Researchers Partner With NIH, Google to Develop AI Learning Modules

Researchers at the University of Arkansas will collaborate with the National Institutes of Health (NIH) and Google to develop software and cloud-based artificial intelligence (AI) modules for biomedical research. 

Working with large biomedical image datasets is key for identifying unique image features and predicting disease, but utilizing such large datasets is difficult without the use of advanced technologies such as AI and cloud computing. Thus, the goal of the project is to help researchers and clinicians understand how to implement these technologies into their work. 

The modules are designed to help educate biomedical researchers on how AI and machine learning (ML) have the potential to streamline and enhance data analysis, particularly for various types of medical images. The latest funding for the project, which totals $140,135, was awarded via the NIH’s National Institute of General Medical Sciences’ (NIGMS) Institutional Development Award Program.

University researchers will partner with software engineers at Google and NIGMS to explore the computational requirements of AI-driven biomedical research and address these using cloud computing, according to the press release. The researchers have chosen to utilize cloud computing because it allows computing services to be accessed over the internet, which will support faster and more flexible biomedical research solutions.

“Big data is transforming health and biomedical science,” said Justin Zhan, PhD, professor of data science at the University of Arkansas, in the press release. “The new technology is rapidly expanding the quantity and variety of imaging modalities, for example, which can tell doctors so much more about their patients. But this transformation has created challenges, particularly with storing and managing massive data sets. Also, while the big data revolution transforms biology and medicine into data-driven sciences, traditional education is responding slowly. Addressing this shortcoming is part of what we’re trying to do.”

Under the collaboration, the researchers will use the resources and technical expertise provided by project partners to train students and healthcare professionals on the use of AI and ML in relation to biomedical research. The press release states that the modules developed by the research team will help these groups understand how AI can be used in biomedical sciences to analyze big data, especially imaging data.

The project’s grant is administered by the Arkansas IDeA Network of Biomedical Research Excellence at the University of Arkansas for Medical Sciences, and case studies for the learning modules are set to be developed using the data science and the imaging and spectroscopy cores of the Arkansas Integrative Metabolic Research Center.  

This federal funding award is the latest in a string of grants provided by the NIH, highlighting the agency’s interest in AI research.

In May, the NIH awarded $68 million to PostEra, a biotechnology company specializing in ML for preclinical drug discovery, as part of an ongoing effort to develop antiviral drugs to help prevent the next pandemic.