Nvidia and the Scripps Research Translational Institute today announced a collaboration to develop AI and deep learning best practices, tools and infrastructure to accelerate AI applications using genomic and digital health sensor data. Early efforts will focus on enhanced genetic and digital sensing prediction of atrial fibrillation, an irregular heartbeat which increases the risk of stroke, along with analytics of whole genome sequences.
“AI in medicine has tremendous promise,” said Eric Topol, the institute’s founder and director. “Eventually, it will markedly improve accuracy, efficiency, and workflow in medical practice with the potential to lower cost. But so much of this depends on validating AI algorithms and proving clinical efficacy. The data inputs from sensors and sequencing, in particular, will play an important role.”
Scripps and Nvidia plan to establish a center of excellence for AI genomics and digital sensors. Writing in a blog, Kimberly Powell, vice president of healthcare at NVIDIA, noted genomics data is doubling every seven months and that a key goal is developing deep learning approaches to help improve mutation detection and make genome sequencing more affordable and accessible.
“The astounding growth in genomics data is why the use of the data-hungry deep learning approach in genomic research papers has increased 40 times in the last four years,” Powell wrote. Likewise, the data output from medical sensors such as smartwatches, blood pressure cuffs and glucose monitors has skyrocketed. NVIDIA AI experts and Scripps researchers and clinicians will use deep learning and, more broadly, machine learning, to tackle the deluge of genomics and sensor data.
The Scripps Research Institute, of which the translational institute is a part, has long been at the forefront of biomedical research. It was ranked as the world’s most influential research institution on innovation by Nature last year, and is a leading participant in the All of US research program being run by NIH. The latter program seeks “to gather data over many years from one million or more people living in the United States, with the ultimate goal of accelerating research and improving health. Unlike research studies that are focused on a specific disease or population, All of Us will serve as a national research resource to inform thousands of studies, covering a wide variety of health conditions.”
Powell wrote, “The pioneering project — which includes a research cohort of more than 1 million U.S. participants — is the largest to study the intersection of biology, genetics, environment, data science and computation.”
Link to Nvidia blog: https://blogs.nvidia.com/blog/2018/10/23/nvidia-scripps-research-partner-ai-genomics-digital-health-sensors/
Link to Scripps announcement: https://www.scripps.edu/news-and-events/press-room/2018/20181023-nvidia-translation.html