Model-agnostic meta-learners for estimating heterogeneous treatment effects over time
This work addresses the need for flexible methods to personalize treatment decisions over time in applications such as healthcare, representing an incremental extension of existing meta-learners from static to time-varying settings.
The paper tackles the problem of estimating heterogeneous treatment effects over time, which is crucial for fields like personalized medicine, by proposing model-agnostic meta-learners that can be used with arbitrary machine learning models, and it provides theoretical analysis and numerical experiments to validate the approach.
Estimating heterogeneous treatment effects (HTEs) over time is crucial in many disciplines such as personalized medicine. For example, electronic health records are commonly collected over several time periods and then used to personalize treatment decisions. Existing works for this task have mostly focused on model-based learners (i.e., learners that adapt specific machine-learning models). In contrast, model-agnostic learners -- so-called meta-learners -- are largely unexplored. In our paper, we propose several meta-learners that are model-agnostic and thus can be used in combination with arbitrary machine learning models (e.g., transformers) to estimate HTEs over time. Here, our focus is on learners that can be obtained via weighted pseudo-outcome regressions, which allows for efficient estimation by targeting the treatment effect directly. We then provide a comprehensive theoretical analysis that characterizes the different learners and that allows us to offer insights into when specific learners are preferable. Finally, we confirm our theoretical insights through numerical experiments. In sum, while meta-learners are already state-of-the-art for the static setting, we are the first to propose a comprehensive set of meta-learners for estimating HTEs in the time-varying setting.