Search papers, labs, and topics across Lattice.
The paper introduces the Medical World Model (MeWM), a generative model for simulating tumor evolution under different treatment conditions to aid clinical decision-making. MeWM combines vision-language models as policy models to generate treatment plans with tumor generative models as dynamics models to simulate tumor progression/regression. By incorporating an inverse dynamics model based on survival analysis, MeWM can evaluate treatment efficacy and optimize individualized treatment protocols, demonstrating superior performance compared to medical-specialized GPTs and improving F1-score in selecting optimal treatment protocols by 13%.
Imagine a world where AI can simulate tumor growth under different treatments, helping doctors choose the best plan – this paper makes that vision a reality with a medical world model that outperforms even specialized GPTs.
Providing effective treatment and making informed clinical decisions are essential goals of modern medicine and clinical care. We are interested in simulating disease dynamics for clinical decision-making, leveraging recent advances in large generative models. To this end, we introduce the Medical World Model (MeWM), the first world model in medicine that visually predicts future disease states based on clinical decisions. MeWM comprises (i) vision-language models to serve as policy models, and (ii) tumor generative models as dynamics models. The policy model generates action plans, such as clinical treatments, while the dynamics model simulates tumor progression or regression under given treatment conditions. Building on this, we propose the inverse dynamics model that applies survival analysis to the simulated post-treatment tumor, enabling the evaluation of treatment efficacy and the selection of the optimal clinical action plan. As a result, the proposed MeWM simulates disease dynamics by synthesizing post-treatment tumors, with state-of-the-art specificity in Turing tests evaluated by radiologists. Simultaneously, its inverse dynamics model outperforms medical-specialized GPTs in optimizing individualized treatment protocols across all metrics. Notably, MeWM improves clinical decision-making for interventional physicians, boosting F1-score in selecting the optimal TACE protocol by 13%, paving the way for future integration of medical world models as the second readers.
