Generating Counterfactual Patient Timelines from Real-World Data

TL;DR

This paper introduces an autoregressive generative model trained on extensive real-world patient data to produce plausible counterfactual clinical trajectories, aiding personalized medicine and in silico trials.

Contribution

It demonstrates that such models can generate realistic counterfactual patient timelines and reproduce known clinical patterns from real-world data.

Findings

Counterfactual simulations showed increased mortality with older age, higher CRP, and impaired kidney function.

Simulations indicated increased remdesivir prescriptions with higher CRP and decreased with kidney issues.

Model validated by reproducing known clinical patterns in COVID-19 patient data.

Abstract

Counterfactual simulation - exploring hypothetical consequences under alternative clinical scenarios - holds promise for transformative applications such as personalized medicine and in silico trials. However, it remains challenging due to methodological limitations. Here, we show that an autoregressive generative model trained on real-world data from over 300,000 patients and 400 million patient timeline entries can generate clinically plausible counterfactual trajectories. As a validation task, we applied the model to patients hospitalized with COVID-19 in 2023, modifying age, serum C-reactive protein (CRP), and serum creatinine to simulate 7-day outcomes. Increased in-hospital mortality was observed in counterfactual simulations with older age, elevated CRP, and elevated serum creatinine. Remdesivir prescriptions increased in simulations with higher CRP values and decreased in those with impaired kidney function. These counterfactual trajectories reproduced known clinical patterns. These findings suggest that autoregressive generative models trained on real-world data in a self-supervised manner can establish a foundation for counterfactual clinical simulation.