The second issue of the Artificial Intelligence series of the Stanford Medicine Magazine focuses on co-director Akshay Chaudhari’s work around developing synthetic data. The article describes how synthetic data can supplement incomplete datasets for underrepresented demographics to help minimize bias while addressing privacy concerns. 

Despite promising outlooks, Chaudhari remarks “it is critical to evaluate the performance of our methods on real datasets to understand what current gaps synthetic data can minimize and what gaps they maintain or even exacerbate. There is no shortcut to robust evaluation and validation.”  

Read more here: https://stanmed.stanford.edu/generative-ai-synthetic-data-promise/