Integrative data semantics through a model-enabled data stewardship

Wegner, Philipp; Schaaf, Sebastian; Uebachs, Mischa; Domingo‐Fernándéz, Daniel; Salimi, Yasamin; Gebel, Stephan; Sargsyan, Astghik; Birkenbihl, Colin; Springstubbe, Stephan; Klockgether, Thomas; Fluck, Juliane; Hofmann‐Apitius, Martin; Kodamullil, Alpha Tom

doi:10.1093/bioinformatics/btac375

Cited by 9 publications

(9 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To date, to our knowledge, there has been no automatic NLP-based harmonization of cohort studies conducted beyond standard string-matching techniques [10] or manual curation [40]. The application of such a standard technique (string-matching) led to relatively poor performance in the present study.…”

Section: Discussionmentioning

confidence: 88%

“…Such a data catalog did not address the available variables on a granular level and the variable harmonization aspect across cohort studies. Another study by Wegner et al (2022) established a semi-automatic DST using a string-matching technique for the harmonization of clinical datasets and applied it in the field of dementia [10]. However, despite previous efforts, there is currently no model or tool enabling fully automatic harmonization in the AD field.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Semantic harmonization of Alzheimer’s disease datasets using AD-Mapper

Wegner,

Balabin,

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

INTRODUCTIONDespite numerous past endeavors for the semantic harmonization of Alzheimer’s disease (AD) cohort studies, an automatic tool has yet to be developed. As cohort studies form the basis of data-driven analysis, harmonizing them is crucial for cross-cohort analysis. We aimed to accelerate this task by constructing an automatic harmonization tool.METHODSWe created a common data model (CDM) through cross-mapping data from 20 cohorts, three CDMs, and ontology terms, which was then used to fine-tune a BioBERT model. Finally, we evaluated the model using three previously unseen cohorts and compared its performance to a string-matching baseline model.RESULTSHere, we present our AD-Mapper interface for automatic harmonization of AD cohort studies, which outperformed a string-matching baseline on previously unseen cohort studies. We showcase our CDM comprising 1218 unique variables.DISCUSSIONAD-Mapper leverages semantic similarities in naming conventions across cohorts to improve mapping performance.

show abstract

Section: Discussionmentioning

confidence: 88%

Section: Introductionmentioning

confidence: 99%

Semantic harmonization of Alzheimer’s disease datasets using AD-Mapper

Wegner,

Balabin,

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…2210. 16649) [17]. In addition, the original cohort pseudonyms have been replaced and the random assignment to the new identifier is not stored.…”

Section: Creation Of the Synthetic Cohortmentioning

confidence: 99%

“…To enable a wide scientific community of ataxia researchers to browse and explore this integrated dataset in a first glance in SCAview, we had to shuffle the data due to data protection reasons and of partly unpublished data. Correlations and distributions within the created synthetic cohort are largely kept [17]. To ensure that no subject can be re-identified even with the creation of this synthetic version of a virtual cohort we did not include the study site in SCAview.…”

Section: Integrated Data Setmentioning

confidence: 99%

SCAview: an Intuitive Visual Approach to the Integrative Analysis of Clinical Data in Spinocerebellar Ataxias

et al. 2023

Self Cite

View full text Add to dashboard Cite

With SCAview, we present a prompt and comprehensive tool that enables scientists to browse large datasets of the most common spinocerebellar ataxias intuitively and without technical effort. Basic concept is a visualization of data, with a graphical handling and filtering to select and define subgroups and their comparison. Several plot types to visualize all data points resulting from the selected attributes are provided. The underlying synthetic cohort is based on clinical data from five different European and US longitudinal multicenter cohorts in spinocerebellar ataxia type 1, 2, 3, and 6 (SCA1, 2, 3, and 6) comprising > 1400 patients with overall > 5500 visits. First, we developed a common data model to integrate the clinical, demographic, and characterizing data of each source cohort. Second, the available datasets from each cohort were mapped onto the data model. Third, we created a synthetic cohort based on the cleaned dataset. With SCAview, we demonstrate the feasibility of mapping cohort data from different sources onto a common data model. The resulting browser-based visualization tool with a thoroughly graphical handling of the data offers researchers the unique possibility to visualize relationships and distributions of clinical data, to define subgroups and to further investigate them without any technical effort. Access to SCAview can be requested via the Ataxia Global Initiative and is free of charge.

show abstract

“…This CDM was built based on the GECCO—German Corona Consensus Dataset ( Sass et al, 2020 )—and extended with 10 other datasets collected globally. The CDM, in combination with the Data Steward Tool (DST) ( https://doi.org/10.1093/bioinformatics/btac375 ) ( Wegner et al, 2021 ), forms an end-to-end data standardization pipeline that can read data, standardize it with a common data standard (CDM) and then export it to well-established health IT formats such as FHIR via RESTful interfaces. Throughout the development, we used the DST to map data from different sources to (i) unify and standardize datasets to standard terminologies and ontologies, (ii) to further enrich the CDM with variable mappings and (iii) to map and compare with other global data standards like OMOP ( https://www.ohdsi.org/data-standardization/the-common-data-model/ ).…”

Section: Introductionmentioning

confidence: 99%

Common data model for COVID-19 datasets

Wegner

Jose²,

Lage-Rupprecht

et al. 2022

Bioinformatics

Self Cite

View full text Add to dashboard Cite

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

show abstract

Integrative data semantics through a model-enabled data stewardship

Cited by 9 publications

References 3 publications

Semantic harmonization of Alzheimer’s disease datasets using AD-Mapper

Semantic harmonization of Alzheimer’s disease datasets using AD-Mapper

SCAview: an Intuitive Visual Approach to the Integrative Analysis of Clinical Data in Spinocerebellar Ataxias

Common data model for COVID-19 datasets

Contact Info

Product

Resources

About