A multiagent large language model-based system to simulate the liver transplant selection committee: a retrospective cohort study
Key Points
This research aims to explore the use of a multiagent language model system to simulate the liver transplant selection committee's decision-making process.
Developed a multiagent language model-based system
Conducted a retrospective cohort study
Analyzed the decision-making process of the selection committee
The AI model effectively mimicked the committee's decisions
Demonstrated potential improvements in the transparency of selection processes
Highlighted areas for enhanced decision quality in liver transplant allocations
Abstract
Transplant AI Initiative, Ajmera Transplant Centre, University Health Network.