Creating an artificial intelligence (AI) model for a healthcare application which works well at multiple institutions typically requires a large collection of training data acquired from varied sources. Obtaining such large and varied healthcare training datasets can be difficult given the sensitive nature of medical data. Beginning in early 2022, AI-LAB users will be able to participate in federated learning (FL) through AI-LAB to help mitigate these issues. FL enables data from multiple institutions to be used for AI model training without data leaving institutional firewalls. This is accomplished by sharing AI models, not sensitive data, with participating institutions. As the COVID-19 pandemic is still ongoing globally, the inaugural AI-LAB FL experiment will aim to create a COVID-19 classification model which has robust performance across multiple institutions.
External News Article:
Add reference to external site news article