Enhancing Gen3 for clinical trial time series analytics and data discovery: a data commons framework for NIH clinical...

Area of Science:

• Biomedical Informatics
• Clinical Research Informatics
• Data Science

Background:

• Clinical trial data requires robust management and analysis for longitudinal studies.
• Existing data commons platforms may lack advanced temporal visualization capabilities.
• Ensuring data Findability, Accessibility, Interoperability, and Reusability (FAIR) is critical for clinical research.

Purpose of the Study:

• To present a framework for enhancing the Gen3 open-source data commons with temporal visualization.
• To enable standardized analytics for longitudinal clinical trial data.
• To support real-time monitoring of outcomes in multi-site research networks.

Main Methods:

• Implementation of a cloud-native architecture using Kubernetes for container orchestration.
• Integration of Kibana for temporal analytics and visualization.
• Development of automated Extract, Transform, Load (ETL) pipelines for data harmonization.
• Adherence to FAIR data principles throughout the framework.

Main Results:

• Successful technical validation of handling diverse time-based data structures with temporal precision.
• Demonstrated ability to maintain measurement context within longitudinal data.
• Framework implemented in NIH HEAL Initiative networks for chronic pain and substance use disorder research.

Conclusions:

• The developed framework enhances Gen3 with crucial temporal visualization capabilities for clinical trials.
• This provides a scalable model for research networks to improve data commons functionality and FAIR data compliance.
• Facilitates real-time monitoring of longitudinal outcomes across multiple clinical trials.