aiqbench analysis
This research reframes cancer treatment as a belief-space planning problem using active inference, addressing the unique challenge where therapies alter patient transition dynamics rather than just controlling state trajectories. By unifying goal-directed control with information acquisition under strict measurement budgets, the framework achieves simultaneous patient categorization and high efficacy on real clinical data from the AACR Project GENIE. The approach offers a principled alternative to standard Reinforcement Learning for sequential decision-making in medical contexts with partial observability and latent heterogeneity.
Belief-Space Control for Personalized Cancer Treatment via Active Inference
arXiv:2606.10376v1 Announce Type: new Abstract: Cancer treatment is at the core a sequential decision-making problem with partial observability, latent patient heterogeneity, and explicit constraints on the budget for medical measurements. Unlike standard Reinforcement Learning (RL) approaches that control state trajectories, cancer treatments permanently modify patients' transition dynamics, changing how states evolve over time. We model cancer treatment as a belief-space planning problem using active inference, deriving an expected free-energy objective that unifies goal-directed control and information acquisition under measurement budgets without. We implement this framework using real clinical cancer data from the AACR Project GENIE Biopharma Collaborative dataset. Results on clinical data demonstrate a simultaneous patient categorization and high treatment efficacy, under real measurement and treatment constraints.
Abstract:Cancer treatment is at the core a sequential decision-making problem with partial observability, latent patient heterogeneity, and explicit constraints on the budget for medical measurements. Unlike standard Reinforcement Learning (RL) approaches that control state trajectories, cancer treatments permanently modify patients' transition dynamics, changing how states evolve over time. We model cancer treatment as a belief-space planning problem using active inference, deriving an expected free-energy objective that unifies goal-directed control and information acquisition under measurement budgets without. We implement this framework using real clinical cancer data from the AACR Project GENIE Biopharma Collaborative dataset. Results on clinical data demonstrate a simultaneous patient categorization and high treatment efficacy, under real measurement and treatment constraints.
Artificial Intelligence (cs.AI)
arXiv:2606.10376 [cs.AI]
(or arXiv:2606.10376v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.10376 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 206 words
