Qianfang: a type-safe and data-driven healthcare system starting from Traditional Chinese Medicine

05/05/2022 3:36 pm - 5:36 pm

Abstract: Although everyone talks about AI + healthcare, many people were unaware of the fact that there are two possible outcomes of the collaboration, due to the inherent dissimilarity between the two giant subjects. The first possibility is healthcare-leads, and AI is for building new tools to make steps in healthcare easier, better, more effective or more accurate. The other possibility is AI-leads, and therefore the protocols of healthcare can be redesigned or redefined to make sure that the whole infrastructure and pipelines are ideal for running AI algorithms.

Our system Qianfang belongs to the second category. We have designed a new kind of clinic for the doctors and patients, so that it will be able to collect high quality data for AI algorithms. Interestingly, the clinic is based on Traditional Chinese Medicine (TCM) instead of modern medicine, because we believe that TCM is more suitable for AI algorithms as the starting point.

In this talk, I will elaborate on how we convert TCM knowledge into a modern type-safe large-scale system, the mini-language that we have designed for the doctors and patients, the interpretability of AI decisions, and our feedback loop for collecting data.

Our project is still on-going, not finished yet.Bio: Yang Yuan is now an assistant professor at IIIS, Tsinghua. He finished his undergraduate study at Peking University in 2012. Afterwards, he received his PhD at Cornell University in 2018, advised by Professor Robert Kleinberg. During his PhD, he was a visiting student at MIT/Microsoft New England (2014-2015) and Princeton University (2016 Fall). Before joining Tsinghua, he spent one year at MIT Institute for Foundations of Data Science (MIFODS) as a postdoc researcher. He now works on AI+Healthcare, AI Interpretability and AI system.