Patient level simulation and reinforcement learning to discover novel strategies for treating ovarian cancer
This work addresses the need for improved survival strategies in ovarian cancer treatment, but it is incremental as it applies existing reinforcement learning methods to a new medical domain.
The researchers tackled the problem of poor prognosis in epithelial ovarian cancer by using reinforcement learning on real-world data to discover novel treatment strategies, resulting in a simulation environment that models patient treatment trajectories.
The prognosis for patients with epithelial ovarian cancer remains dismal despite improvements in survival for other cancers. Treatment involves multiple lines of chemotherapy and becomes increasingly heterogeneous after first-line therapy. Reinforcement learning with real-world outcomes data has the potential to identify novel treatment strategies to improve overall survival. We design a reinforcement learning environment to model epithelial ovarian cancer treatment trajectories and use model free reinforcement learning to investigate therapeutic regimens for simulated patients.