The ABCD-J Project
The ABCD-J research community project is a collaboration between five research institutions in the German state of North Rhine-Westphalia: University Clinic RWTH Aachen, University Clinic Bonn, University Clinic Köln, University Clinic Düsseldorf and Research Centre Jülich. The overarching goal of ABCD-J is to elevate existing technical solutions for research practice adoption. From the social perspective, the ABCD-J project aims to promote and facilitate collaboration between multiple research centres, while from the technical perspective the project will accelerate research through homogenization of workflows and processes, with particular emphasis on digital biomarker development.
ABCD-J Platform
The ABCD-J platform provides clinical researchers in the field of neurology and psychiatry with a digital infrastructure that allows 1) the collection of data using mobile health technologies, 2) the harmonization and management of data according to FAIR (Findable, Accessible, Interoperable, Reusable) principles, and 3) the automated analysis of data using machine learning algorithms with the goal of developing digital biomarkers.
JTrack
The JTrack platform consists of the two JTrack applications EMA and Social, and a server structure to enable central data collection. The platform was developed to gather and study specific digital phenotyping information about smartphone usage, sensor data and participants' daily lives. The JTrack platform was released as an open source collaboration tool to enable clinical and behavioral researchers to collect their own digital phenotyping data from specific study populations. In the framework of the ABCD-J project, JTrack will be integrated into clinical studies across all partner sites, allowing for a harmonized and standardized evaluation of different clinical cohorts.
DataLad
DataLad is a free and open source distributed data management system that keeps track of data, creates structure, ensures reproducibility, supports collaboration, and integrates with widely used data infrastructure.
julearn
Machine learning workflows, including model assessment and comparison, are integrated into a library known as 'julearn'. This library enables users to effortlessly design and test machine learning models directly from pandas DataFrames, while maintaining the flexibility of utilizing scikit-learn's data processing tools and models.
ABCD-J Data Catalog
The data catalog showcases a wide variety of datasets collected and shared by partner institutions in the ABCD-J community. Did you know that you can link your data to the catalog without having to upload it?
Link your data!
