Common data model for COVID-19 datasets

• DOI: 10.1093/bioinformatics/btac651
• Publication Date: 2022-10-28T04:53:43Z
• Authors: Philipp Wegner; Geena Mariya Jose; Vanessa Lage-Rupp...; Sepehr Golriz Kha...; Bide Zhang; Stephan Springstubbe; Marc Jacobs; Thomas Linden; Cindy Ku; Bruce Schultz; Martin Hofmann-Ap...; Alpha Tom Kodamullil
• Keywords: Applications Note; 0303 health sciences; 03 medical and health sciences; Humans; COVID-19; Pandemics; Algorithms

Abstract Motivation A global medical crisis like the coronavirus disease 2019 (COVID-19) pandemic requires interdisciplinary and highly collaborative research from all over world. One of key challenges for is a lack interoperability among various heterogeneous data sources. Interoperability, standardization mapping datasets are necessary analysis applications in advanced algorithms such as developing personalized risk prediction modeling. Results To ensure compatibility COVID-19 datasets, we present here common model (CDM) which has been built 11 different geographical locations. The current version CDM holds 4639 variables related to basic patient information (age, biological sex diagnosis) well disease-specific variables, example, Anosmia Dyspnea. Each associated with specific types, variable mappings, value ranges, units encodings that could be used standardizing any dataset. Moreover, established standards OMOP FHIR makes well-designed interoperability. Availability implementation available public repo here: https://github.com/Fraunhofer-SCAI-Applied-Semantics/COVID-19-Global-Model. Supplementary at Bioinformatics online.