Synergies between centralized and federated approaches to data quality: a report from the national COVID cohort collaborative

OBJECTIVE

In response to COVID-19, the informatics community united to aggregate as much clinical data as possible to characterize this new disease and reduce its impact through collaborative analytics. The National COVID Cohort Collaborative (N3C) is now the largest publicly available HIPAA limited dataset in US history with over 6.4 million patients and is a testament to a partnership of over 100 organizations.

MATERIALS AND METHODS

We developed a pipeline for ingesting, harmonizing, and centralizing data from 56 contributing data partners using 4 federated Common Data Models. N3C data quality (DQ) review involves both automated and manual procedures. In the process, several DQ heuristics were discovered in our centralized context, both within the pipeline and during downstream project-based analysis. Feedback to the sites led to many local and centralized DQ improvements.

RESULTS

Beyond well-recognized DQ findings, we discovered 15 heuristics relating to source Common Data Model conformance, demographics, COVID tests, conditions, encounters, measurements, observations, coding completeness, and fitness for use. Of 56 sites, 37 sites (66%) demonstrated issues through these heuristics. These 37 sites demonstrated improvement after receiving feedback.

DISCUSSION

We encountered site-to-site differences in DQ which would have been challenging to discover using federated checks alone. We have demonstrated that centralized DQ benchmarking reveals unique opportunities for DQ improvement that will support improved research analytics locally and in aggregate.

CONCLUSION

By combining rapid, continual assessment of DQ with a large volume of multisite data, it is possible to support more nuanced scientific questions with the scale and rigor that they require.

Implementation of a learning healthcare system for sickle cell disease

Objective

Using sickle cell disease (SCD) as a model, the objective of this study was to create a comprehensive learning healthcare system to support disease management and research. A multidisciplinary team developed a SCD clinical data dictionary to standardize bedside data entry and inform a scalable environment capable of converting complex electronic healthcare records (EHRs) into knowledge accessible in real time.

Materials and Methods

Clinicians expert in SCD care developed a data dictionary to describe important SCD-associated health maintenance and adverse events. The SCD data dictionary was deployed in the EHR using EPIC SmartForms, an efficient bedside data entry tool. Additional data elements were extracted from the EHR database (Clarity) using Pentaho Data Integration and stored in a data analytics database (SQL). A custom application, the Sickle Cell Knowledgebase, was developed to improve data analysis and visualization. Utilization, accuracy, and completeness of data entry were assessed.

Results

The SCD Knowledgebase facilitates generation of patient-level and aggregate data visualization, driving the translation of data into knowledge that can impact care. A single patient can be selected to monitor health maintenance, comorbidities, adverse event frequency and severity, and medication dosing/adherence.

Conclusions

Disease-specific data dictionaries used at the bedside will ultimately increase the meaningful use of EHR datasets to drive consistent clinical data entry, improve data accuracy, and support analytics that will facilitate quality improvement and research.