Generating Counterfactual Patient Timelines from Real-World Data
This work provides a method for generating counterfactual clinical timelines from real-world data, which could enable personalized medicine and in silico trials, but the validation is limited to reproducing known patterns without quantitative comparison to ground truth.
The authors trained an autoregressive generative model on real-world data from over 300,000 patients and 400 million timeline entries to generate clinically plausible counterfactual patient trajectories. The model reproduced known clinical patterns, such as increased mortality with older age and elevated biomarkers, and appropriate medication adjustments in COVID-19 patients.
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.