Scripps and NVIDIA announce partnership to advance AI in health data

Scripps Research Translational Institute of La Jolla, CA, and NVIDIA, a global computing company, announced this week that they will team up to develop Artificial Intelligence practices and applications that integrate genomic and digital health sensor data. Using data inputs from genomic sequencing and commonly available sensors, the partnership will work toward validating and refining AI algorithms to drive the burgeoning AI analysis field forward.

The expanding popularity and accessibility of genomic and sensor data from sources such as 23 and Me, AncestryDNA, Fitbit, Apple, and continuous glucose monitors, has resulted in a wealth of health data in recent years that will be could be key to analyzing treatment effectiveness, creating personalized treatment, and overall population health trends if it is efficiently and effectively processed. Scripps and NVIDIA plan to research and apply machine learning and deep learning to the exploding amounts of data to improve health outcomes.

AI involves both machine learning and deep learning. Machine learning involves computers or machines learning by experience and building skills without human instruction or programming, while deep learning, a subset of machine learning, uses artificial neural networks and algorithms, inspired by human brain processes, to learn from large amounts of data. A deep learning algorithm, for example, would perform a task repeatedly, each time varying it slightly to improve the outcome. Such processes require huge amounts of data, the collection of which is predicted to continue to grow with the increasing popularity of wearables such as Fitbits and Apple Watches.

The partnership plans to establish a “center of excellence” for artificial intelligence in genomics and digital sensors with a mission of accelerating AI applications and leveraging genomics and sensor data to keep us healthier longer.

To begin the venture says that it will focus on heart rhythm disorders, using data from wearables. Scripps is already drawing on Fitbit data for part of the National Institutes of Health’s All of Us research program, intended to advance precision medicine and build a large-scale data set from 1 million participants, one of the largest scale data sets ever compiled. The team hopes to move on to study other conditions, such as high blood pressure and diabetes.

Explained Dr. Eric Topol, founder and director of the Scripps Research Translational Institute,

“AI in medicine has tremendous promise. 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.”