AI and machine learning play an important role in our daily lives, but there is often a lack of transparency associated to how the models work and what inputs were provided to train them. Model cards, a “nutrition label” for machine learning models, are one easy-to-implement way to begin addressing this challenge and bring more visibility to the public on how predictive models are being used to impact them.

A story of how we used computer vision and unsupervised machine learning to identify novel patterns in breast cancer tumor tissue sample images.