The doc.ai team is bundled up and ready to head to Vancouver, Canada for the Thirty-third Annual Conference on Neural Information Processing Systems (NeurIPS). The purpose of the conference is to foster the exchange of research on neural information processing systems which benefits from a combined view of biological, physical, mathematical, and computational sciences. This conference brings together the best and brightest in the industry and we’re excited to be a part of it.
At doc.ai, we’re always looking for ways to use A.I. and machine learning to take into account our life data (what happens outside of your doctor’s visits) in an effort to accelerate medical research and ultimately transform approaches to care. It’s complex and requires a lot of data and model building. You can read more about A.I. at doc.ai here.
We will be participating in two presentations at NeurIPS. One of our core values at doc.ai is to develop and push forward A.I. research and techniques that build user privacy and ownership into the design of products. In the first presentation, Phil Dow, machine learning engineer at doc.ai will present some exciting developments we’ve made in a privacy-preserving technique called Federated Learning. The second doc.ai presentation will include an industry conversation with our CEO Walter DeBrower and Sandra Steyaert computational biologist at doc.ai about bridging the gap between effective algorithms and medical adoption.
Federated Learning in Healthcare
Sunday, Dec. 8 at 11:30 am at the Expo Hall Stage
Machine learning promises to revolutionize many industries, but its application is restricted to areas where there is enough data to train useful models. Often, the barriers to data acquisition are not technological but issues such as privacy, trust, regulatory compliance, and intellectual property. This is especially the case in healthcare, where patients and consumers expect privacy with respect to personal information and where organizations want to protect the value of their data and are also required to follow regulatory laws such as HIPAA in the United States and the GDRP in the Eurozone. Federated learning, which provides the ability to share a model without sharing the data used to train it, has the potential to address these concerns. This talk will explore the application of Federated Learning to problems in healthcare. We’ll examine two applications specifically: Federated Mobile Learning, which takes place in the consumer space where data is located on a user’s personal device, and Federated Cloud Learning, which focuses on business applications in which internal company data cannot be shared with other entities or even within an organization itself. We will also address some of the engineering and theoretical challenges of Federated Learning. Finally, we will conclude that Federated Learning is a viable approach to machine learning in the healthcare space that can address patient, business, and regulatory concerns with the application of privacy-preserving techniques.
Bridging the Gap Between Effective Algorithms and Medical Adoption
Sunday, Dec. 8 at 5:00 pm at the Expo Hall Stage
Deep learning in healthcare presents unparalleled opportunities to serve humanity through streamlining medical workflows, predicting patient outcomes, and guiding treatment decisions. But unlike enterprise or consumer products, clinical AI solutions face enormous regulatory, ethical, and legislative challenges.
We will discuss the challenges of deploying healthcare algorithms with respect to existing privacy laws and redefining what constitutes medical data. Hear the perspective from industry, academia, and government healthcare experts as they examine integration of social determinants, genomics, and lifestyle habits into models. These new opportunities raise legitimate concerns about trust, adoption, and unanticipated consequences.
If you’re attending NeurIPS please stop by our booth (#101) next to Google and Lyft in the Expo Hall for some hot chocolate and interesting conversation about shaping the future of health.
Additionally, we’re looking forward to seeing many of you at the doc.ai private party.
See you at NeurIPS.