Title: Real-World Evidence Generative Modeling:  A Deep Generative Model for Clinical Evidence Generation

 

 

Abstract: Current GPTs and NLPs have not yet focused on generating causal evidence from Real-World Data (RWD). Here, we develop the very first generative pretrained transformer (GPT) model designed specifically for RWD with negative control outcome (NCO) powered debiasing capability.  Our model is a generalist for Real World Evidence (RWE) generation by first pretraining on large datasets and then fine-tuning on small but relevant cohorts.