Multi-treatment Effect Estimation from Biomedical Data
This addresses treatment effect estimation in biomedical data, but appears incremental as it builds on existing multi-task learning methods.
The paper tackles the problem of estimating effects of multiple treatments applied simultaneously, proposing the M3E2 model that handles continuous and binary treatments with many covariates, and shows superior performance in synthetic benchmarks.
This work proposes the M3E2, a multi-task learning neural network model to estimate the effect of multiple treatments. In contrast to existing methods, M3E2 can handle multiple treatment effects applied simultaneously to the same unit, continuous and binary treatments, and many covariates. We compared M3E2 with three baselines in three synthetic benchmark datasets: two with multiple treatments and one with one treatment. Our analysis showed that our method has superior performance, making more assertive estimations of the multiple treatment effects.