Clinical Dataset Structure: A Universal Framework for Structuring Clinical Research Datasets

Each year, a rapidly growing volume of datasets is shared across the research community. In clinical studies, many data types are collected per participant, such as surveys, vital signs, eye images, and more. There is currently no consensus on how to organize multimodal data and include related information known as metadata. Standards like BIDS (Brain Imaging Data Structure) exist but only for structuring individual modalities. To address this challenge in the AI Ready and Exploratory Atlas for Diabetes Insights (AI-READI) project, we developed the Clinical Dataset Structure (CDS). The CDS provides a simple and intuitive way to organize clinical research data and metadata in line with the FAIR Principles. It recommends organizing multimodal clinical research datasets into one folder per data type, named as per a set convention, where applicable standard structure must then be followed within each folder.