NVIDIA’s Mona Flores: How Medical AI and Federated Learning Power Innovation

What if machine learning and data scattered around the world held the keys to the cures for a variety of rare or new diseases? Until recently, it was often nearly impossible to use that data, due in part to the data privacy restrictions in place around the world. That’s starting to change, thanks to federated learning and the innovative work of doctors such as Mona Flores, head of medical AI at NVIDIA.

"Being able to show that we can use federated learning and still protect privacy will really change what we can do with AI and ML in medicine, and will spearhead many advancements to come,” she says.

Dr. Flores is a surgeon who has done ground-breaking work in applications of medical AI, including a federated learning pilot at 20 hospitals that proved the advantages of using federated learning with privacy-protected data to train models to recognize diseases such as COVID-19. The result? The ability to predict which treatments will be needed, and where, which helped shape decisions about where and when to deploy lifesaving treatments.

Domino Interviews Flores and Other Top Innovators

Domino recently interviewed Flores for our new ebook, The Data Science Innovator’s Playbook, which covers the rise of data science in fueling innovation, a story told through interviews with seven top data science innovators chosen by their peers at Rev 3 in May. She’s one of three featured medical innovators, and the only one who’s an accomplished surgeon in addition to spearheading advances in the field of medical data science.

All of these innovators are tackling some of the world’s toughest problems, many of which—such as COVID—present particularly difficult challenges to the healthcare profession. But, says Flores, new tools are strengthening data science, so the rising discipline is increasingly able to handle whatever challenges the world throws at it.

And when it comes to healthcare, one of the difficulties data scientists and medical researchers face is how to use patient data in a way that protects privacy, meets regulatory laws and guidelines, and helps to train machine learning models whose results can spell new cures and better outcomes for potentially millions of patients. Federated learning shows great promise in this area, and will doubtless continue to fuel new innovation in healthcare and in many other fields.

Learn more from Dr. Mona Flores, M.D., and how NVIDIA is helping overcome these challenges.

Other Featured Innovators Weigh in on Data Science’s Ascendancy

The free ebook discusses many data science innovations and also includes career advice and perspectives about changing roles in data science. Download the The Data Science Innovator’s Playbook to read more of insights from Flores, as well as many other themes, strategies, tactics and insights from:

• Cassie Kozyrkov—Chief Decision Scientist, Google
• Andy Nicholls—Senior Director, Head of Statistical Data Sciences, GSK plc
• Robert Nishihara—Co-creator of Ray, and Co-founder & CEO, Anyscale
• John K. Thompson—Analytics Thought Leader, Best-selling Author, Innovator in Data & Analytics
• Glenn Hofmann—Chief Analytics Officer, New York Life Insurance Co.