NIH's New AI Initiative Aims to Improve Integrative, Biomedical Research

NIH's New AI Initiative Aims to Improve Integrative, Biomedical Research

NCCIH outlines the potential Brain2AI has for biomedical and behavioral research.

The National Center for Complementary and Integrative Health is helping lead a new initiative at the National Institutes of Health to advance biomedical research with the adoption of artificial intelligence.

The initiative, called Brain2AI, is bringing technological and biomedical experts together to accomplish a variety of goals, including generating new ethical and trustworthy biomedical and behavioral data; developing software and standards to unify data attributes across various data sources and types; and creating automated tools to accelerate findable, accessible, interoperable and reusable data sets.

NCCIH spoke about Brain2AI during last week’s Integrative Medicine & Health Symposium, highlighting how the initiative, as well as AI as a whole, can sharpen integrative medical research and work around understanding salutogenesis — factors that support human health and wellbeing.

Integrative medicine and salutogenesis research involve the study of complex interconnection between the body’s system, which is typically difficult to do as it requires researchers to collect vast amounts of data in multiple systems over time, NCCIH Director Dr. Helene Langevin said. 

With AI, however, Langevin said that researchers can move away from the difficulty of trying to manually find trends across social, psychological and physiological systems and toward patterns that machines discover across those systems’ data.

“Computing methods using artificial intelligence can be trained to recognize patterns, and even better, to recognize changes in patterns over time, even when these are very complex,” Langevin said. “This can be tremendously helpful to explore complex phenomena.”

Biomedical and behavioral research has been able to collect vast amount of data across spatial and temporal scales, including genetics, tissue structure and function, and the whole person. NCCIH Extramural Research Division Program Director Lanay Mudd said this combination of mass data with improving capabilities in AI is making it possible for NIH to bridge the two together for improved research outcomes.

“We’re also experiencing a revolution in data analysis techniques with machine learning and other forms of artificial intelligence that can detect patterns and complex datasets and make connections and predictions beyond human intuition,” Mudd said. “We’re really ready to build a bridge across these different fields, and that’s what the Bridge2AI program aims to do to come up with a new AI/ML biomedical field where the biomedical experiments can be better designed for using these different techniques, and the techniques themselves can be refined for better use in biomedical experiments.”

While the biomedical and behavioral research community have already seen AI and ML uses across spaces like clinical care and some research programs, Bridge2AI will ensure that overall data used for research at NIH will be friendly for AI and ML use cases. This way, research in areas like salutogenesis that require a variety of data will be able to benefit from growth in AI and ML, Mudd said.

“The grand challenge … would be to use artificial intelligence to develop models that explain how bio, psycho, social networks change over time as an individual moves from a less healthy to a healthier state, with the long-term goal of eventually using these models to test salutogenic effects of non-drug interventions,” Langevin added.

As NIH launches Bridge2AI, it’s working toward releasing funding opportunities as early as June this year. 

NCCIH is partnering alongside the National Library of Medicine, National Eye Institute, National Human Genome Research Institute and National Institute of Biomedical Imaging and Bioengineering to approve and fund Bridge2AI’s work.

 
Standard