In the December edition of the Association of American Cancer Institute’s Commentary, former NCI Director, Dr. Kimryn Rathmell, and NCI Deputy Director for Data Science and Strategy, Dr. Warren Kibbe, share their thoughts on the “Maximize Data Utility” goal of the National Cancer Plan and discuss the ways the institute is making data artificial intelligence (AI)-ready. Read the full article, and you’ll also see how NCI is translating knowledge into benefits for patients with cancer.

For data science to have the highest impact on cancer research, it’s important that data are ready for use with AI. Drs. Kibbe and Rathmell describe factors that help increase AI-readiness, enhance the value of cancer research data, and thereby maximize data utility.

Key Factors

• Cancer centers are integrating data science into every aspect of cancer research.
• Resources such as NCI Thesaurus, Metathesaurus, Enterprise Vocabulary Services, and the cancer Data Standards Repository are supporting well-defined data. This lays the groundwork for large scale data analysis.
• The availability of large data collections programs like The Cancer Imaging Archive or the Imaging Data Commons give you the ability to train and validate new analysis methods, make discoveries, and more.
• Data sharing across cancer research fields is expanding. Many deep learning methods such as large language models can now work with more complex data sets if they are well-annotated. Adding data sets to repositories like the Cancer Research Data Commons helps drive these developments.
• NCI prioritizes making data from government-sponsored research accessible and available to enable enhancements in cancer research.
• NCI is committed to training students and trainees in data science so that there’s a robust future workforce.
• Professionals across the field use cancer data from The Cancer Genome Atlas and the Childhood Cancer Data Initiative Molecular Characterization Initiative to improve precision oncology. Resources that enhance data accessibility help bring professionals from academia and industry together to drive innovation in cancer research and care.

Explore any of the tools mentioned above to help drive your own cancer research using data science.