a data specialist manually curated and semantically harmonized the acquired datasets. We developed a platform that facilitates data exploration. RESULTS: We present ADataViewer, an interactive platform that facilitates the exploration of 20 cohort datasets with respect to longitudinal follow-up, demographics, ethnoracial diversity, measured modalities, and statistical properties of individual variables. Additionally, we publish a variable mapping catalog harmonizing 1,196 variables across the 20 cohorts. The platform is available under https://adata.scai.fraunhofer.de/. DISCUSSION: ADataViewer supports robust data-driven research by transparently displaying cohort dataset content and suggesting datasets suited for discovery and validation studies based on selected variables of interest.

show abstract

Evaluating the Alzheimer's disease data landscape

Cited by 30 publications

References 26 publications

Caution, “normal” BMI: health risks associated with potentially masked individual underweight—EPMA Position Paper 2021

Caution, “normal” BMI: health risks associated with potentially masked individual underweight—EPMA Position Paper 2021

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

ADataViewer: Exploring Semantically Harmonized Alzheimer’s Disease Cohort Datasets

Contact Info

Product

Resources

About