Timezone: »

Learning to search efficiently for causally near-optimal treatments
Samuel HÃ¥kansson · Viktor Lindblom · Omer Gottesman · Fredrik Johansson

Wed Dec 09 09:00 PM -- 11:00 PM (PST) @ Poster Session 4 #1265

Finding an effective medical treatment often requires a search by trial and error. Making this search more efficient by minimizing the number of unnecessary trials could lower both costs and patient suffering. We formalize this problem as learning a policy for finding a near-optimal treatment in a minimum number of trials using a causal inference framework. We give a model-based dynamic programming algorithm which learns from observational data while being robust to unmeasured confounding. To reduce time complexity, we suggest a greedy algorithm which bounds the near-optimality constraint. The methods are evaluated on synthetic and real-world healthcare data and compared to model-free reinforcement learning. We find that our methods compare favorably to the model-free baseline while offering a more transparent trade-off between search time and treatment efficacy.

Author Information

Samuel HÃ¥kansson (Chalmers University of Technology)
Viktor Lindblom (Chalmers University of Technology)
Omer Gottesman (Harvard University)
Fredrik Johansson (Chalmers University of Technology)

More from the Same Authors