The NIH Common Fund’s Bridge to Artificial Intelligence (Bridge2AI) program launched to tackle biomedical challenges beyond human intuition. The program uses biomedical and behavioral research to generate artificial intelligence (AI) and machine learning (ML) models. Bridge2AI starts with an ‘analysis-first’ approach that uses machine-understandability of data and incorporates ethical principles surrounding data collection and use.  

“The overarching goal of the recently announced Bridge2AI awards is to generate richly detailed and balanced flagship data sets,” says NCI Imaging Data Commons (IDC) lead, Dr. Keyvan Farahani. “That includes functional genomics in cancer that are responsive to the needs of AI/ML research in several domains of biomedical and behavioral sciences.”

Studies suggest that AI has the potential to gather information pertaining to disease reoccurrence, with greater precision and speed than what humans currently can.

The NIH-wide effort pulled together diverse and cross-disciplinary teams to generate tools, resources, and richly detailed data that are responsive to AI approaches. Anyone interested in the resources for teams can register for the Bridge2AI Team Building Platform. Recordings of past team-building activities can be viewed on the NIH Common Fund website.

The Bridge2AI program strives to:

• create new flagship biomedical and behavioral data sets.
• develop software and standards to merge data attributes across data sources and data types.
• create automated tools to speed up the creation of FAIR (Findable, Accessible, Interoperable, and Reusable) data sets.
• provide resources to distribute data, ethical principles, tools, and best practices.
• create training materials and activities that connect the AI, biomedical, and behavioral research communities.