TRIALSCOPE - A Framework for Clinical Trial Simulation from Real-World Data

The rapid digitization of real-world data presents an unprecedented opportunity to optimize health care delivery and accelerate biomedical discovery. However, these data are often found in unstructured forms, such as clinical notes in electronic medical records (EMRs), and are typically plagued by confounders, making it challenging to generate robust real-world evidence (RWE). Therefore, we present TRIALSCOPE, a framework designed to distill RWE from population-level observational data at scale.

TRIALSCOPE leverages biomedical language models to structure clinical text at scale, employs advanced probabilistic modeling for denoising and imputation, and incorporates state-of-the-art causal inference techniques to address common confounders in treatment effect estimation.

Extensive experiments were conducted on a large-scale dataset of over 1 million cancer patients from a single large health care network in the United States. TRIALSCOPE was shown to automatically curate high-quality structured patient data, expanding the dataset and incorporating key patient attributes only available in unstructured form. The framework reduces confounding in treatment effect estimation, generating comparable results with randomized controlled lung cancer trials. In addition, we demonstrate simulations of unconducted clinical trials - including a pancreatic cancer trial with varying eligibility criteria - using a suite of validation tests to ensure robustness. Thorough ablation studies were conducted to better understand key components of TRIALSCOPE and establish best practices for RWE generation from EMRs.

TRIALSCOPE was able to extract cancer treatment data from EMRs, overcoming limitations of manual curation. We were also able to show that TRIALSCOPE could reproduce the results of lung and pancreatic cancer clinical trials from the extracted real-world data.