Exploring the Dataset Landscape in Alzheimer's Disease


Data collected in cohort studies lay the groundwork for a plethora of Alzheimer’s disease (AD) research endeavors. In this work, we systematically sketch out the AD cohort data landscape.

We accessed and investigated major AD cohort datasets with the aim of 1) characterizing their underlying data, 2) assessing the quantity and availability of data, and 3) evaluating the interoperability across these distinct cohort datasets. This web-application allows for exploration of the AD data landscape and helps researchers to identify the most suitable datasets for their projects.

Below the publication outlining this work:

Birkenbihl, C, Salimi, Y, Domingo‐Fernándéz, D, et al. Evaluating the Alzheimer's disease data landscape (2020). Alzheimer's & Dementia, 6:e12102.

Cohort Comparison


In the following section you can find an overview of the investigated cohorts. We describe the cohort size, provide basic information regarding the study design and links for data access requests. Additionally, we evaluated and compared the distributions of key Alzheimer's disease biomarkers.

9 Cohorts
60004 Patients
13 Compared Modalities

Ethnoracial Diversity

The displayed pie chart visualizes the ethnoracial diversity in the investigated cohorts. With ethnoracial factors being an important characteristic with regard to Alzheimer’s disease (Babulal et al. 2019), we observe an evident bias towards white/caucasian individuals in the data landscape. Following the link, you can find one chart per cohort illustrating the diversity in that cohort.

Total of All Studies

Modality Overview

In the context of this work, we compared the availability of data modalities across the investigated cohort studies. You can explore both our findings and the employed curation criteria following the links below.

Heatmap Screenshot
Feature Mapping

Feature Mappings

In this section you can investigate the interoperability between the datasets. We conceptually mapped and visualized a subset of features.

Longitudinal Follow-up

Using the following link, you can explore interactive visualizations displaying the longitudinal follow-up and participant drop-out encountered in the included studies. Furthermore, we show the relative longitudinal coverage for important Alzheimer’s disease biomarkers per cohort.

Cohort Comparison


Projects in which AData(Viewer) is currently used.


Virtual Brain Cloud

Personalized Recommendations
for Neurodegenerative Diseases
Read More


Organising Knowledge about Neurodegenerative Disease Mechanisms
Read More


European prevention of Alzheimer’s dementia consortium
Read More

This work has received support from the EU/EFPIA Innovative Medicines Initiative Joint Undertaking 'AETIONOMY' (grant n° 115568), and 'EPAD' (grant n° 115736), and additionally from the H2020 project 'Virtual Brain Cloud' (grant n° 826421).

Contact Us

Prof. Dr. Martin Hofmann-Apitius

Head of the Bioinformatics department.

Prof. Dr. Martin Hofmann-Apitius

Martin is leading the Department of Bioinformatics at the Fraunhofer Institute for Algorithms and Scientific Computing (SCAI) in Sankt Augustin (Germany), a governmental not-for-profit, applied research institute. He is also Professor for Applied Life Science Informatics at Bonn-Aachen International Center for Information Technology (B-IT). He is (co-) author of more than 150 scientific publications.

Colin Birkenbihl

PhD student.

Colin Birkenbihl

Colin is currently pursuing his PhD. He is involved in multiple large EU projects (AETIONOMY, EPAD, RADAR-AD) and is deputy lead of a work package in the Horizon2020 project TheVirtualBrain-Cloud. His main focus of work is data mining, machine learning, and statistics. Applying these skill sets, he tries to build comparative models on Alzheimer’s disease data.