Maximize Data Utility - National Cancer Plan
A wealth of clinical, genomic, and other health data is collected from patients each day. Ensuring patient privacy and improving data sharing could make these data more readily accessible to researchers, who can use them to find connections or see trends and patterns that could accelerate their research.
The State of Maximizing Data Utility Today
Cancer research data may come from experiments, clinical trials, electronic health records (EHRs), and other sources. EHRs, for example, allow a range of patients to provide data from routine clinical care. With EHRs, it is now possible to directly engage patients in data sharing, respect their wishes for how their data are used, and return results to them. However, issues with how data from EHRs are collected and formatted still limit how much they are used in research.
Additionally, new software tools are revolutionizing how we collect, organize, and use data for biomedical research. For example, machine learning algorithms can identify patterns in large, complex datasets and evaluate the likely outcomes of different treatments. However, machine learning tools are only as good as the data they are trained on, so they must be powered by accurate and reliable data that represents the diversity of all of society.
Creating a national data ecosystem for equitably and responsibly collecting and sharing cancer data will also enable scientists and research participants to contribute, access, combine, and analyze diverse data related to cancer.
Strategies to Maximize Data Utility
- Provide structure to enable data sharing throughout cancer research and build tools that make it easier to use and analyze data to achieve rapid progress.
- Build and maintain a secure Cancer Research Data Ecosystem that protects patient privacy while collecting, standardizing, and providing access to a broad range of research data.
- Develop data quality standards, metrics, and practices to promote the use of routine health care data more in research.
- Engage patients directly in data sharing and respect their wishes for data use.
- Return individual and study results to research participants.
- Enable underserved communities and health care organizations with limited resources to engage with and benefit from available data and related scientific advances.
Examples of NCI-Supported Research to Achieve This Goal
- NCI is collaborating with the childhood cancer community to improve how childhood cancer data is collected, connected, and shared to speed up research through the Childhood Cancer Data Initiative.
- A cloud-based data infrastructure called the NCI Cancer Research Data Commons connects collections of cancer data with tools to help analyze that data.
- Projects like Accelerating Therapeutics for Opportunities in Medicine involve NCI and the Department of Energy working together to use AI, high-performance computing, and biomedical data to accelerate drug development.