The European League Against Rheumatism (EULAR) developed recommendations to provide a framework for the collection, analysis, and use of big data, including clinical, biological, social, imaging, and environmental, in rheumatic and musculoskeletal diseases (RMDs), according to a report published in Annals of Rheumatic Diseases.

To address the main questions about data sources and collection, analysis, and data interpretation and implementation of findings, a multidisciplinary task force of 14 international experts from 8 European countries was assembled. A systematic literature review of big data in RMDs followed by task force meetings led to the development of evidence- and consensus-based overarching principles and points to consider. The final manuscript was reviewed and approved by all members of the task force and the EULAR Executive Committee.

Researchers indicated that the target audience for these recommendations include researchers in the field of big data in RMDs, data collection organizations and/or groups collecting data, data analysts, patients at risk for and with RMDs, patient associations, and stakeholders such as research organizations, funding agencies, policymakers, authorities, governments, and medical societies.

On the basis of a review of published literature, the term “big data” was defined as “extremely large datasets, which may be complex, multidimensional, unstructured and from heterogeneous sources, and which accumulate rapidly”; computational technology, including artificial intelligence can be applied to big data.


Continue Reading

The overarching principles and points to consider included a level of agreement rated by the task force on a scale of 0 to 10, and level of evidence and strength of recommendation were rated from level 1 to 5 based on the Oxford Center for Evidence-Based Medicine classification.

Overarching Principles

· Ethical issues, including privacy, confidentiality and security, identity, and transparency, are the key principles to consider for all big data use. This was noted to be a regulatory and legal requirement as well.

· Big data provides unprecedented opportunities for transformative discoveries in RMD research and practice and for cross-use of such discoveries in other medical fields.

· The ultimate goal of big data in RMDs is to improve and benefit the health, lives, and care of patients, including health promotion and assessment, prevention, diagnosis, treatment, and monitoring of disease; this is a key priority of the EULAR.

Points to Consider

1. Data Collection – Use of Standards

The use of global, harmonized and comprehensive standards should be promoted to facilitate interoperability of big data.

2. Data Collection and Storage – FAIR Principle

Big data should be based on the Findable, Accessible, Interoperable and Reusable (FAIR) principle, which refers to standardization, interoperability, and data storage.

3. Data Storage – Data Platforms

For big data in RMDs, data platforms that allow public access should be preferred, to promote open and reproducible research, particularly when data were made possible by private funding.

4. Privacy by Design

Privacy by design should be applied to the collection, processing, storage, analysis, and interpretation of big data.

5. Collaboration

For big data projects, the task force recommended interdisciplinary collaboration between appropriate stakeholders, including biomedical, health, and life scientists, computational and/or data scientists, clinicians and health professionals, and patients.

6. Data Analyses Reporting

Methods used to analyze big data should be reported explicitly and transparently in scientific publications. The task force recommended proper reporting to avoid confusion and promote reproducibility.

7. Benchmarking of Data Analyses

Researchers recommended benchmarking of computational methods for the use of big data in RMD research because it allows for the comparison of artificial intelligence methods in RMDs.

Related Articles

8. Validation of Big Data Findings

Before implementation, conclusions and/or models derived from big data should be independently validated to overcome current biases and limitations and assure scientific soundness.

9. Implementation of Findings

Clinical implementation of findings should be proactively considered at the earliest opportunity by researchers using big data.

10. Training

According to the task force, as a result of the rapid changes in the field, interdisciplinary training on big data methods in RMDs for clinicians/health professionals/health and life scientists and data scientists must be encouraged among academic institutions, public research bodies, and international organizations.

“In conclusion, it is anticipated that new data in this rapidly moving field will emerge over the next few years and that some of the questions formulated in the research agenda will be answered. Therefore, we will consider an update of these [points to consider] as needed in a few years,” the researchers concluded.

Disclosure: Several study authors declared affiliations with the pharmaceutical industry. Please see the original reference for a full list of authors’ disclosures.

Reference

Gossec L, Kedra J, Servy, H et al. EULAR points to consider for the use of big data in rheumatic and musculoskeletal diseases. Ann Dis Rheum. 2020;79:69-76.