Ensuring fair, safe, and interpretable artificial intelligence-based prediction tools in a real-world oncological setting.

Renee GeorgeBenjamin EllisAndrew WestAlex GraffStephen WeaverMichelle AbramowskiKatelin BrownLauren KerrSheng-Chieh LuChristine SwisherChris Sidey-Gibbons

Published in: Communications medicine (2023)

Our algorithm demonstrates exceptional performance at predicting risk of 30-day ED visits. We confirm that model outputs are equitable and stable over time using a proactive monitoring approach.

Keyphrases

artificial intelligence
machine learning
deep learning
big data
emergency department
rectal cancer
radical prostatectomy
robot assisted