Tag
This paper presents an online adaptive clinical decision support AI system that integrates treatment effect estimation, digital twin simulation, and reinforcement learning to recommend treatments in a safe, clinician-supervised manner, validated on a synthetic simulator and the TCGA ovarian cancer dataset.
This paper addresses the challenge of estimating individual treatment effects from graph data by modeling differentiated networked effects, proposing a mechanism with partial attention and a message amplifier to capture varying neighbor importance and scale. Experiments show improved performance over existing methods.